WO2002043352A2 - System and method for object identification and behavior characterization using video analysis - Google Patents

System and method for object identification and behavior characterization using video analysis Download PDF

Info

Publication number
WO2002043352A2
WO2002043352A2 PCT/US2001/043282 US0143282W WO0243352A2 WO 2002043352 A2 WO2002043352 A2 WO 2002043352A2 US 0143282 W US0143282 W US 0143282W WO 0243352 A2 WO0243352 A2 WO 0243352A2
Authority
WO
WIPO (PCT)
Prior art keywords
behavior
video
image
foreground
mouse
Prior art date
Application number
PCT/US2001/043282
Other languages
French (fr)
Other versions
WO2002043352A3 (en
Inventor
Yiqing Liang
Linda Crnic
Vikrant Kobla
Wayne Wolf
Original Assignee
Clever Sys. Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Family has litigation
First worldwide family litigation filed litigation Critical https://patents.darts-ip.com/?family=24885865&utm_source=google_patent&utm_medium=platform_link&utm_campaign=public_patent_search&patent=WO2002043352(A2) "Global patent litigation dataset” by Darts-ip is licensed under a Creative Commons Attribution 4.0 International License.
Application filed by Clever Sys. Inc. filed Critical Clever Sys. Inc.
Priority to EP01987014A priority Critical patent/EP1337962B9/en
Priority to JP2002544950A priority patent/JP2004514975A/en
Priority to AU2002239272A priority patent/AU2002239272A1/en
Publication of WO2002043352A2 publication Critical patent/WO2002043352A2/en
Publication of WO2002043352A3 publication Critical patent/WO2002043352A3/en

Links

Classifications

    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
    • A01K1/00—Housing animals; Equipment therefor
    • A01K1/02—Pigsties; Dog-kennels; Rabbit-hutches or the like
    • A01K1/03—Housing for domestic or laboratory animals
    • A01K1/031—Cages for laboratory animals; Cages for measuring metabolism of animals
    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
    • A01K29/00—Other apparatus for animal husbandry
    • A01K29/005—Monitoring or measuring activity, e.g. detecting heat or mating
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1113—Local tracking of patients, e.g. in a hospital or private home
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1116—Determining posture transitions
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1118—Determining activity level
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
    • A61B5/1128—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique using image analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/40—Detecting, measuring or recording for evaluating the nervous system
    • A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
    • A61B5/4094—Diagnosing or monitoring seizure diseases, e.g. epilepsy
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G06V40/23—Recognition of whole body movements, e.g. for sport training
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2503/00—Evaluating a particular growth phase or type of persons or animals
    • A61B2503/40—Animals
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2503/00—Evaluating a particular growth phase or type of persons or animals
    • A61B2503/42—Evaluating a particular growth phase or type of persons or animals for laboratory research
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing

Definitions

  • the invention relates generally to object identification and recognition. More particularly, one aspect of the invention is directed to monitoring and characterization of an object in an image, for example an animal or a person, using video analysis.
  • Video analysis has developed over the past few decades to become an integral part of machine operations in manufacturing using machine automation.
  • video object recognition and pattern recognition has been used to orient and align various pieces of a product for machining and assembly in various manufacturing industries.
  • One such use is in the manufacturing of semiconductor integrated circuits and microelectronic packaging, h this case, pattern recognition has made great inroads because the size of the work product is microscopic and orientation and alignment of the work product is thus far too tedious for a human being to do consistently and accurately over a large number of pieces.
  • military has carried out research to use video to track moving targets such as tanks and vehicles, in the scene. Other positioning instruments such as global positioning system will be used to assist such tracking.
  • Another application for video analysis is monitoring animal activity in laboratory testing for the pharmaceutical and biological sciences.
  • One particular area is monitoring animal behavior to determine the effects of various new drugs or gene changes on a particular type of animal.
  • One such animal used in laboratory testing is the mouse.
  • Model organisms are an important tool for understanding and dissecting human disease and biological process. Because mice and humans share many of the same fundamental biological and behavioral processes, this animal is one of the most significant laboratory models for human disease and studying biological processes in mammals.
  • Adding a time line for the locus of mouse point is all they can offer.
  • Other animal location type systems used to monitor animal motion include those described in U.S. Pat. Nos. 3,100,473; 3,803,571; 3,974,798; 4,337,726; 4,574,734; and 5,816,256.
  • the other systems in the field are the systems that identify individual behavior using video.
  • the existing video analysis systems e.g. Noldus Observer/Ethovision, Sterling, VA; HVS Image, Hampton, UK; AccuScan Instruments Inc.'s VideoScan2000 System; and San Diego Instruments Poly-Track system, San Diego, CA
  • Digitized images from video are used to capture the body of mouse and provide quantitative data about the position and movements of the animal and the pattern of these variables across time. They do not just treat the animal (e.g., mouse) as a point in the space. Instead, they handle it as a block of pixels. More information is preserved. However, they can only make use of a few simple features. For example, the mass center of the animal (e.g., mouse) is calculated and used as a means for tracking the animal (e.g., a mouse). As such, a lot of information that is critical to identify the animal's behaviors such as different postures, positions of portions of the animal's body such as limbs, is lost. These systems can only distinguish basic behaviors such as locomotion, and cannot automatically identify simple animal postures such as eating, rearing, and jumping, not to mention complex behaviors such as skilled reaching. Such behavior identification requires human intervention and input.
  • the Noldus Observer system has a video camera, TV monitor, a high end VCR, and a PC system, all hooked together.
  • the camera takes video footage of the mouse in a cage. This video is recorded on videotape, digitized, input into the PC system, and displayed on the computer monitor.
  • the human observer can control the recorded video that is displayed, the human observer still needs to look at the animal on the screen, decide which behavior the animal is engaged in, and enter (by typing) the information into a mechanism provided by the system for storage and later analysis. While this system facilitates observation of behavior, it does not automate it, and is thus prone to human error and extremely labor intensive.
  • the tasks of coding behavior throughout the day and building a profile of behavior for different types of animals and different strains of the same animal e.g., different strains of mouse
  • the present invention is directed to systems and methods for finding patterns of behaviors and/or activities of an object using video.
  • the invention includes a system with a video camera connected to a computer in which the computer is configured to automatically provide object identification, object motion tracking (for moving objects), object shape and posture classification, and behavior identification.
  • the present invention is capable of automatically monitoring a video image to identify, track and classify the actions of various obj ects and their movements.
  • the video image may be provided in real time from a camera and/or from a storage location.
  • the invention is particularly useful for monitoring and classifying animal behavior for testing drugs and genetic mutations, but may be used in any of a number of surveillance or other applications.
  • the invention includes a system in which an analog video camera and a video record/playback device (e.g., VCR) are coupled to a video digitization/compression unit.
  • the video camera may provide a video image containing an object to be identified.
  • the video digitization/compression unit is coupled to a computer that is configured to automatically monitor the video image to identify, track and classify the actions of the object and its movements over time within a sequence of video session image frames.
  • the digitization/compression unit may convert analog video and audio into, for example, MPEG or other formats.
  • the computer may be, for example, a personal computer, using either a Windows platform or a Unix platform, or a Macintosh computer and compatible platform.
  • the computer is loaded and configured with custom software programs (or equipped with firmware) using, for example, MATLAB or C/C++ programming language, so as to analyze the digitized video for object identification and segmentation, tracking, and/or behavior/activity characterization.
  • This software may be stored in, for example, a program memory, which may include ROM, RAM, CD ROM and/or a hard drive, etc.
  • the software or firmware includes a unique background subtraction method which is more simple, efficient, and accurate than those previously known.
  • the system receives incoming video images from either the video camera in real time or pre-recorded from the video record/playback unit.
  • the information is converted from analog to digital format and may be compressed by the video digitization/compression unit.
  • the digital video images are then provided to the computer where various processes are undertaken to identify and segment a predetermined object from the image, h a preferred embodiment the object is an object (e.g., a mouse) in motion with some movement from frame to frame in the video, and is in the foreground of the video images, i any case, the digital images may be processed to identify and segregate a desired (predetermined) object from the various frames of incoming video. This process may be achieved using, for example, background subtraction, mixture modeling, robust estimation, and/or other processes. The shape and location of the desired object is then tracked from one frame or scene to another frame or scene of video images.
  • object e.g., a mouse
  • the changes in the shapes, locations, and/or postures of the object of interest maybe identified, their features extracted, and classified into meaningful categories, for example, vertical positioned side view, horizontal positioned side view, vertical positioned front view, horizontal positioned front view, moving left to right, etc.
  • the shape, location, and posture categories may be used to characterize the object's activity into one of a number of pre-defined behaviors.
  • some pre-defined normal behaviors may include sleeping, eating, drinking, walking, running, etc.
  • pre-defined abnormal behavior may include spinning vertical, jumping in the same spot, etc.
  • the pre-defined behaviors may be stored in a database in the data memory.
  • the behavior may be characterized using, for example, approaches such as rule-based label analysis, token parsing procedure, and or Hidden Markov Modeling (HMM).
  • HMM Hidden Markov Modeling
  • the system maybe constructed to characterize the object behavior as new behavior and particular temporal rhythm.
  • the system operates as follows. As a preliminary matter, normal postures and behaviors of the animals are defined and may be entered into a Normal Postures and Behaviors database, hi analyzing in a first instant, incoming video images are received. The system determines if the video images are in analog or digital format and input into a computer. If the video images are in analog format they are digitized and may be compressed, using, for example, an MPEG digitizer/compression unit. Otherwise, the digital video image may be input directly to the computer. Next, a background may be generated or updated from the digital video images and foreground objects detected. Next, the foreground objects features are extracted.
  • the foreground object shape is classified into various categories, for example, standing, sitting, etc.
  • the foreground object posture is compared to the various predefined postures stored in the database, and then identified as a particular posture or a new (unidentified) posture.
  • various groups of postures are concatenated into a series to make up a foreground object behavior and then compared against the sequence of postures, stored in for example a database in memory, that make up known normal or abnormal behaviors of the animal.
  • the abnormal behaviors are then identified in terms of known abnormal behavior, new behavior and/or daily rhythm.
  • object detection is performed through a unique method of background subtraction. First, the incoming digital video signal is split into individual images (frames) in real-time.
  • the system determines if the background image derived from prior incoming video needs to be updated due to changes in the background image or a background image needs to be developed because there was no background image was previously developed. If the background image needs to be generated, then a number of frames of video image, for example 20, will be grouped into a sample of images. Then, the system creates a standard deviation map of the sample of images. Next, the process removes a bounding box area in each frame or image where the variation within the group of images is above a predetermined threshold (i.e., where the object of interest or moving objects are located). Then, the various images within the sample less the bounding box area are averaged. Final background is obtained by averaging 5-10 samples. This completes the background generation process.
  • a predetermined threshold i.e., where the object of interest or moving objects are located
  • the background image does not remain constant for a great length of time due to various reasons.
  • the background needs to be recalculated periodically as above or it can be recalculated by keeping track of the difference image and note any sudden changes.
  • the newly generated background image is next subtracted from the current video image(s) to obtain foreground areas that may include the object of interest.
  • regions of interest are obtained by identifying areas where the intensity difference generated from the subtraction is greater than a predetermined threshold, which constitute potential foreground object(s) being sought. Classification of these foreground regions of interest will be performed using the sizes of the ROIs, distances among these ROIs, threshold of intensity, and connectedness, to thereby identify the foreground objects.
  • the foreground object identification/detection process may be refined by adaptively learning histograms of foreground ROIs and using edge detection to more accurately identify the desired object(s).
  • the information identifying the desired foreground object is output. The process may then continue with the tracking and/or behavior characterization step(s).
  • the previous embodiments are particularly applicable to the study and analysis of mice used in genetic and drug experimentation.
  • One variation of the present invention is directed particularly to automatically determining the behavioral characteristics of a mouse in a home cage.
  • the need for sensitive detection of novel phenotypes of genetically manipulated or drug-administered mice demands automation of analyses. Behavioral phenotypes are often best detected when mice are unconstrained by experimenter manipulation.
  • automation of analysis of behavior in a known environment, for example a home cage would be a powerful tool for detecting phenotypes resulting from gene manipulations or drug administrations. Automation of analysis would allow quantification of all behaviors as they vary across the daily cycle of activity.
  • the automated system may also be able to detect behaviors that do not normally occur and present the investigator with video clips of such behavior without the investigator having to view an entire day or long period of mouse activity to manually identify the desired behavior.
  • the systematically developed definition of mouse behavior that is detectable by the automated analysis according to the present invention makes precise and quantitative analysis of the entire mouse behavior repertoire possible for the first time.
  • the various computer algorithms included in the invention for automating behavior analysis based on the behavior definitions ensure accurate and efficient identification of mouse behaviors, hi addition, the digital video analysis techniques of the present invention improves analysis of behavior by leading to: (1) decreased variance due to non-disturbed observation of the animal; (2) increased experiment sensitivity due to the greater number of behaviors sampled over a much longer time span than ever before possible; and (3) the potential to be applied to all common normative behavior patterns, capability to assess subtle behavioral states, and detection of changes of behavior patterns in addition to individual behaviors.
  • Classification criteria (based on features extracted from the foreground object such as shape, position, movement) were derived and fitted into a decision tree (DT) classification algorithm.
  • the decision tree could classify almost 500 sample features into 5 different postures classes with an accuracy over 93%.
  • a simple HMM system has been built using dynamic programming and has been used to classify the classified postures identified by the DT and yields an almost perfect mapping from input posture to output behaviors in mouse behavior sequences.
  • the invention may identify some abnormal behavior by using video image information
  • abnormalities may also result from an increase in any particular type of normal behavior. Detection of such new abnormal behaviors may be achieved by the present invention detecting, for example, segments of behavior that do not fit the standard profile.
  • the standard profile may be developed for a particular strain of mouse whereas detection of abnormal amounts of a normal behavior can be detected by comparison to the statistical properties of the standard profile.
  • the automated analysis of the present invention may be used to build profiles of the behaviors, their amount, duration, and daily cycle for each animal, for example each commonly used strain of mice.
  • a plurality of such profiles may be stored in, for example, a database in a data memory of the computer. One or more of these profile may then be compared to a mouse in question and difference from the profile expressed quantitatively.
  • the techniques developed with the present invention for automation of the categorization and quantification of all home-cage mouse behaviors throughout the daily cycle is a powerful tool for detecting phenotypic effects of gene manipulations in mice. As previously discussed, this technology is extendable to other behavior studies of animals and humans, as well as surveillance purposes. As will be described in detail below, the present invention provides automated systems and methods for automated accurate identification, tracking and behavior categorization of an object whose image is captured with video.
  • Figure 1 is a block diagram of one exemplary system configurable to find the position, shape, and behavioral characteristics of an object using automated video analysis, according to one embodiment of the present invention.
  • Figure 2 is a block diagram of various functional portions of a computer system, such as the computer system shown in Figure 1, when configured to find the position, shape, and behavioral characteristics of an object using automated video analysis, according to one embodiment of the present invention.
  • Figure 3 is a flow chart of a method of automatic video analysis for object identification and characterization, according to one embodiment of the present invention.
  • Figure 4 is a flow chart of a method of automatic video analysis for object identification and characterization, according to another embodiment of the present invention.
  • Figure 5 is a flow chart of a method of automatic video analysis for object detection and identification, according to one variation of the present invention.
  • Figure 6 illustrates a sample video image frame with a mouse in a rearing up posture as determined using one variation of the present invention to monitor and characterize mouse behavior.
  • Figure 7A is a first video image frame in a sequence with a mouse in an eating posture for illustrating background generation for a background subtraction process according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
  • Figure 7B is a copy of the first video image frame of Figure 7A in which the process has extracted an area of the video image related to the mouse in the foreground resulting in a "hole" which will be filled up when other frames are averaged with it for a background subtraction process according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
  • Figure 7C is the resulting background image for a video clip including the first video image frame of Figure 7A converted as shown in Figure 7B and averaged with subsequent video images, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
  • Figure 8A is a difference image between foreground and background for the image shown in Figure 7A, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
  • Figure 8B is the image shown in Fig. 7A after completing a threshold process for identifying the foreground image of the mouse which is shown as correctly identified, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
  • Figure 8C is a video image frame showing the foreground mouse object correctly identified by the system as identified with a polygon outline, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
  • Figure 9 A is a video image frame showing a mouse eating, to demonstrate a b-spline approach to object location and outline identification according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
  • Figure 9B is a computer generated image showing the outline of the foreground mouse shown in Figure 9A after edge segmentation, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
  • Figure 9C is a computer generated image of the outline of the foreground mouse shown in Figure 9 A as derived from the outline of the mouse shown in Figure 9B as generated from a b-spline process, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
  • Figure 10 is a chart illustrating one example of various mouse state transitions used in characterizing mouse behavior including: Horizontal (HS); Cuddled up (CU); Partially reared (PR); Vertically Reared (VR); and Forward Back (FB), along with an indication of duration of these states based on a sample, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
  • HS Horizontal
  • PR Partially reared
  • VR Vertically Reared
  • FB Forward Back
  • the present invention can automatically find the patterns of behaviors and/or activities of a predetermined object being monitored using video.
  • the invention includes a system with a video camera connected to a computer in which the computer is configured to automatically provide object identification, object motion tracking (for moving objects), object shape and posture classification, and behavior identification.
  • the system includes various video analysis algorithms.
  • the computer processes analyze digitized video with the various algorithms so as to automatically monitor a video image to identify, track and classify the actions of one or more predetennined objects and its movements captured by the video image as it occurs from one video frame or scene to another.
  • the system may characterize behavior by accessing a database of object information of known behavior of the predetermined object.
  • the image to be analyzed may be provided in real time from one or more camera and/or from storage.
  • the invention is configured to enable monitoring and classifying of animal behavior that results from testing drugs and genetic mutations on animals.
  • the system may be similarly configured for use in any of a number of surveillance or other applications.
  • the invention can be applied to various situations in which tracking moving objects is needed.
  • One such situation is security surveillance in public areas like airports, military bases, or home security systems.
  • the system maybe useful in automatically identifying and notifying proper law enforcement officials if a crime is being committed and/or a particular behavior being monitored is identified.
  • the system may be useful for monitoring of parking security or moving traffic at intersections so as to automatically identify and track vehicle activity.
  • the system may be configured to automatically determine if a vehicle is speeding or has performed some other traffic violation.
  • the system may be configured to automatically identify and characterize human behavior involving guns or human activity related to robberies or thefts.
  • the invention may be capable of identifying and understanding subtle behaviors involving portions of body such as forelimb and can be applied to identify and understand human gesture recognition. This could help deaf individuals communicate.
  • the invention may also be the basis for computer understanding of human gesture to enhance the present human-computer interface experience, where gestures will be used to interface with computers. The economic potential of applications in computer-human interface applications and in surveillance and monitoring applications is enormous.
  • the invention includes a system in which an analog video camera 105 and a video storage/retrieval unit 110 may be coupled to each other and to a video digitization/compression unit 115.
  • the video camera 105 may provide a real time video image containing an object to be identified.
  • the video storage/retrieval unit 110 may be, for example, a VCR, DVD, CD or hard disk unit.
  • the video digitization/compression unit 115 is coupled to a computer 150 that is configured to automatically monitor a video image to identify, track and classify the actions (or state) of the object and its movements (or stillness) over time within a sequence of images.
  • the digitization/compression unit 115 may convert analog video and audio into, for example, MPEG format, Real Player format, etc.
  • the computer may be, for example, a personal computer, using either a Windows platform or a Unix platform, or a Macintosh computer and compatible platform.
  • the computer may include a number of components such as (1) a data memory 151, for example, a hard drive or other type of volatile or nonvolatile memory; (2) a program memory 152, for example, RAM, ROM, EEPROM, etc. that may be volatile or non- volatile memory; (3) a processor 153, for example, a microprocessor; and (4) a second processor to manage the computation intensive features of the system, for example, a math coprocessor 154.
  • the computer may also include a video processor such as an MPEG encoder/decoder.
  • a video processor such as an MPEG encoder/decoder.
  • the computer 150 has been shown in Figure 1 to include two memories (data memory 151 and program memory 152) and two processors (processor 153 and math co-processor 154), in one variation the computer may include only a single processor and single memory device or more then two processors and more than two memory devices.
  • the computer 150 maybe equipped with user interface components such as a keyboard 155, electronic mouse 156, and display unit 157.
  • the system may be simplified by using all digital components such as a digital video camera and a digital video storage/retrieval unit 110, which may be one integral unit. In this case, the video digitization/compression unit 115 may not be needed.
  • the computer is loaded and configured with custom software program(s) (or equipped with firmware) using, for example, MATLAB or C/C++ programming language, so as to analyze the digitized video for object identification and segmentation, tracking, and/or behavior/activity characterization.
  • This software may be stored in, for example, a program memory 152 or data memory that may include ROM, RAM, CD ROM and/or a hard drive, etc.
  • the software or firmware includes a unique background subtraction method which is more simple, efficient, and accurate than those previously known which will be discussed in detail below, any case, the algorithms may be implemented in software and may be understood as unique functional modules as shown in Figure 2 and now described.
  • the system is preloaded with standard object information before analyzing an incoming video including a predetermined object, for example, a mouse.
  • a stream of digital video including a known obj ect with known characteristics may be fed into the system to a standard object classifier module 220.
  • a user may then view the standard object on a screen and identify and classify various behaviors of the standard object, for example, standing, sitting, lying, normal, abnormal, etc.
  • Data information representing such standard behavior may then be stored in the standard object behavior storage modules 225, for example a database in data memory 151.
  • standard object behavior information data sets maybe loaded directly into the standard object behavior storage module 225 from another system or source as long as the data is compatible with the present invention protocols and data structure.
  • the system may be used to analyze and classify the behavior of one or more predetermined objects, for example, a mouse.
  • digital video (either real-time and or stored) of monitored objects to be identified and characterized is input to an object identification and segregation module 205.
  • This module identifies and segregates a predetermined type of object from the digital video image and inputs it to an object tracking module 210.
  • the object tracking module 210 facilitates tracking of the predetermined object from one frame or scene to another as feature information.
  • This feature information is then extracted and input to the object shape and posture classifier 215.
  • This module classifies the various observed states of the predetermined object of interest into various shape and posture categories and sends it to the behavior identification module 230.
  • the behavior identification module 230 compares the object shape, motion, and posture information with shape, motion, and posture information for a standard object and classifies the behavior accordingly into the predefined categories exhibited by the standard object, including whether the behavior is normal, abnormal, new, etc. This information is output to the user as characterized behavior information on, for example, a display unit 157.
  • the system may receive incoming video images at step 305, from the video camera 105 in real time, pre-recorded from the video storage/retrieval unit 110, and/or a memory integral to the computer 150. If the video is in analog format, then the information is converted from analog to digital format and may be compressed by the video digitization/compression unit 115.
  • the digital video images are then provided to the computer 150 for various computational intensive processing to identify and segment a predetermined object from the image, hi a preferred embodiment, the object to be identified and whose activities is to be characterized is a moving object, for example a mouse, which has some movement from frame to frame or scene to scene in the video images and is generally in the foreground of the video images.
  • the digital images may be processed to identify and segregate a desired (predetermined) object from the various frames of mcoming video. This process may be achieved using, for example, background subtraction, mixture modeling, robust estimation, and/or other processes.
  • various movements (or still shapes) of the desired object may then be tracked from one frame or scene to another frame or scene of video images.
  • this tracking may be achieved by, for example, tracking the outline contour of the object from one frame or scene to another as it varies from shape to shape and/or location to location.
  • the changes in the motion of the object such as the shapes, locations, and postures of the object of interest, maybe identified and their features extracted and classified into meaningful categories. These categories may include, for example, vertical positioned side view, horizontal positioned side view, vertical positioned front view, horizontal positioned front view, moving left to right, etc.
  • the states of the object may be used to characterize the objects activity into one of a number of pre-defined behaviors.
  • some pre-defined normal behaviors may include sleeping, eating, drinking, walking, running, etc.
  • pre-defined abnormal behavior may include spinning vertical, jumping in the same spot, etc.
  • the pre-defined behaviors may be stored in a database in the data memory 151.
  • Types of behavior may also be characterized using, for example, approaches such as rule-based label analysis, token parsing procedure, and/or Hidden Markov Modeling (HMM).
  • HMM Hidden Markov Modeling
  • the HMM is particularly helpful in characterizing behavior that is determined with temporal relationships of the various motion of the object across a selection of frames. From these methods, the system may be capable of characterizing the object behavior as new behavior and particular temporal rhythm.
  • the system is directed toward video analysis of animated objects such as animals.
  • video of the activities of a standard object and known behavior characteristics are input into the system.
  • This information maybe provided from a video storage/retrieval unit 110 in digitized video form into a standard object classified module 220.
  • This information may then be manually categorized at step 416 to define normal and abnormal activities or behaviors by a user viewing the video images on the display unit 157 and inputting their classifications. For example, experts in the field may sit together watching recorded scenes.
  • an animal's e.g., a mouse
  • behaviors may constitute the important posture and behavior database and are entered into a storage, for example a memory, of known activity of the standard object at step 420.
  • This information provides a point of reference for video analysis to characterize the behavior of non-standard objects whose behaviors/activities need to be characterized such as genetically altered or drug administered mice.
  • normal postures and behaviors of the animals are defined and may be entered into a normal postures and behaviors database.
  • the system may then be used to analyze incoming video images that may contain an object for which automated behavior characterization is desired.
  • incoming video images are received.
  • decision step 406 the system determines if the video images are in analog or digital format. If the video images are in analog format they are then digitized at step 407.
  • the video may be digitized and may be compressed, using, for example, a digitizer/compression unit 115 into a convenient digital video format such as MPEG, RealPlayer, etc. Otherwise, the digital video image may be input directly to the computer 150. Now the object of interest is identified within the video images and segregated for analysis.
  • a background may be generated or updated from the digital video images and foreground objects including a predetermined object for behavior characterization may be detected. For example, a mouse in a cage is detected in the foreground and segregated from the background. Then, at step 409, features such as centroid, the principal orientation angle of the object, the area (number of pixels), the eccentricity (roundness), and the aspect ratio of the object, and/or shape in terms of convex hull or b-spline, of the foreground object of interest (e.g., a mouse) are extracted. Next, at step 410, the foreground object shape and postures are classified into various categories, for example, standing, sitting, etc.
  • the foreground object e.g., a mouse
  • the foreground object posture maybe compare to the various predefined postures in the set of known postures in the standard object storage of step 420, which may be included in a database.
  • the observed postures of the object contained in the analyzed video image may be classified and identified as a particular posture known for the standard object or a new previously unidentified posture.
  • various groups of postures maybe concatenated into a series to make up a foreground object behavior that is then compared against the sequence of postures, stored in for example a database in memory, that make up a known standard object behavior.
  • This known standard behavior is, in a preferred embodiment, normal behavior for the type of animal being studied.
  • the known activity of the standard object may be normal or abnormal behavior of the animal.
  • the abnormal behaviors are then identified in terms of (1) known abnormal behavior; (2) new behavior likely to be abnormal; and/or (3) daily rhythm differences likely to be abnormal behavior.
  • Known normal behavior may also be output as desired by the user. This information is automatically identified to the user for their review and disposition.
  • the information output may include behavior information that is compatible with current statistical packages such as Systat and SPSS.
  • object detection is performed through a unique method of background subtraction.
  • incoming video is provided to the system for analysis. This video may be provided by digital equipment and input to the object identification and segregation module 205 of the computer 150.
  • the incoming digital video signal may be split into individual images (frames) in real-time. This step maybe included if it is desired to carry out real-time analysis.
  • decision step 506 the system determines if the background image needs to be developed because there was no background image developed previously or the background image has changed.
  • a background image is generated by first grouping a number of frames or images into a sample of video images, for example 20 frames or images.
  • the background may need to be updated periodically due to changes caused by, for example, lighting and displacement of moveable objects in the cage, such as the bedding.
  • the system generates a standard deviation map of the group of images.
  • an object(s) bounding box area is identified and removed from each frame or image to create a modified frame or image.
  • the bounding box area is determined by sensing the area wherein the variation of a feature such as the standard deviation of intensity is above a predetermined threshold.
  • an area in the digitized video image where the object of interest in motion is located is removed leaving only a partial image.
  • the various modified images within the group, less the bounding box area are combined, for example averaged, to create a background image at step 511.
  • the background image does not remain constant for a great length of time due to various reasons. For example, the bedding in a mouse cage can shift due to the activity of the mouse. External factors such as change in illumination conditions also require background image recalculations. If the camera moves, then, background might need to be changed. Thus, the background typically needs to be recalculated periodically as described above or it can be recalculated by keeping track of the difference image and note any sudden changes such as an increase in the number of particular color (e.g., white) pixels in the difference image or the appearance of patches of the particular color (e.g., white) pixels in another area of the difference image, hi any case, the newly generated background image may then be combined with any existing background image to create a new background image at step 511.
  • particular color e.g., white
  • the newly generated background image is next, at step 512, subtracted from the current video image(s) to obtain foreground areas that may include the object of interest.
  • the process may proceed to step 512 and the background image is subtracted from the current image, leaving the foreground objects.
  • the object identification/detection process is performed.
  • regions of interest ROI
  • Classification of these foreground regions of interest will be performed using the sizes of the ROIs, distances among these ROIs, threshold of intensity, and connectedness to identify the foreground objects.
  • the foreground object identification/detection process may be refined by utilizing information about the actual distribution (histograms) of the intensity levels of the foreground object and using edge detection to more accurately identify the desired object(s).
  • the system continuously maintains a distribution of the foreground object intensities as obtained.
  • a lower threshold may be used to thereby permit a larger amount of noise to appear in the foreground image in the form of ROIs.
  • a histogram is then updated with the pixels in the ROI.
  • plotting a histogram of all the intensities of a particular color pixels over many images provides a bi-modal shape with the larger peak corresponding to the foreground object's intensity range and the smaller peak corresponding to the noise pixels in the ROI's images.
  • step 516 having "learned" the intensity range of the foreground object, only those pixels in the foreground object that conform to this intensity range are selected, thereby identifying the foreground object more clearly even with background that is fairly similar.
  • the foreground object of interest may be refined using edge information to more accurately identify the desired object.
  • An edge detection mechanism such as Prewitt operator is applied to the original image. Adaptive thresholds for edge detections can be used.
  • the actual boundary of the foreground object is assumed to be made up of one or more segments in the edge map, i.e., the actual contour of the foreground objects comprises edges in the edge map.
  • the closed contour of the "detected" foreground object is broken into smaller segments, if necessary. Segments in the edge map that are closest to these contour segments according to a distance metric are found to be the desired contour.
  • One exemplary distance metric is the sum of absolute normal distance to the edge map segment from each point in the closed contour of the "detected" foreground object.
  • the previous embodiments are generally applicable to identifying, tracking, and characterizing the activities of a particular object of interest present in a video image, e.g., an animal, a human, a vehicle, etc.
  • the invention is also particularly applicable to the study and analysis of animals used for testing new drugs and/or genetic mutations.
  • a number of variations of the invention related to determining changes in behavior of mice will be described in more detail below using examples of video images obtained.
  • One variation of the present invention is designed particularly for the purpose of automatically determining the behavioral characteristics of a mouse.
  • the need for sensitive detection of novel phenotypes of genetically manipulated or dmg-administered mice demands automation of analyses. Behavioral phenotypes are often best detected when mice are unconstrained by experimenter manipulation.
  • automation of analysis of behavior in a home cage would be a preferred means of detecting phenotypes resulting from gene manipulations or drug administrations.
  • Automation of analysis as provided by the present invention will allow quantification of all behaviors and may provide analysis of the mouse's behavior as they vary across the daily cycle of activity. Because gene defects causing developmental disorders in humans usually result in changes in the daily rhythm of behavior, analysis of organized patterns of behavior across the day may be effective in detecting phenotypes in transgenic and targeted mutant mice.
  • the automated system of the present invention may also detect behaviors that do not normally occur and present the investigator with video clips of such behavior without the investigator having to view an entire day or long period of mouse activity to manually identify the desired behavior.
  • the systematically developed definition of mouse behavior that is detectable by the automated analysis of the present invention makes precise and quantitative analysis of the entire mouse behavior repertoire possible for the first time.
  • the various computer algorithms included in the invention for automating behavior analysis based on the behavior definitions ensure accurate and efficient identification of mouse behaviors.
  • the digital video analysis techniques of the present invention improves analysis of behavior by leading to: (1) decreased variance due to non-disturbed observation of the animal; (2) increased experiment sensitivity due to the greater number of behaviors sampled over a much longer time span than ever before possible; and (3) the potential to be applied to all common normative behavior patterns, capability to assess subtle behavioral states, and detection of changes of behavior patterns in addition to individual behaviors.
  • Development activities have been complete to validate various scientific definition of mouse behaviors and to create novel digital video processing algorithms for mouse tracking and behavior recognition, which are embody in software and hardware system according to the present invention.
  • the first step in the analysis of home cage behavior is an automated initialization step that involves analysis of video images to identify the location and outline of the mouse, as indicated by step 310.
  • the location and outline of the mouse are tracked over time, as indicated by step 315.
  • Performing the initialization step periodically may be used to reset any propagation errors that appear during the tracking step.
  • the mouse is tracked over time, its features including shape are extracted, and used for training and classifying the posture of the mouse from frame to frame, as indicated by step 320.
  • Posture labels are generated for each frame, which are analyzed over time to determine the actual behavior, as indicated by step 325.
  • FIG. 6 A typical video frame of a mouse in its home cage is shown in Figure 6.
  • a mouse In this video frame a mouse is shown in a rearing up posture. Many such frames make up the video of, for example, a 24 hour mouse behavior monitoring session.
  • FIG. 5 A typical video frame of a mouse in its home cage is shown in Figure 6.
  • Background subtraction as used in the present invention generally involves generating a still background image from all or a subset of the frames in a video clip and subtracting this background image from any given image to obtain the foreground objects.
  • the background is generated by averaging many frames, for example approximately 100 frames of the video, after compensating for any shifts caused by the motion of the camera. Even if foreground objects are present in the frames that are being averaged to generate the background image, their unwanted contribution is negligible when large numbers of frames are used for the background calculation, assuming that the foreground object does not remain at the same location throughout. Nevertheless, it may be helpful to not consider those pixels where the foreground object is present. In one implementation of the background averaging process, only the stationary pixels in an image are considered to avoid the unwanted contributions of the foreground moving objects.
  • the stationary and non-stationary pixels are determined by analyzing the local variations of each pixel of a series of frames over a short time period as indicated in step 509 of figure 5.
  • the standard deviation from the mean is first calculated for each pixel. If the standard deviation is greater than a chosen threshold, we tag those pixels as being non- stationary or varying pixels. Those pixels that are below the threshold may be tagged as stationary or constant pixels. Only those stationary pixels are used in the averaging process to calculate the background. Since the varying pixels are not used, there will be "holes" in each image that is being used in the averaging process. Over time, not all frames will have these holes at the same location and hence, a complete background image may be obtained with the averaging process. Once the background image has been obtained, subtraction of the background image from the given analyzed image yields the foreground objects.
  • a chosen threshold we tag those pixels as being non- stationary or varying pixels. Those pixels that are below the threshold may be tagged as stationary or constant pixels. Only those stationary pixels are used in the averaging process to calculate the background. Since the varying pixels are not used, there will be "holes" in each image that is being used in the averaging process. Over time, not
  • T be the number of frames that are being averaged to calculate the background.
  • P (Xtytt) be the pixel value at position (x, y) and frame number t , then the mean, p x ⁇ , and standard deviation, ⁇ ( ⁇ . y) , for that location are defined respectively as,
  • ⁇ x y For a particular pixel is greater than a threshold, for example an intensity of 64 on the scale of 0 to 255 was used for a video clip with mouse in a cage, then it is omitted from the background image calculation.
  • a threshold for example an intensity of 64 on the scale of 0 to 255 was used for a video clip with mouse in a cage
  • the background image of a video session does not remain constant for a great length of time.
  • the bedding in the mouse cage can shift due to the activity of the mouse.
  • the background may need to be recalculated periodically.
  • External factors such as change in illumination conditions may require background image recalculations. If the camera 105 moves, then the background image might need to be recalculated.
  • Another method other than performing background recalculations periodically, is to keep track of the difference image and note any sudden changes such as an increase in the number of white pixels in the difference image or the appearance of patches of white pixels in another area of the difference image.
  • Figures 7 A, 7B and 7C An example of some screen shots of one exemplary background subtraction process used for monitoring a mouse with the present invention is shown in Figures 7 A, 7B and 7C.
  • Figure 7 A illustrates a first frame in a sequence with the mouse in an eating posture 705.
  • Figure 7B illustrates the same frame of the video image now having the area of the frame in which the pixels are changing identified as a blocked out 710.
  • the background has a "hole” 710 (shown in black).
  • This hole 710 will be filled with an image indicative of the true complete background image when other frames are averaged with it.
  • several samples should first be generated. For example, a 10-20 frame sample (30 frames per second) from a video clip is taken and then averaged to generate one sample.
  • FIG. 7C illustrates the resulting background image for the video clip once the group of frames in a sample set and a number of sample sets are averaged together.
  • this method is quite successful at generating a reasonably complete background image (less the foreground object of interest) to be used in the background subtraction process for identifying and segregating a desired object, in this case a mouse.
  • One primary advantage of this technique is its low complexity that enables the background recalculations and foreground object detection to be performed with ease. This makes the background subtraction method of the present invention well suited for use in realtime processing applications.
  • Various other algorithms may be used for object or mouse identification.
  • a mixture model and/or robust estimation algorithms in addition to, or in place of, background subtraction.
  • These algorithms are newly developed theory in image sequence processing and object segmentation. They may handle object segmentation better than background subtraction in certain circumstances.
  • Preliminary analysis indicates that mixture model and/or robust estimation algorithms may have excellent results for mouse identification.
  • the background is then used to determine the foreground objects by taking the intensity difference and applying a threshold determination procedure to remove noise.
  • This step may involve threshold determination on both the intensity and the size of region.
  • An 8-connection labeling procedure may be performed to screen out disconnected small noisy regions and improve the region that corresponds to the mouse.
  • all pixels in a frame will be assigned a label as foreground pixel or background pixel.
  • Thresholding has generated labels for certain pixels. Neighbors of those labeled pixels that have not been labeled may obtain the same label as the labeled pixel.
  • Eight-connectedness defines 8 corner-adjacent pixels that are all neighbors. The remaining regions indicated to be foreground objects are much smaller compared to the region of mouse, thus a size criteria is used to select the larger mouse region. The outline or contour of this foreground object is thus determined.
  • convex hull of the pixels is used in the foreground object for representation.
  • Convex hull H of an arbitrary set S which is a region in the frame in this case, is the smallest set containing S.
  • the set difference H-S is called the convex deficiency D of the set S.
  • the region S' boundary can be partitioned by following the contour of S and marking the points at which transition is made into or out of a component of the convex deficiency. These marking points can be connected into a polygon that gives a description of the region.
  • the centroid (or center of mass) of the foreground object is calculated and is used for representing the location of the object (e.g., mouse).
  • Figures 8 A, 8B and 8C illustrate the results of the location and object outline identification for a mouse using the present invention.
  • Figure 8A illustrates a difference image between foreground and background for the image in Figure 7A.
  • Figure 8B illustrates the image after thresholding showing the foreground mouse 705 object correctly identified.
  • Figure 8C illustrates a video image showing the foreground object, a mouse correctly identified with a polygon outline 805, created using convex hull approach as described above.
  • Another method of location and outline identification that may improve the representation of the shape of the mouse is the b-spline method.
  • B-spline are piecewise polynomial functions that can provide local approximation of contours of shapes using a small number of parameters and the piecewise smooth lines can be uged to represent the outline of the object area. This is useful because human perception of shapes is deemed to be based on curvatures of parts of contours (or object surfaces). This is especially true since shapes of mice are curvatures at any time. This representation may thus results in compression of boundary data as well as smoothing of coarsely digitized contours.
  • This set of points is to be approximated by a B-spline representation as follows: iv-l
  • a series of image processing procedures may be performed first to detect edge using a sobel edge detection algorithm and then, using morphological operations to trim edge points to ensure that the edge points are singly chained.
  • Figures 9 A - 9C One example of the use of the B-Spline algorithm implemented in the present invention is illustrated in Figures 9 A - 9C.
  • Figure 9A illustrates an exemplary video image frame of mouse eating 705.
  • Figure 9B illustrates the segmented edge 905 of the mouse 705 found in Figure 9 A.
  • Figure 9C illustrates a b-spline representation of the mouse edge 910 extrapolated from the segmented edge of the mouse found in Figure 9 A.
  • b-spline representation, or convex hull representation can be used as features of foreground object, in addition to other features that include but not limited to: centroid, the principal orientation angle of the object, the area (number of pixels), the eccentricity (roundness), and the aspect ratio of object.
  • Ideal tracking of foreground objects in the image domain involves a matching operation to be performed that identifies corresponding points from one frame to the next. This process may become computationally too consuming or expensive to perform in an efficient manner. Thus, one approach is to use approximations to the ideal case that can be accomplished in a short amount of time. For example, tracking the foreground object may be achieved by merely tracking the outline contour from one frame to the next in the feature space (i.e., identified foreground object image).
  • tracking is performed in the feature space, which provides a close approximation to tracking in the image domain.
  • the features include the centroid, principal orientation angle of the object, area (number of pixels), eccentricity (roundness), and the aspect ratio of object with lengths measured along the secondary and primary axes of the object.
  • S be the set of pixels in the foreground object
  • A denote the area in number of pixels
  • C x , C y denote the centroid
  • ⁇ denote the orientation angle
  • E denote the eccentricity
  • R denote the aspect ratio.
  • Second order moments m. 2,0 ⁇ (x-C x )(y-C y )
  • R is equal to the ratio of the length of the range of the points projected along an axis perpendicular to ⁇ , to the length of the range of the points projected along an axis parallel to ⁇ . This may also be defined as the aspect ratio (ratio of width to length) after rotating the foreground obj ect by ⁇ .
  • Tracking in the feature space involves following feature values from one frame to the next. For example, if the area steadily increases, it could mean that the mouse is coming out of a cuddled up position to a more elongated position, or that it could be moving from a front view to a side view, etc. If the position of the centroid of the mouse moves up, it means that the mouse may be rearing up on its hind legs. Similarly, if the angle of orientation changes from horizontal to vertical, it may be rearing up. These changes can be analyzed with combinations of features also.
  • the foreground state of the mouse is classified into one of the given classes.
  • This information may be stored in, for example, a database in, for example, a data memory, hi one variation of the invention a Decision Tree classifier (e.g., object shape and posture classifier 215) was implemented by training the classifier with 488 samples of digitized video of a standard, in this case, normal mouse. Six attributes (or features) for each sample were identified. Five posture classes for classification were identified as listed below.
  • the system of the present invention was exercised using these classifications.
  • the distribution of the samples amongst the five classes is shown in Table 1.
  • Table 1 Performing a 10-fold cross-validation on the 488 training samples, a combined accuracy of 93.65% was obtained indicating that the classifier was performing well. This in the range of the highest levels of agreement between human observers.
  • the cross-validation procedure involves randomly dividing a training set into N approximately equal sets, and for each of the N folds or iterations, one set is set aside for testing while the remaining N -1 sets are used as training samples.
  • Accuracy values for individual classes are indicated in the last column of Table 1.
  • Table 2 shows the overall accuracy values for each fold. We assign appropriate labels for each frame depending on the class to with it was classified to.
  • Table 1 Distribution of samples in the five classes and the accuracy values for each class.
  • Table 2 Accuracy results for each fold for a cross-validation test.
  • the present system provides good accuracy for mouse shape and posture recognition and classification.
  • One approach is to use a rule-based label analysis procedure (or a token parsing procedure) by which the sequence of labels is analyzed and identify particular behaviors when its corresponding sequence of labels is derived from a video frame being analyzed. For example, if a long sequence (lasting for example several minutes) of the "Cuddled up position" label (Class 3) is observed, and if its centroid remains stationary, then, it may be concluded that the mouse is sleeping. If the location of the waterspout is identified, and if we observe a series of "partially reared" (Class 5) labels, and if the position of the centroid, and the mouse's angle of orientation fall within a small range that has been predetermined, the system can determine and identify that the mouse is drinking. It may also be useful for certain extra conditions to be tested such as, "some part (the mouth) of the mouse must touch the spout if drinking is to be identified" in addition to temporal characteristics of the behavior.
  • a rule-based label analysis procedure or a token parsing procedure
  • HMMs Hidden Markov Models
  • the five exemplary mouse state transitions include: (1) Horizontal (HS) 1005, (2) Cuddled up (CU) 1010, (3) Partially reared (PR) 1015, (4) Vertically Reared (VR) 1020, and (5) Forward Back (FB) 1025 postures.
  • Figure 10 shows the five posture states and the duration for which a mouse spent in each state in an exemplary sample video clip.
  • One example of a pattern that is understandable and evident from the figure is that the mouse usually passes through the partially reared (PR) 1015 state to reach the vertically reared (VR) 1025 state from the other three ground-level states.
  • the states are defined according to the five posture classes mentioned previously.
  • a simple HMM system has been created using dynamic programming to find the best match between the input sequence and paths through the state machine. It has been used to classify events in one of the mouse behavior sequences.
  • the HMM system was provided with a sequence of tokens representing recognized actions or views from a benchmark mouse-rear video; this file includes views from five different postures, which are:
  • Each of these represents a posture of the mouse and all together they constitute five (5) tokens. These tokens cause the HMM to go from one (hidden) state to another.
  • the HMM may classify behavior into one of, for example, four hidden states: horizontal, rearing, cuddled, or indecisive:
  • HMM defining mouse behaviors can be described as:
  • This approach to a HMM for mouse behavior characterization may result in a number of mismatched cases which maybe categorized into three (3) types: (a) one mismatch (the last token) because the start and stop states were forced to be 0; (b) the PARTIALLY_REARED may be mapped to indecisive, but this may only be a difference in the naming; and (c) the FRONT_OR_BACK may be mapped to the same value as HORIZ_SIDE_VIEW (21 cases).
  • the system could be configured to automatically detect and characterize an animal freezing and/or touching or sniffing a particular object. Also, the system could be configured to compare the object's behavior against a "norm" for a particular behavioral parameter. Other detailed activities such as skilled reaching and forelimb movements as well as social behavior among groups of animals can also be detected and characterized.
  • the system of the present invention first obtains the video image background and uses it to identify the foreground objects. Then, features are extracted from the foreground objects, which are in turn passed to the decision tree classifier for classification and labeling. This labeled sequence is passed to a behavior identification system module that identifies the final set of behaviors for the video clip. The image resolution of the system that has been obtained and the accuracy of identification of the behaviors attempted so far have been very good and resulted in an effective automated video image object recognition and behavior characterization system.
  • the invention may identify some abnormal behavior by using video image information (for example, stored in memory) of known abnormal animals to build a video profile for that behavior. For example, video image of vertical spinning while hanging from the cage top was stored to memory and used to automatically identify such activity in mice. Further, abnormalities may also result from an increase in any particular type of normal behavior.
  • video image information for example, stored in memory
  • video image of vertical spinning while hanging from the cage top was stored to memory and used to automatically identify such activity in mice.
  • abnormalities may also result from an increase in any particular type of normal behavior.
  • Detection of such new abnormal behaviors may be achieved by the present invention detecting, for example, segments of behavior that do not fit the standard profile.
  • the standard profile may be developed for a particular strain of mouse whereas detection of abnormal amounts of a normal behavior can be detected by comparison to the statistical properties of the standard profile.
  • the automated analysis of the present invention may be used to build a profile of the behaviors, their amount, duration, and daily cycle for each animal, for example each commonly used strain of mice.
  • a plurality of such profiles may be stored in, for example, a database in a data memory of the computer. One or more of these profile may then be compared to a mouse in question and difference from the profile expressed quantitatively.
  • the techniques developed with the present invention for automation of the categorization and quantification of all home-cage of mouse behaviors throughout the daily cycle is a powerful tool for detecting phenotypic effects of gene manipulations in mice.
  • this technology is extendable to other behavior studies of animals and humans, as well as surveillance purposes, hi any case, the present invention has proven to be a significant achievement in creating an automated system and methods for automated accurate identification, tracking and behavior categorization of an object whose image is captured in a video image.
  • the present invention may also include audio analysis and/or multiple camera analysis.
  • the video image analysis maybe augmented with audio analysis since audio is typically included with most video systems today.
  • audio may be an additional variable used to determine and classify a particular objects behavior.
  • the analysis may be expanded to video image analysis of multiple objects, for example mice, and their social interaction with one another, hi a still further variation, the system may include multiple cameras providing one or more planes of view of an object to be analyzed.
  • the camera may be located in remote locations and the video images sent via the Internet for analysis by a server at another site, hi fact, the standard object behavior data and/or database may be housed in a remote location and the data files may be downloaded to a stand alone analysis system via the Internet, in accordance with the present invention.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Public Health (AREA)
  • Animal Behavior & Ethology (AREA)
  • Medical Informatics (AREA)
  • Biophysics (AREA)
  • Veterinary Medicine (AREA)
  • Surgery (AREA)
  • Molecular Biology (AREA)
  • Physiology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Pathology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Environmental Sciences (AREA)
  • Neurology (AREA)
  • Psychiatry (AREA)
  • Human Computer Interaction (AREA)
  • Zoology (AREA)
  • Artificial Intelligence (AREA)
  • Neurosurgery (AREA)
  • Social Psychology (AREA)
  • Animal Husbandry (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Epidemiology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Primary Health Care (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • General Business, Economics & Management (AREA)

Abstract

In general, the present invention is directed to systems and methods for finding the position and shape of an object using video. The invention includes a system with a video camera (105) coupled to a computer (150) in which the computer is configured to automatically provide object segmentation and identification, object (310) motion tracking for moving objects, object position classification (410), and behavior identification. Thus, the present invention is capable of automatically monitoring a video image to identify, track and classify the actions of various objects and the object's movements within the image.

Description

SYSTEM AND METHOD FOR OBJECT IDENTIFICATION AND BEHAVIOR CHARACTERIZATION USING VIDEO ANALYSIS
GOVERNMENT RIGHTS NOTICE Portions of the material in this specification arose as a result of Government support under contracts MH58964 and MH58964-02 between Clever Sys., Inc. and The National Institute of Mental Health, National Institute of Health. The Government has certain rights in this invention.
BACKGROUND OF THE INVENTION
1. Technical Field
The invention relates generally to object identification and recognition. More particularly, one aspect of the invention is directed to monitoring and characterization of an object in an image, for example an animal or a person, using video analysis.
2. Background Art
Video analysis has developed over the past few decades to become an integral part of machine operations in manufacturing using machine automation. For example, video object recognition and pattern recognition has been used to orient and align various pieces of a product for machining and assembly in various manufacturing industries. One such use is in the manufacturing of semiconductor integrated circuits and microelectronic packaging, h this case, pattern recognition has made great inroads because the size of the work product is microscopic and orientation and alignment of the work product is thus far too tedious for a human being to do consistently and accurately over a large number of pieces. hi recent years, military has carried out research to use video to track moving targets such as tanks and vehicles, in the scene. Other positioning instruments such as global positioning system will be used to assist such tracking.
Another application for video analysis is monitoring animal activity in laboratory testing for the pharmaceutical and biological sciences. One particular area is monitoring animal behavior to determine the effects of various new drugs or gene changes on a particular type of animal. One such animal used in laboratory testing is the mouse. Over the last two decades, major technological advances have enabled scientists to build a rich repository of mouse models. Model organisms are an important tool for understanding and dissecting human disease and biological process. Because mice and humans share many of the same fundamental biological and behavioral processes, this animal is one of the most significant laboratory models for human disease and studying biological processes in mammals. However, the adequate behavioral characterization (behavioral phenotyping - the impact of a genetic manipulation on visible characteristics of an organism) of genetically engineered mice is becoming a serious bottleneck in the development of animal models; an exponentially increasing number of genotypes are created, but the behavioral phenotyping is often at best rudimentary or is abandoned completely. This is because presently the phenotyping process is largely manual, time consuming, and insensitive to subtle phenotypes.
Video technologies for mouse behavior analysis have been introduced and several products are commercially available. However, these technologies are still primitive and the functionality of the products is far from adequate for the research purposes. There are presently two types of systems available for monitoring mouse behavior, those that identify individual behaviors and those that identify only the location of the mouse.
The most basic state-of-art mouse behavior analysis systems rely on traditional analog technologies that can only treat a mouse as an indivisible object and identify the mouse location. All the information about a mouse is packed as a point in the space and a lot of important information about mouse behavior is lost. The best these systems can do is to find the position of the mouse. Systems like San Diego rnstruments' Photobeam and AccuScan Instruments Inc.'s Digiscan Line of Animal Activity Monitoring, Columbus, OH uses simple and rudimentary photo-beams to detect and track the positions of mouse. These systems trackers have a very low spatial resolution, limiting their output to a rough measure of the animal's activity. They cannot differentiate even such basic behaviors as locomotion and circling. Adding a time line for the locus of mouse point is all they can offer. Other animal location type systems used to monitor animal motion include those described in U.S. Pat. Nos. 3,100,473; 3,803,571; 3,974,798; 4,337,726; 4,574,734; and 5,816,256. The other systems in the field are the systems that identify individual behavior using video. The existing video analysis systems (e.g. Noldus Observer/Ethovision, Sterling, VA; HVS Image, Hampton, UK; AccuScan Instruments Inc.'s VideoScan2000 System; and San Diego Instruments Poly-Track system, San Diego, CA) do not meet expectations either. Digitized images from video are used to capture the body of mouse and provide quantitative data about the position and movements of the animal and the pattern of these variables across time. They do not just treat the animal (e.g., mouse) as a point in the space. Instead, they handle it as a block of pixels. More information is preserved. However, they can only make use of a few simple features. For example, the mass center of the animal (e.g., mouse) is calculated and used as a means for tracking the animal (e.g., a mouse). As such, a lot of information that is critical to identify the animal's behaviors such as different postures, positions of portions of the animal's body such as limbs, is lost. These systems can only distinguish basic behaviors such as locomotion, and cannot automatically identify simple animal postures such as eating, rearing, and jumping, not to mention complex behaviors such as skilled reaching. Such behavior identification requires human intervention and input.
In addition, these systems are often developed for rats that remain relatively stationary in shape as they are in locomotion. However, other animals such as a mouse frequently stretch out, making their center of mass much less stable than a rat. As the center of gravity shifts rapidly and frequently, this falsely adds to measures such as distance traveled, making these systems highly inaccurate for mice. Further, the systems are devised to study white rats on a dark background and are not accurate for tracking other animals such as brown or black mice.
The most advanced systems are those offered by Noldus. The Noldus Observer system has a video camera, TV monitor, a high end VCR, and a PC system, all hooked together. The camera takes video footage of the mouse in a cage. This video is recorded on videotape, digitized, input into the PC system, and displayed on the computer monitor. Although the human observer can control the recorded video that is displayed, the human observer still needs to look at the animal on the screen, decide which behavior the animal is engaged in, and enter (by typing) the information into a mechanism provided by the system for storage and later analysis. While this system facilitates observation of behavior, it does not automate it, and is thus prone to human error and extremely labor intensive. The tasks of coding behavior throughout the day and building a profile of behavior for different types of animals and different strains of the same animal (e.g., different strains of mouse) is prohibitively time consuming with this equipment.
SUMMARY OF THE INVENTION hi general, the present invention is directed to systems and methods for finding patterns of behaviors and/or activities of an object using video. The invention includes a system with a video camera connected to a computer in which the computer is configured to automatically provide object identification, object motion tracking (for moving objects), object shape and posture classification, and behavior identification. Thus, the present invention is capable of automatically monitoring a video image to identify, track and classify the actions of various obj ects and their movements. The video image may be provided in real time from a camera and/or from a storage location. The invention is particularly useful for monitoring and classifying animal behavior for testing drugs and genetic mutations, but may be used in any of a number of surveillance or other applications. one embodiment the invention includes a system in which an analog video camera and a video record/playback device (e.g., VCR) are coupled to a video digitization/compression unit. The video camera may provide a video image containing an object to be identified. The video digitization/compression unit is coupled to a computer that is configured to automatically monitor the video image to identify, track and classify the actions of the object and its movements over time within a sequence of video session image frames. The digitization/compression unit may convert analog video and audio into, for example, MPEG or other formats. The computer may be, for example, a personal computer, using either a Windows platform or a Unix platform, or a Macintosh computer and compatible platform. The computer is loaded and configured with custom software programs (or equipped with firmware) using, for example, MATLAB or C/C++ programming language, so as to analyze the digitized video for object identification and segmentation, tracking, and/or behavior/activity characterization. This software may be stored in, for example, a program memory, which may include ROM, RAM, CD ROM and/or a hard drive, etc. In one variation of the invention the software (or firmware) includes a unique background subtraction method which is more simple, efficient, and accurate than those previously known. In operation, the system receives incoming video images from either the video camera in real time or pre-recorded from the video record/playback unit. If the video is in analog format, then the information is converted from analog to digital format and may be compressed by the video digitization/compression unit. The digital video images are then provided to the computer where various processes are undertaken to identify and segment a predetermined object from the image, h a preferred embodiment the object is an object (e.g., a mouse) in motion with some movement from frame to frame in the video, and is in the foreground of the video images, i any case, the digital images may be processed to identify and segregate a desired (predetermined) object from the various frames of incoming video. This process may be achieved using, for example, background subtraction, mixture modeling, robust estimation, and/or other processes. The shape and location of the desired object is then tracked from one frame or scene to another frame or scene of video images. Next, the changes in the shapes, locations, and/or postures of the object of interest maybe identified, their features extracted, and classified into meaningful categories, for example, vertical positioned side view, horizontal positioned side view, vertical positioned front view, horizontal positioned front view, moving left to right, etc. Then, the shape, location, and posture categories may be used to characterize the object's activity into one of a number of pre-defined behaviors. For example, if the object is an animal, some pre-defined normal behaviors may include sleeping, eating, drinking, walking, running, etc., and pre-defined abnormal behavior may include spinning vertical, jumping in the same spot, etc. The pre-defined behaviors may be stored in a database in the data memory. The behavior may be characterized using, for example, approaches such as rule-based label analysis, token parsing procedure, and or Hidden Markov Modeling (HMM). Further, the system maybe constructed to characterize the object behavior as new behavior and particular temporal rhythm.
In another preferred embodiment directed toward video analysis of animated objects such as animals, the system operates as follows. As a preliminary matter, normal postures and behaviors of the animals are defined and may be entered into a Normal Postures and Behaviors database, hi analyzing in a first instant, incoming video images are received. The system determines if the video images are in analog or digital format and input into a computer. If the video images are in analog format they are digitized and may be compressed, using, for example, an MPEG digitizer/compression unit. Otherwise, the digital video image may be input directly to the computer. Next, a background may be generated or updated from the digital video images and foreground objects detected. Next, the foreground objects features are extracted. Then, the foreground object shape is classified into various categories, for example, standing, sitting, etc. Next, the foreground object posture is compared to the various predefined postures stored in the database, and then identified as a particular posture or a new (unidentified) posture. Then, various groups of postures are concatenated into a series to make up a foreground object behavior and then compared against the sequence of postures, stored in for example a database in memory, that make up known normal or abnormal behaviors of the animal. The abnormal behaviors are then identified in terms of known abnormal behavior, new behavior and/or daily rhythm. In one variation of the invention, object detection is performed through a unique method of background subtraction. First, the incoming digital video signal is split into individual images (frames) in real-time. Then, the system determines if the background image derived from prior incoming video needs to be updated due to changes in the background image or a background image needs to be developed because there was no background image was previously developed. If the background image needs to be generated, then a number of frames of video image, for example 20, will be grouped into a sample of images. Then, the system creates a standard deviation map of the sample of images. Next, the process removes a bounding box area in each frame or image where the variation within the group of images is above a predetermined threshold (i.e., where the object of interest or moving objects are located). Then, the various images within the sample less the bounding box area are averaged. Final background is obtained by averaging 5-10 samples. This completes the background generation process. However, often the background image does not remain constant for a great length of time due to various reasons. Thus, the background needs to be recalculated periodically as above or it can be recalculated by keeping track of the difference image and note any sudden changes. The newly generated background image is next subtracted from the current video image(s) to obtain foreground areas that may include the object of interest.
Next, the object identification/detection process is performed. First, regions of interest (ROT) are obtained by identifying areas where the intensity difference generated from the subtraction is greater than a predetermined threshold, which constitute potential foreground object(s) being sought. Classification of these foreground regions of interest will be performed using the sizes of the ROIs, distances among these ROIs, threshold of intensity, and connectedness, to thereby identify the foreground objects. Next, the foreground object identification/detection process may be refined by adaptively learning histograms of foreground ROIs and using edge detection to more accurately identify the desired object(s). Finally, the information identifying the desired foreground object is output. The process may then continue with the tracking and/or behavior characterization step(s).
The previous embodiments are particularly applicable to the study and analysis of mice used in genetic and drug experimentation. One variation of the present invention is directed particularly to automatically determining the behavioral characteristics of a mouse in a home cage. The need for sensitive detection of novel phenotypes of genetically manipulated or drug-administered mice demands automation of analyses. Behavioral phenotypes are often best detected when mice are unconstrained by experimenter manipulation. Thus, automation of analysis of behavior in a known environment, for example a home cage, would be a powerful tool for detecting phenotypes resulting from gene manipulations or drug administrations. Automation of analysis would allow quantification of all behaviors as they vary across the daily cycle of activity. Because gene defects causing developmental disorders in humans usually result in changes in the daily rhythm of behavior, analysis of organized patterns of behavior across the day may also be effective in detecting phenotypes in transgenic and targeted mutant mice. The automated system may also be able to detect behaviors that do not normally occur and present the investigator with video clips of such behavior without the investigator having to view an entire day or long period of mouse activity to manually identify the desired behavior.
The systematically developed definition of mouse behavior that is detectable by the automated analysis according to the present invention makes precise and quantitative analysis of the entire mouse behavior repertoire possible for the first time. The various computer algorithms included in the invention for automating behavior analysis based on the behavior definitions ensure accurate and efficient identification of mouse behaviors, hi addition, the digital video analysis techniques of the present invention improves analysis of behavior by leading to: (1) decreased variance due to non-disturbed observation of the animal; (2) increased experiment sensitivity due to the greater number of behaviors sampled over a much longer time span than ever before possible; and (3) the potential to be applied to all common normative behavior patterns, capability to assess subtle behavioral states, and detection of changes of behavior patterns in addition to individual behaviors.
Development activities have been completed to validate various scientific definitions of mouse behaviors and to create novel digital video processing algorithms for mouse tracking and behavior recognition, which are embodied in a software and hardware system according to the present invention. An automated method for analysis of mouse behavior from digitized 24 hour video has been achieved using the present invention and its digital video analysis method for object identification and segmentation, tracking, and classification. Several different methods and their algorithms, including Background Subtraction, Probabilistic approach with Expectation-Maximization, and Robust Estimation to find parameter values by best fitting a set of data measurements and results proved successful. The entire behavioral repertoire of individual mice in their home cage was categorized using successive iterations by manual videotape analysis. These manually defined behavior categories constituted the basis of automatic classification. Classification criteria (based on features extracted from the foreground object such as shape, position, movement) were derived and fitted into a decision tree (DT) classification algorithm. The decision tree could classify almost 500 sample features into 5 different postures classes with an accuracy over 93%. A simple HMM system has been built using dynamic programming and has been used to classify the classified postures identified by the DT and yields an almost perfect mapping from input posture to output behaviors in mouse behavior sequences. The invention may identify some abnormal behavior by using video image information
(for example, stored in memory) of known abnormal animals to build a video profile for that behavior. For example, video image of vertical spirining while hanging from the cage top was stored to memory and used to automatically identify such activity in mice. Further, abnormalities may also result from an increase in any particular type of normal behavior. Detection of such new abnormal behaviors may be achieved by the present invention detecting, for example, segments of behavior that do not fit the standard profile. The standard profile may be developed for a particular strain of mouse whereas detection of abnormal amounts of a normal behavior can be detected by comparison to the statistical properties of the standard profile. Thus, the automated analysis of the present invention may be used to build profiles of the behaviors, their amount, duration, and daily cycle for each animal, for example each commonly used strain of mice. A plurality of such profiles may be stored in, for example, a database in a data memory of the computer. One or more of these profile may then be compared to a mouse in question and difference from the profile expressed quantitatively.
The techniques developed with the present invention for automation of the categorization and quantification of all home-cage mouse behaviors throughout the daily cycle is a powerful tool for detecting phenotypic effects of gene manipulations in mice. As previously discussed, this technology is extendable to other behavior studies of animals and humans, as well as surveillance purposes. As will be described in detail below, the present invention provides automated systems and methods for automated accurate identification, tracking and behavior categorization of an object whose image is captured with video.
BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 is a block diagram of one exemplary system configurable to find the position, shape, and behavioral characteristics of an object using automated video analysis, according to one embodiment of the present invention. Figure 2 is a block diagram of various functional portions of a computer system, such as the computer system shown in Figure 1, when configured to find the position, shape, and behavioral characteristics of an object using automated video analysis, according to one embodiment of the present invention.
Figure 3 is a flow chart of a method of automatic video analysis for object identification and characterization, according to one embodiment of the present invention. Figure 4 is a flow chart of a method of automatic video analysis for object identification and characterization, according to another embodiment of the present invention. Figure 5 is a flow chart of a method of automatic video analysis for object detection and identification, according to one variation of the present invention. Figure 6 illustrates a sample video image frame with a mouse in a rearing up posture as determined using one variation of the present invention to monitor and characterize mouse behavior.
Figure 7A is a first video image frame in a sequence with a mouse in an eating posture for illustrating background generation for a background subtraction process according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
Figure 7B is a copy of the first video image frame of Figure 7A in which the process has extracted an area of the video image related to the mouse in the foreground resulting in a "hole" which will be filled up when other frames are averaged with it for a background subtraction process according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
Figure 7C is the resulting background image for a video clip including the first video image frame of Figure 7A converted as shown in Figure 7B and averaged with subsequent video images, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
Figure 8A is a difference image between foreground and background for the image shown in Figure 7A, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
Figure 8B is the image shown in Fig. 7A after completing a threshold process for identifying the foreground image of the mouse which is shown as correctly identified, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
Figure 8C is a video image frame showing the foreground mouse object correctly identified by the system as identified with a polygon outline, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior. Figure 9 A is a video image frame showing a mouse eating, to demonstrate a b-spline approach to object location and outline identification according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
Figure 9B is a computer generated image showing the outline of the foreground mouse shown in Figure 9A after edge segmentation, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
Figure 9C is a computer generated image of the outline of the foreground mouse shown in Figure 9 A as derived from the outline of the mouse shown in Figure 9B as generated from a b-spline process, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior. Figure 10 is a chart illustrating one example of various mouse state transitions used in characterizing mouse behavior including: Horizontal (HS); Cuddled up (CU); Partially reared (PR); Vertically Reared (VR); and Forward Back (FB), along with an indication of duration of these states based on a sample, according to one variation of the present invention as applied for monitoring and characterizing mouse behavior.
DESCRIPTION OF THE PREFERRED EMBODIMENTS The past few years have seen an increase in the integration of video camera and computer technologies. Today, the integration of the two technologies allows video images to be digitized, stored, and viewed on small inexpensive computers, for example, a personal computer. Further, the processing and storage capabilities of these small inexpensive computers has expanded rapidly and reduced the cost for performing data and computational intensive applications. Thus, video analysis systems may now be configured to provide robust surveillance systems that can provide automated analysis and identification of various objects and characterization of their behavior. The present invention provides such systems and related methods.
In general, the present invention can automatically find the patterns of behaviors and/or activities of a predetermined object being monitored using video. The invention includes a system with a video camera connected to a computer in which the computer is configured to automatically provide object identification, object motion tracking (for moving objects), object shape and posture classification, and behavior identification. In a preferred embodiment the system includes various video analysis algorithms. The computer processes analyze digitized video with the various algorithms so as to automatically monitor a video image to identify, track and classify the actions of one or more predetennined objects and its movements captured by the video image as it occurs from one video frame or scene to another. The system may characterize behavior by accessing a database of object information of known behavior of the predetermined object. The image to be analyzed may be provided in real time from one or more camera and/or from storage.
In various exemplary embodiments described in detail as follows, the invention is configured to enable monitoring and classifying of animal behavior that results from testing drugs and genetic mutations on animals. However, as indicated above the system may be similarly configured for use in any of a number of surveillance or other applications. For example, the invention can be applied to various situations in which tracking moving objects is needed. One such situation is security surveillance in public areas like airports, military bases, or home security systems. The system maybe useful in automatically identifying and notifying proper law enforcement officials if a crime is being committed and/or a particular behavior being monitored is identified. The system may be useful for monitoring of parking security or moving traffic at intersections so as to automatically identify and track vehicle activity. The system may be configured to automatically determine if a vehicle is speeding or has performed some other traffic violation. Further, the system may be configured to automatically identify and characterize human behavior involving guns or human activity related to robberies or thefts. Similarly, the invention may be capable of identifying and understanding subtle behaviors involving portions of body such as forelimb and can be applied to identify and understand human gesture recognition. This could help deaf individuals communicate. The invention may also be the basis for computer understanding of human gesture to enhance the present human-computer interface experience, where gestures will be used to interface with computers. The economic potential of applications in computer-human interface applications and in surveillance and monitoring applications is enormous.
In one preferred embodiment illustrated in Figure 1, the invention includes a system in which an analog video camera 105 and a video storage/retrieval unit 110 may be coupled to each other and to a video digitization/compression unit 115. The video camera 105 may provide a real time video image containing an object to be identified. The video storage/retrieval unit 110 may be, for example, a VCR, DVD, CD or hard disk unit. The video digitization/compression unit 115 is coupled to a computer 150 that is configured to automatically monitor a video image to identify, track and classify the actions (or state) of the object and its movements (or stillness) over time within a sequence of images. The digitization/compression unit 115 may convert analog video and audio into, for example, MPEG format, Real Player format, etc. The computer may be, for example, a personal computer, using either a Windows platform or a Unix platform, or a Macintosh computer and compatible platform. In one variation the computer may include a number of components such as (1) a data memory 151, for example, a hard drive or other type of volatile or nonvolatile memory; (2) a program memory 152, for example, RAM, ROM, EEPROM, etc. that may be volatile or non- volatile memory; (3) a processor 153, for example, a microprocessor; and (4) a second processor to manage the computation intensive features of the system, for example, a math coprocessor 154. The computer may also include a video processor such as an MPEG encoder/decoder. Although the computer 150 has been shown in Figure 1 to include two memories (data memory 151 and program memory 152) and two processors (processor 153 and math co-processor 154), in one variation the computer may include only a single processor and single memory device or more then two processors and more than two memory devices. Further, the computer 150 maybe equipped with user interface components such as a keyboard 155, electronic mouse 156, and display unit 157. In one variation, the system may be simplified by using all digital components such as a digital video camera and a digital video storage/retrieval unit 110, which may be one integral unit. In this case, the video digitization/compression unit 115 may not be needed.
The computer is loaded and configured with custom software program(s) (or equipped with firmware) using, for example, MATLAB or C/C++ programming language, so as to analyze the digitized video for object identification and segmentation, tracking, and/or behavior/activity characterization. This software may be stored in, for example, a program memory 152 or data memory that may include ROM, RAM, CD ROM and/or a hard drive, etc. hi one variation of the invention the software (or firmware) includes a unique background subtraction method which is more simple, efficient, and accurate than those previously known which will be discussed in detail below, any case, the algorithms may be implemented in software and may be understood as unique functional modules as shown in Figure 2 and now described.
Referring to Figure 2, the system is preloaded with standard object information before analyzing an incoming video including a predetermined object, for example, a mouse. First, a stream of digital video including a known obj ect with known characteristics may be fed into the system to a standard object classifier module 220. A user may then view the standard object on a screen and identify and classify various behaviors of the standard object, for example, standing, sitting, lying, normal, abnormal, etc. Data information representing such standard behavior may then be stored in the standard object behavior storage modules 225, for example a database in data memory 151. Of course, standard object behavior information data sets maybe loaded directly into the standard object behavior storage module 225 from another system or source as long as the data is compatible with the present invention protocols and data structure. In any case, once the standard object behavior data is entered into the standard object behavior storage module 225, the system may be used to analyze and classify the behavior of one or more predetermined objects, for example, a mouse.
In the automatic video analysis mode, digital video (either real-time and or stored) of monitored objects to be identified and characterized is input to an object identification and segregation module 205. This module identifies and segregates a predetermined type of object from the digital video image and inputs it to an object tracking module 210. The object tracking module 210 facilitates tracking of the predetermined object from one frame or scene to another as feature information. This feature information is then extracted and input to the object shape and posture classifier 215. This module classifies the various observed states of the predetermined object of interest into various shape and posture categories and sends it to the behavior identification module 230. The behavior identification module 230 compares the object shape, motion, and posture information with shape, motion, and posture information for a standard object and classifies the behavior accordingly into the predefined categories exhibited by the standard object, including whether the behavior is normal, abnormal, new, etc. This information is output to the user as characterized behavior information on, for example, a display unit 157.
Referring now to Figure 3, a general method of operation for one embodiment of the invention will be described, i operation, in the video analysis mode the system may receive incoming video images at step 305, from the video camera 105 in real time, pre-recorded from the video storage/retrieval unit 110, and/or a memory integral to the computer 150. If the video is in analog format, then the information is converted from analog to digital format and may be compressed by the video digitization/compression unit 115. The digital video images are then provided to the computer 150 for various computational intensive processing to identify and segment a predetermined object from the image, hi a preferred embodiment, the object to be identified and whose activities is to be characterized is a moving object, for example a mouse, which has some movement from frame to frame or scene to scene in the video images and is generally in the foreground of the video images. In any case, at step 310 the digital images may be processed to identify and segregate a desired (predetermined) object from the various frames of mcoming video. This process may be achieved using, for example, background subtraction, mixture modeling, robust estimation, and/or other processes.
Next, at step 315, various movements (or still shapes) of the desired object may then be tracked from one frame or scene to another frame or scene of video images. As will be discussed in more detail below, this tracking may be achieved by, for example, tracking the outline contour of the object from one frame or scene to another as it varies from shape to shape and/or location to location. Next, at step 320, the changes in the motion of the object, such as the shapes, locations, and postures of the object of interest, maybe identified and their features extracted and classified into meaningful categories. These categories may include, for example, vertical positioned side view, horizontal positioned side view, vertical positioned front view, horizontal positioned front view, moving left to right, etc. Then, at step 325, the states of the object, for example the shape, location, and posture categories, may be used to characterize the objects activity into one of a number of pre-defined behaviors. For example, if the object is an animal, some pre-defined normal behaviors may include sleeping, eating, drinking, walking, running, etc., and pre-defined abnormal behavior may include spinning vertical, jumping in the same spot, etc. The pre-defined behaviors may be stored in a database in the data memory 151.
Types of behavior may also be characterized using, for example, approaches such as rule-based label analysis, token parsing procedure, and/or Hidden Markov Modeling (HMM). The HMM is particularly helpful in characterizing behavior that is determined with temporal relationships of the various motion of the object across a selection of frames. From these methods, the system may be capable of characterizing the object behavior as new behavior and particular temporal rhythm.
Referring now to Figure 4 a more detailed description of another preferred embodiment will be described. In this case the system is directed toward video analysis of animated objects such as animals. As a preliminary matter, at step 415 video of the activities of a standard object and known behavior characteristics are input into the system. This information maybe provided from a video storage/retrieval unit 110 in digitized video form into a standard object classified module 220. This information may then be manually categorized at step 416 to define normal and abnormal activities or behaviors by a user viewing the video images on the display unit 157 and inputting their classifications. For example, experts in the field may sit together watching recorded scenes. They may then define, for example, an animal's (e.g., a mouse) behavior(s), both qualitatively and quantitatively, with or without some help from systems like the Noldus Observer system. These cataloged behaviors may constitute the important posture and behavior database and are entered into a storage, for example a memory, of known activity of the standard object at step 420. This information provides a point of reference for video analysis to characterize the behavior of non-standard objects whose behaviors/activities need to be characterized such as genetically altered or drug administered mice. For example, normal postures and behaviors of the animals are defined and may be entered into a normal postures and behaviors database. Once information related to characterizing a standard object (s) is established, the system may then be used to analyze incoming video images that may contain an object for which automated behavior characterization is desired. First, at step 405, incoming video images are received. Next, at decision step 406, the system determines if the video images are in analog or digital format. If the video images are in analog format they are then digitized at step 407. The video may be digitized and may be compressed, using, for example, a digitizer/compression unit 115 into a convenient digital video format such as MPEG, RealPlayer, etc. Otherwise, the digital video image may be input directly to the computer 150. Now the object of interest is identified within the video images and segregated for analysis. As such, at step 408, a background may be generated or updated from the digital video images and foreground objects including a predetermined object for behavior characterization may be detected. For example, a mouse in a cage is detected in the foreground and segregated from the background. Then, at step 409, features such as centroid, the principal orientation angle of the object, the area (number of pixels), the eccentricity (roundness), and the aspect ratio of the object, and/or shape in terms of convex hull or b-spline, of the foreground object of interest (e.g., a mouse) are extracted. Next, at step 410, the foreground object shape and postures are classified into various categories, for example, standing, sitting, etc.
Then, at step 411, the foreground object (e.g., a mouse) posture maybe compare to the various predefined postures in the set of known postures in the standard object storage of step 420, which may be included in a database. At steps 412, the observed postures of the object contained in the analyzed video image may be classified and identified as a particular posture known for the standard object or a new previously unidentified posture. Next, at step 413, various groups of postures maybe concatenated into a series to make up a foreground object behavior that is then compared against the sequence of postures, stored in for example a database in memory, that make up a known standard object behavior. This known standard behavior is, in a preferred embodiment, normal behavior for the type of animal being studied. However, the known activity of the standard object may be normal or abnormal behavior of the animal. In either case, at step 414, the abnormal behaviors are then identified in terms of (1) known abnormal behavior; (2) new behavior likely to be abnormal; and/or (3) daily rhythm differences likely to be abnormal behavior. Known normal behavior may also be output as desired by the user. This information is automatically identified to the user for their review and disposition. In one variation of the invention, the information output may include behavior information that is compatible with current statistical packages such as Systat and SPSS.
In one embodiment of the invention as illustrated in Figure 5, object detection is performed through a unique method of background subtraction. First, at step 405, incoming video is provided to the system for analysis. This video may be provided by digital equipment and input to the object identification and segregation module 205 of the computer 150. Next, at step 505, the incoming digital video signal may be split into individual images (frames) in real-time. This step maybe included if it is desired to carry out real-time analysis. Then, at decision step 506, the system determines if the background image needs to be developed because there was no background image developed previously or the background image has changed. If the background image needs to be generated or updated, then at step 507 a background image is generated by first grouping a number of frames or images into a sample of video images, for example 20 frames or images. The background may need to be updated periodically due to changes caused by, for example, lighting and displacement of moveable objects in the cage, such as the bedding. Then, at step 508 the system generates a standard deviation map of the group of images. Next, at step 509, an object(s) bounding box area is identified and removed from each frame or image to create a modified frame or image. The bounding box area is determined by sensing the area wherein the variation of a feature such as the standard deviation of intensity is above a predetermined threshold. Thus, an area in the digitized video image where the object of interest in motion is located is removed leaving only a partial image. Then, at step 510, the various modified images within the group, less the bounding box area, are combined, for example averaged, to create a background image at step 511.
Since varying pixels are not used in averaging, "holes" will be created in each image that is being used in the averaging process. Over time, not all frames will have these holes at the same location and hence, a complete background image is obtained after the averaging process. Final background is obtained by averaging 5-10 samples. This completes at least one iteration of the background generation process.
The background image does not remain constant for a great length of time due to various reasons. For example, the bedding in a mouse cage can shift due to the activity of the mouse. External factors such as change in illumination conditions also require background image recalculations. If the camera moves, then, background might need to be changed. Thus, the background typically needs to be recalculated periodically as described above or it can be recalculated by keeping track of the difference image and note any sudden changes such as an increase in the number of particular color (e.g., white) pixels in the difference image or the appearance of patches of the particular color (e.g., white) pixels in another area of the difference image, hi any case, the newly generated background image may then be combined with any existing background image to create a new background image at step 511.
The newly generated background image is next, at step 512, subtracted from the current video image(s) to obtain foreground areas that may include the object of interest.
Further, if the background does not need to be updated as determined at decision step 506, then the process may proceed to step 512 and the background image is subtracted from the current image, leaving the foreground objects.
Next, at steps 513-518, the object identification/detection process is performed. First, at step 513, regions of interest (ROI) are obtained by identifying an area where the intensity difference is greater than a predetermined threshold, which constitute potential foreground object(s) being sought. Classification of these foreground regions of interest will be performed using the sizes of the ROIs, distances among these ROIs, threshold of intensity, and connectedness to identify the foreground objects. Next, the foreground object identification/detection process may be refined by utilizing information about the actual distribution (histograms) of the intensity levels of the foreground object and using edge detection to more accurately identify the desired object(s).
At step 514, during both the background generation and background subtraction steps for object identification, the system continuously maintains a distribution of the foreground object intensities as obtained. A lower threshold may be used to thereby permit a larger amount of noise to appear in the foreground image in the form of ROIs. Thus, at step 514, a histogram is then updated with the pixels in the ROI. At step 515, plotting a histogram of all the intensities of a particular color pixels over many images, provides a bi-modal shape with the larger peak corresponding to the foreground object's intensity range and the smaller peak corresponding to the noise pixels in the ROI's images. Now, at step 516, having "learned" the intensity range of the foreground object, only those pixels in the foreground object that conform to this intensity range are selected, thereby identifying the foreground object more clearly even with background that is fairly similar.
In any case, next at step 517 the foreground object of interest may be refined using edge information to more accurately identify the desired object. An edge detection mechanism such as Prewitt operator is applied to the original image. Adaptive thresholds for edge detections can be used. Once the edge map is obtained, the actual boundary of the foreground object is assumed to be made up of one or more segments in the edge map, i.e., the actual contour of the foreground objects comprises edges in the edge map. The closed contour of the "detected" foreground object is broken into smaller segments, if necessary. Segments in the edge map that are closest to these contour segments according to a distance metric are found to be the desired contour. One exemplary distance metric is the sum of absolute normal distance to the edge map segment from each point in the closed contour of the "detected" foreground object. Finally, at step 518 the information identifying the desired foreground object is output. The process may then continue with tracking and/or behavior characterization steps.
The previous embodiments are generally applicable to identifying, tracking, and characterizing the activities of a particular object of interest present in a video image, e.g., an animal, a human, a vehicle, etc. However, the invention is also particularly applicable to the study and analysis of animals used for testing new drugs and/or genetic mutations. As such, a number of variations of the invention related to determining changes in behavior of mice will be described in more detail below using examples of video images obtained. One variation of the present invention is designed particularly for the purpose of automatically determining the behavioral characteristics of a mouse. The need for sensitive detection of novel phenotypes of genetically manipulated or dmg-administered mice demands automation of analyses. Behavioral phenotypes are often best detected when mice are unconstrained by experimenter manipulation. Thus, automation of analysis of behavior in a home cage would be a preferred means of detecting phenotypes resulting from gene manipulations or drug administrations. Automation of analysis as provided by the present invention will allow quantification of all behaviors and may provide analysis of the mouse's behavior as they vary across the daily cycle of activity. Because gene defects causing developmental disorders in humans usually result in changes in the daily rhythm of behavior, analysis of organized patterns of behavior across the day may be effective in detecting phenotypes in transgenic and targeted mutant mice. The automated system of the present invention may also detect behaviors that do not normally occur and present the investigator with video clips of such behavior without the investigator having to view an entire day or long period of mouse activity to manually identify the desired behavior.
The systematically developed definition of mouse behavior that is detectable by the automated analysis of the present invention makes precise and quantitative analysis of the entire mouse behavior repertoire possible for the first time. The various computer algorithms included in the invention for automating behavior analysis based on the behavior definitions ensure accurate and efficient identification of mouse behaviors. In addition, the digital video analysis techniques of the present invention improves analysis of behavior by leading to: (1) decreased variance due to non-disturbed observation of the animal; (2) increased experiment sensitivity due to the greater number of behaviors sampled over a much longer time span than ever before possible; and (3) the potential to be applied to all common normative behavior patterns, capability to assess subtle behavioral states, and detection of changes of behavior patterns in addition to individual behaviors. Development activities have been complete to validate various scientific definition of mouse behaviors and to create novel digital video processing algorithms for mouse tracking and behavior recognition, which are embody in software and hardware system according to the present invention.
Various lighting options for videotaping have been evaluated. Lighting at night as well as with night vision cameras was evaluated. It has been determined that good quality video was obtained with normal commercial video cameras using dim red light, a frequency that is not visible to rodents. Videos were taken in a standard laboratory environment using commercially available cameras 105, for example a Sony analog camera, to ensure that the computer algorithms developed would be applicable to the quality of video available in the average laboratory. The commercially available cameras with white lighting gave good results during the daytime and dim red lighting gave good results at night time.
Referring again to Figure 3, the first step in the analysis of home cage behavior is an automated initialization step that involves analysis of video images to identify the location and outline of the mouse, as indicated by step 310. Second, the location and outline of the mouse are tracked over time, as indicated by step 315. Performing the initialization step periodically may be used to reset any propagation errors that appear during the tracking step. As the mouse is tracked over time, its features including shape are extracted, and used for training and classifying the posture of the mouse from frame to frame, as indicated by step 320. Posture labels are generated for each frame, which are analyzed over time to determine the actual behavior, as indicated by step 325. These steps will now be described in detail using the particular application of mouse behavior characterization.
I. Mouse Identification
A typical video frame of a mouse in its home cage is shown in Figure 6. In this video frame a mouse is shown in a rearing up posture. Many such frames make up the video of, for example, a 24 hour mouse behavior monitoring session. As previously indicated, there are several approaches available for identifying and tracking moving objects in a scene. One of the simplest and most straightforward methods is background subtraction of which one example was provided in Figure 5.
A. Background Subtraction Background subtraction as used in the present invention generally involves generating a still background image from all or a subset of the frames in a video clip and subtracting this background image from any given image to obtain the foreground objects.
The background is generated by averaging many frames, for example approximately 100 frames of the video, after compensating for any shifts caused by the motion of the camera. Even if foreground objects are present in the frames that are being averaged to generate the background image, their unwanted contribution is negligible when large numbers of frames are used for the background calculation, assuming that the foreground object does not remain at the same location throughout. Nevertheless, it may be helpful to not consider those pixels where the foreground object is present. In one implementation of the background averaging process, only the stationary pixels in an image are considered to avoid the unwanted contributions of the foreground moving objects. The stationary and non-stationary pixels are determined by analyzing the local variations of each pixel of a series of frames over a short time period as indicated in step 509 of figure 5. The standard deviation from the mean is first calculated for each pixel. If the standard deviation is greater than a chosen threshold, we tag those pixels as being non- stationary or varying pixels. Those pixels that are below the threshold may be tagged as stationary or constant pixels. Only those stationary pixels are used in the averaging process to calculate the background. Since the varying pixels are not used, there will be "holes" in each image that is being used in the averaging process. Over time, not all frames will have these holes at the same location and hence, a complete background image may be obtained with the averaging process. Once the background image has been obtained, subtraction of the background image from the given analyzed image yields the foreground objects. One exemplary algorithm for such a background subtraction method will now be described.
Let T be the number of frames that are being averaged to calculate the background. Let P(Xtytt) be the pixel value at position (x, y) and frame number t , then the mean, p x } , and standard deviation, σ(Λ. y) , for that location are defined respectively as,
_ γ T
P(χ,y) ~ ~LfΔ P{χ,y.t)
1 .=ι
1 τ σ(χ,y) = ~ψZ[ £-< (Pi O ~ P(χ.y) '
If the standard deviation, σ x y) , for a particular pixel is greater than a threshold, for example an intensity of 64 on the scale of 0 to 255 was used for a video clip with mouse in a cage, then it is omitted from the background image calculation.
Typically, the background image of a video session does not remain constant for a great length of time. For example, in the case of monitoring mouse behavior the bedding in the mouse cage can shift due to the activity of the mouse. Hence, the background may need to be recalculated periodically. External factors such as change in illumination conditions may require background image recalculations. If the camera 105 moves, then the background image might need to be recalculated.
Another method, other than performing background recalculations periodically, is to keep track of the difference image and note any sudden changes such as an increase in the number of white pixels in the difference image or the appearance of patches of white pixels in another area of the difference image.
An example of some screen shots of one exemplary background subtraction process used for monitoring a mouse with the present invention is shown in Figures 7 A, 7B and 7C. Figure 7 A illustrates a first frame in a sequence with the mouse in an eating posture 705. Figure 7B illustrates the same frame of the video image now having the area of the frame in which the pixels are changing identified as a blocked out 710. As a result the background has a "hole" 710 (shown in black). This hole 710 will be filled with an image indicative of the true complete background image when other frames are averaged with it. In order to generate a good background from a video sequence, several samples should first be generated. For example, a 10-20 frame sample (30 frames per second) from a video clip is taken and then averaged to generate one sample. Once a sample is obtained, it may be used to update a previously existing background. A sufficiently complete background may be obtained by averaging a number of sample sets, for example 5-10 samples sets. Figure 7C illustrates the resulting background image for the video clip once the group of frames in a sample set and a number of sample sets are averaged together. As can be seen in Figure 7C, this method is quite successful at generating a reasonably complete background image (less the foreground object of interest) to be used in the background subtraction process for identifying and segregating a desired object, in this case a mouse. One primary advantage of this technique is its low complexity that enables the background recalculations and foreground object detection to be performed with ease. This makes the background subtraction method of the present invention well suited for use in realtime processing applications.
B. Other Algorithms for Mouse Identification
Various other algorithms may be used for object or mouse identification. For example, one might use a mixture model and/or robust estimation algorithms in addition to, or in place of, background subtraction. These algorithms are newly developed theory in image sequence processing and object segmentation. They may handle object segmentation better than background subtraction in certain circumstances. Preliminary analysis indicates that mixture model and/or robust estimation algorithms may have excellent results for mouse identification.
π. Location and Outline Identification and Feature Extraction
In any case, once the background has been generated, it is then used to determine the foreground objects by taking the intensity difference and applying a threshold determination procedure to remove noise. This step may involve threshold determination on both the intensity and the size of region. An 8-connection labeling procedure may be performed to screen out disconnected small noisy regions and improve the region that corresponds to the mouse. In the labeling process, all pixels in a frame will be assigned a label as foreground pixel or background pixel. Thresholding has generated labels for certain pixels. Neighbors of those labeled pixels that have not been labeled may obtain the same label as the labeled pixel. Eight-connectedness defines 8 corner-adjacent pixels that are all neighbors. The remaining regions indicated to be foreground objects are much smaller compared to the region of mouse, thus a size criteria is used to select the larger mouse region. The outline or contour of this foreground object is thus determined.
Further, the convex hull of the pixels is used in the foreground object for representation. Convex hull H of an arbitrary set S, which is a region in the frame in this case, is the smallest set containing S. The set difference H-S is called the convex deficiency D of the set S. The region S' boundary can be partitioned by following the contour of S and marking the points at which transition is made into or out of a component of the convex deficiency. These marking points can be connected into a polygon that gives a description of the region. The centroid (or center of mass) of the foreground object is calculated and is used for representing the location of the object (e.g., mouse).
Figures 8 A, 8B and 8C illustrate the results of the location and object outline identification for a mouse using the present invention. Figure 8A illustrates a difference image between foreground and background for the image in Figure 7A. Figure 8B illustrates the image after thresholding showing the foreground mouse 705 object correctly identified. Figure 8C illustrates a video image showing the foreground object, a mouse correctly identified with a polygon outline 805, created using convex hull approach as described above. Another method of location and outline identification that may improve the representation of the shape of the mouse is the b-spline method. B-spline are piecewise polynomial functions that can provide local approximation of contours of shapes using a small number of parameters and the piecewise smooth lines can be uged to represent the outline of the object area. This is useful because human perception of shapes is deemed to be based on curvatures of parts of contours (or object surfaces). This is especially true since shapes of mice are curvatures at any time. This representation may thus results in compression of boundary data as well as smoothing of coarsely digitized contours.
Suppose the mouse shape extracted is represented as a set of ordered boundary points Wj = (Xj, Yt ), with 0 ≤ i < n . This set of points is to be approximated by a B-spline representation as follows: iv-l
P{t) = ∑QkBk(t) k=0 where the Bk are modified B-spline basis functions, and P(O)= P(.V) to constitute a close shape. Qt ≡ (Qu , Q2t ) are so called control points, which are not only the coefficients in this equation, but also physically define vertices of a polygon that guides the splines to trace a smooth curve. Using standard Least-square minimization method, to minimize:
Figure imgf000028_0001
where t,- is the knots associated with k where the spline functions are tied together. Two equations can be obtained:
∑MuQu = ∑Bt(tj)Xι ∑MuQv = f (f . k=0 ι=0 A-=0 ι=0 where 0 < / < yV and = ∑n^Br{tk)Bs(tk) . Based on the silhouette obtained from background subtraction, a series of image processing procedures may be performed first to detect edge using a sobel edge detection algorithm and then, using morphological operations to trim edge points to ensure that the edge points are singly chained.
In order to proceed, a fixed reference point on the closed shape is required. We make use of the features we have extracted for the shape and use the angle, which indicates the direction of the principal axis derived through Principle Component Analysis (CPA), to derive that reference point. A straight line that goes through the centroid with that angle is generated and the point at which this straight line intersects the edge pixel is the reference point. We use the reference point as the starting point to order those edge pixels clockwise to facilitate the solution of the above equations. We obtain a matrix of the control points, which define uniquely the b-spline function.
One example of the use of the B-Spline algorithm implemented in the present invention is illustrated in Figures 9 A - 9C. The original image, the detected edge, and the plotted b-spline function where the vertices of the curve are the control points, are shown in Figures 9A, 9B, and 9C, respectively. Figure 9A illustrates an exemplary video image frame of mouse eating 705. Figure 9B illustrates the segmented edge 905 of the mouse 705 found in Figure 9 A. Figure 9C illustrates a b-spline representation of the mouse edge 910 extrapolated from the segmented edge of the mouse found in Figure 9 A.
As a result, either b-spline representation, or convex hull representation can be used as features of foreground object, in addition to other features that include but not limited to: centroid, the principal orientation angle of the object, the area (number of pixels), the eccentricity (roundness), and the aspect ratio of object.
in. Mouse tracking
Ideal tracking of foreground objects in the image domain involves a matching operation to be performed that identifies corresponding points from one frame to the next. This process may become computationally too consuming or expensive to perform in an efficient manner. Thus, one approach is to use approximations to the ideal case that can be accomplished in a short amount of time. For example, tracking the foreground object may be achieved by merely tracking the outline contour from one frame to the next in the feature space (i.e., identified foreground object image).
In one variation of the invention, tracking is performed in the feature space, which provides a close approximation to tracking in the image domain. The features include the centroid, principal orientation angle of the object, area (number of pixels), eccentricity (roundness), and the aspect ratio of object with lengths measured along the secondary and primary axes of the object. In this case, let S be the set of pixels in the foreground object, A denote the area in number of pixels, (Cx, Cy) denote the centroid, φ denote the orientation angle, E denote the eccentricity, and R denote the aspect ratio. Then, Ά S Λ S
Let us define three intermediate terms, called second order moments, m. 2,0 ∑(x-Cx)(y-Cy)
Figure imgf000030_0001
Using the central moments, we define,
1 _ 2mj . φ = — arctan-
2 ™2fi -mϋ>2
Figure imgf000030_0002
R is equal to the ratio of the length of the range of the points projected along an axis perpendicular to φ, to the length of the range of the points projected along an axis parallel to φ. This may also be defined as the aspect ratio (ratio of width to length) after rotating the foreground obj ect by φ.
Tracking in the feature space involves following feature values from one frame to the next. For example, if the area steadily increases, it could mean that the mouse is coming out of a cuddled up position to a more elongated position, or that it could be moving from a front view to a side view, etc. If the position of the centroid of the mouse moves up, it means that the mouse may be rearing up on its hind legs. Similarly, if the angle of orientation changes from horizontal to vertical, it may be rearing up. These changes can be analyzed with combinations of features also.
However, it is possible for a b-spline representation to be used to perform near- optimal tracking efficiently in the image domain (i.e., the complete image before background is subtracted).
TV. Mouse posture classification
Once the features are obtained for the frames in the video sequence, the foreground state of the mouse is classified into one of the given classes. This involves building a classifier that can classify the shape using the available features. This information may be stored in, for example, a database in, for example, a data memory, hi one variation of the invention a Decision Tree classifier (e.g., object shape and posture classifier 215) was implemented by training the classifier with 488 samples of digitized video of a standard, in this case, normal mouse. Six attributes (or features) for each sample were identified. Five posture classes for classification were identified as listed below.
1. Horizontally positioned, side view, either in normal state or elongated.
2. Vertically positioned, either rearing or hanging from top (e.g., See Figures 6 and 8C).
3. Cuddled up position (like a ball).
4. Horizontally positioned, but either front or back view, i.e., axis of mouse along the viewer's line of sight.
5. Partially reared, e.g., when drinking or eating, sitting on hind legs (e.g., See Figure 7A).
The system of the present invention was exercised using these classifications. The distribution of the samples amongst the five classes is shown in Table 1. Performing a 10-fold cross-validation on the 488 training samples, a combined accuracy of 93.65% was obtained indicating that the classifier was performing well. This in the range of the highest levels of agreement between human observers. The cross-validation procedure involves randomly dividing a training set into N approximately equal sets, and for each of the N folds or iterations, one set is set aside for testing while the remaining N -1 sets are used as training samples. Accuracy values for individual classes are indicated in the last column of Table 1. Table 2 shows the overall accuracy values for each fold. We assign appropriate labels for each frame depending on the class to with it was classified to.
Table 1 : Distribution of samples in the five classes and the accuracy values for each class.
Figure imgf000031_0001
Figure imgf000032_0001
It is evident from the data in the Table 1 that class 2 was arguably the most easily for the automated system to identify. This is because the vertical position is quite distinct from the other postures. On the other hand, classes 3 and 4 yield the poorest results due to similarity in the two postures. Both classes depict the mouse as a fairly round object, the only primary difference being the size of the object - class 3 sizes are expected to be slightly larger than those from class 4.
Table 2: Accuracy results for each fold for a cross-validation test.
Figure imgf000033_0001
As illustrated by the tables, the present system provides good accuracy for mouse shape and posture recognition and classification.
V. Behavior identification
Once the postures in all the frames in the video clip have been labeled, we now need to determine certain pre-defined behaviors as defined in the database based on the postures that have been identified. Currently, 23 such behaviors have been defined which include: sleep, groom, eat, rear up on the hind legs, drink, walk, jump, hang from the top of the cage, stretch, dig, awaken, arousal, twitch, stretch, yawn, pause, circle, forage, chew, urinate, defecate. In addition, grooming is divided into licking and scratching and rearing up into supported and unsupported. This process will be accomplished in real-time so that immediate results will be reported to investigators or stored in a database. One approach is to use a rule-based label analysis procedure (or a token parsing procedure) by which the sequence of labels is analyzed and identify particular behaviors when its corresponding sequence of labels is derived from a video frame being analyzed. For example, if a long sequence (lasting for example several minutes) of the "Cuddled up position" label (Class 3) is observed, and if its centroid remains stationary, then, it may be concluded that the mouse is sleeping. If the location of the waterspout is identified, and if we observe a series of "partially reared" (Class 5) labels, and if the position of the centroid, and the mouse's angle of orientation fall within a small range that has been predetermined, the system can determine and identify that the mouse is drinking. It may also be useful for certain extra conditions to be tested such as, "some part (the mouth) of the mouse must touch the spout if drinking is to be identified" in addition to temporal characteristics of the behavior.
Another approach involves using a probabilistic model such as Hidden Markov Models (HMMs), where models may be built for each class of behavior with framing samples. These models may then be used to identify behaviors based on the incoming sequence of labels. The HMM can provide significant added accuracy to temporal relationships for proper complex behavior characterization.
Referring now to Figure 10, various exemplary mouse state transitions tested in the present invention are illustrated. The five exemplary mouse state transitions include: (1) Horizontal (HS) 1005, (2) Cuddled up (CU) 1010, (3) Partially reared (PR) 1015, (4) Vertically Reared (VR) 1020, and (5) Forward Back (FB) 1025 postures. As illustrated, Figure 10 shows the five posture states and the duration for which a mouse spent in each state in an exemplary sample video clip. One example of a pattern that is understandable and evident from the figure is that the mouse usually passes through the partially reared (PR) 1015 state to reach the vertically reared (VR) 1025 state from the other three ground-level states. The states are defined according to the five posture classes mentioned previously.
Many important features can be derived from this representation, e.g., if the state changes are very frequent, it would imply that the mouse is very active. If the mouse remained in a single ground-level state such as "cuddled-up" (class 3) for an extended period of time, the system may conclude that the mouse is sleeping or resting. The sequence of transitions are also important, e.g., if the mouse rears (class 2) from a ground-level state such as "Horizontally positioned" (class 1), it should pass briefly through the partially reared state (class 5). Techniques such as HMMs exploit these types of time-sequence-dependent information for performing classification.
A simple HMM system has been created using dynamic programming to find the best match between the input sequence and paths through the state machine. It has been used to classify events in one of the mouse behavior sequences. The HMM system was provided with a sequence of tokens representing recognized actions or views from a benchmark mouse-rear video; this file includes views from five different postures, which are:
c = cuddled_posture_view f = front_or_back_view h = horizontal_side_view (1) p = partially_reared_view r = reared_or_vertical_view
Each of these represents a posture of the mouse and all together they constitute five (5) tokens. These tokens cause the HMM to go from one (hidden) state to another. The HMM may classify behavior into one of, for example, four hidden states: horizontal, rearing, cuddled, or indecisive:
0 = horizontal; 1 = cuddled; 2 = rearing; 3 = indecisive; (2)
Thus, the HMM defining mouse behaviors can be described as:
size 4 5; start 0 stop O; symbols c fh p r
This approach to a HMM for mouse behavior characterization may result in a number of mismatched cases which maybe categorized into three (3) types: (a) one mismatch (the last token) because the start and stop states were forced to be 0; (b) the PARTIALLY_REARED may be mapped to indecisive, but this may only be a difference in the naming; and (c) the FRONT_OR_BACK may be mapped to the same value as HORIZ_SIDE_VIEW (21 cases). However, it is reasonable that both FRONT_OR_BACK and HORIZ_SIDE_VIEW are mapped to the same classification because both are similar to each other "behaviorally", i.e., from the mouse's point of view, being FRONT_OR_BACK or HORIZ_STDE are the same thing. This may yield a perfect mapping from input to output. This is but one exemplary approach for the frame work for defining a HMM analysis for determining mouse behavior. Although the above exemplary embodiment is directed to a mouse analyzed in a home cage, it is to be understood that the mouse (or any object) may be analyzed in any location or environment. Further, the invention in one variation may be used to automatically detect and characterize one or more particular behaviors. For example, the system could be configured to automatically detect and characterize an animal freezing and/or touching or sniffing a particular object. Also, the system could be configured to compare the object's behavior against a "norm" for a particular behavioral parameter. Other detailed activities such as skilled reaching and forelimb movements as well as social behavior among groups of animals can also be detected and characterized. hi summary, when a new video clip is analyzed, the system of the present invention first obtains the video image background and uses it to identify the foreground objects. Then, features are extracted from the foreground objects, which are in turn passed to the decision tree classifier for classification and labeling. This labeled sequence is passed to a behavior identification system module that identifies the final set of behaviors for the video clip. The image resolution of the system that has been obtained and the accuracy of identification of the behaviors attempted so far have been very good and resulted in an effective automated video image object recognition and behavior characterization system.
The invention may identify some abnormal behavior by using video image information (for example, stored in memory) of known abnormal animals to build a video profile for that behavior. For example, video image of vertical spinning while hanging from the cage top was stored to memory and used to automatically identify such activity in mice. Further, abnormalities may also result from an increase in any particular type of normal behavior.
Detection of such new abnormal behaviors may be achieved by the present invention detecting, for example, segments of behavior that do not fit the standard profile. The standard profile may be developed for a particular strain of mouse whereas detection of abnormal amounts of a normal behavior can be detected by comparison to the statistical properties of the standard profile. Thus, the automated analysis of the present invention may be used to build a profile of the behaviors, their amount, duration, and daily cycle for each animal, for example each commonly used strain of mice. A plurality of such profiles may be stored in, for example, a database in a data memory of the computer. One or more of these profile may then be compared to a mouse in question and difference from the profile expressed quantitatively.
The techniques developed with the present invention for automation of the categorization and quantification of all home-cage of mouse behaviors throughout the daily cycle is a powerful tool for detecting phenotypic effects of gene manipulations in mice. As previously discussed, this technology is extendable to other behavior studies of animals and humans, as well as surveillance purposes, hi any case, the present invention has proven to be a significant achievement in creating an automated system and methods for automated accurate identification, tracking and behavior categorization of an object whose image is captured in a video image.
Although particular embodiments of the present invention have been shown and described, it will be understood that it is not intended to limit the invention to the preferred or disclosed embodiments, and it will be obvious to those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the present invention. Thus, the invention is intended to cover alternatives, modifications, and equivalents, which may be included within the spirit and scope of the invention as defined by the claims.
For example, the present invention may also include audio analysis and/or multiple camera analysis. The video image analysis maybe augmented with audio analysis since audio is typically included with most video systems today. As such, audio may be an additional variable used to determine and classify a particular objects behavior. Further, in another variation, the analysis may be expanded to video image analysis of multiple objects, for example mice, and their social interaction with one another, hi a still further variation, the system may include multiple cameras providing one or more planes of view of an object to be analyzed. In an even further variation, the camera may be located in remote locations and the video images sent via the Internet for analysis by a server at another site, hi fact, the standard object behavior data and/or database may be housed in a remote location and the data files may be downloaded to a stand alone analysis system via the Internet, in accordance with the present invention. These additional features/functions adds versatility to the present invention and may improve the behavior characterization capabilities of the present invention to thereby achieve object behavior categorization which is nearly perfect to that of a human observer for a broad spectrum of applications.
All publications, patents, and patent applications cited herein are hereby incorporated by reference in their entirety for all purposes.

Claims

WHAT IS CLA ED IS:
1. A system, comprising: a computer configured to determine a position and shape of an object of interest from video images and characterize activity of said object of interest based on analysis of changes in said position and said shape over time.
2. The system of claim 1, further comprising: a video camera coupled to said computer for providing said video images.
3. The system of claim 2, further comprising: a video digitization unit couple to said video camera and said computer for converting said video images provided by said video camera from analog to digital format.
4. The system of claim 3, further comprising: a storage/retrieval unit coupled to said video digitization unit, said video camera, and said computer, for storing said video images and standard object video images.
5. The system of claim 1, wherein said computer includes an object identification and segregation module receiving said video images.
6. The system of claim 5, wherein said object identification and segregation module operates using a background subtraction algorithm in which a plurality of said video images are grouped into a set, a standard deviation map of the set of video images is created, a bounding box where a variation is greater than a predetermined threshold is remove from said set of video images, and the set of images less said bounding boxes is averaged to produce a background image.
7. The system of claim 6, wherein said computer further includes a behavior identification module for characterizing activity of said object, said behavior identification module being coupled to said object identification and segregation module.
8. The system of claim 7, wherein said computer further includes an object tracking module for tracking said object from one frame of said video images to another frame, and an object shape and location change classifier for classifying the activity of said object, coupled to each other, said object identification and segregation module, and said behavior identification module.
9. The system of claim 8, wherein said computer further includes a standard object behavior storage module that stores information about known behavior of a predetermined standard object for comparing the activity of said object, said standard object behavior storage module being coupled to said behavior identification module, and a standard object classifier module coupled to said standard object behavior module.
10. The system of claim 5, wherein said computer further includes a standard object behavior storage module that stores information about known behavior of a predetermined standard object for comparing the activity of said object, said standard object behavior storage module being coupled to said behavior identification module.
11. The system of claim 1 , wherein said obj ect is a living obj ect.
12. The system of claim 1, wherein said object is an animal. 15
13. The system of claim 1 , wherein said obj ect is a mouse.
14. The system of claim 1, wherein said object is a human.
15. The system of claim 1, wherein said object is a man made machine.
16. A method of determining and characterizing activity of an object using computer processing of video images, comprising the steps of:
20 detecting a foreground object of interest in said video images; tracking changes to said foreground object over a plurality of said video images; identifying and classifying said changes to said foreground object; and characterizing said activity of said foreground object based on comparison to
25 activity of a standard obj ect.
17. The method of claim 16, wherein said step of characterizing said activity includes the steps of: describing a sequence of postures as behavior primitives; and aggregating behavior primitives into actual behavior over a range of images.
18. The method of claim 16, wherein said foreground obj ect detection includes the step of generating a background image from an average of a set of individual frames of said video images.
19. * The method of claim 18, wherein said step of generating a background image includes the step of determining variation in intensity of pixels within said individual frames to identify a region where said foreground object is located.
20. The method of claim 19, wherein said step of generating a background image further includes the step of using non- variant pixels of the video images to generate said background image.
21. The method of claim 20, wherein said step of generating a background image is performed periodically to correct for changes in background objects and small movements of a camera capturing said video images.
22. The method of claim 16, wherein said detecting a foreground object includes using a background subtraction method comprising the steps of: multiply frames in a neighborhood of current image; apply a lenient threshold on a difference between a current image and a background so as to determine a broad region of interest; classify by intensity various pixels in said region of interest to obtain said foreground object; and Pply edge information to refine contours of said foreground object image.
23. The method of claim 16, wherein said step of detecting said foreground includes the step of manual identification of foreground objects to be tracked and characterized.
24. The method of claim 17, wherein said posture determination and description includes using statistical and contour-based shape information.
25. The method of claim 24, wherein said step of identifying and classifying changes to said foreground object includes using statistical shape information selected from the group consisting of: area of the foreground object; centroid of the foreground object; bounding box and its aspect ratio of the foreground object; eccentricity of the foreground object; and a directional orientation of the foreground object relative to an axis as generated with a Principal Component Analysis.
26. The method of claim 24, wherein said step of identifying and classifying changes to said foreground object uses contour-based shape information selected from the group consisting of b-spline representation, convex hull representation, and corner points.
27. The method of claim 24, wherein said step of identifying and classifying changes to said foreground object includes identifying a set of model postures and their description information, said set of model postures including horizontal posture, vertical posture, eating posture, or sleeping posture.
28. The method of claim 27, wherein said step of identifying and classifying changes to said foreground object includes classifying the statistical and contour-based shape information from a current image to assign a best-matched posture.
29. The method of claim 17, wherein the said step of describing said behavior primitives includes the step of identifying patterns of postures over a sequence of images.
30. The method of claim 29, wherein said step of describing said behavior primitives step further includes the step of analyzing temporal information selected from the group consisting of direction and magnitude of movement of the centroid, increase and decrease of the eccentricity, increase and decrease of the area, increase and decrease of the aspect ratio of the bounding box, change in the b-spline representation points, change in the convex hull points, and direction and magnitude of corner points.
31. The method of claim 29, wherein the step of describing said behavior primitives step includes behavior of a standard object such as stationary, moving for left to right and vice versa, standing up, and falling down.
32. The method of claim 29, wherein the step of describing said behavior primitives step includes a step for providing a means for entering user defined customized behavior primitives.
33. The method of claim 17 , wherein the said step of determining actual behavior by aggregating behavior primitives includes the step of analyzing temporal ordering of the primitives, such as using information about a transition from a previous behavior primitive to a next behavior primitive.
34. The method of claim 33, wherein said temporal analysis is a time-series analysis such as Hidden Markov Model (HMMs).
35. The method of claim 33 , wherein the said step of determining actual behavior includes identifying actual behavior selected from a group consisting of sleeping, eating, roaming around, grooming, and climbing.
36. A method for background subtraction of a video image, comprising the steps of: grouping a number of images into a set of video images; creating a standard deviation map of the grouped images; removing a bounding box area of said image where variation is above a predetermined threshold to create a partial image; and combining said partial image with an existing set of partial images by averaging the set of images to generate a complete background image deplete of a desired foreground object.
37. The method of claim 36, further comprising the step of subtracting said complete background image from a cuπent image so as to obtain said desired foreground object.
38. The method of claim 36, wherein said steps are repeated periodically to update said complete background image.
39. A system, comprising: a computer configured to detect and characterize at least a single behavior of an object of interest based on movement of said object, using video image analysis.
40. The system of claim 39, wherein said object is an animal and said behavior is detecting when said animal is freezing or a touch or sniff of a particular item.
41. The system of claim 39, wherein said object is an animal and said detecting and characterizing said behavior is determined by comparing behavior of said animal against a predetermined norm.
42. The system of claim 39, wherein said object is an animal and characterizing said behavior is determined by analyzing a daily pattern of said object against a statistical norm so as to detect effects of drugs or genetic manipulations on said anima.
PCT/US2001/043282 2000-11-24 2001-11-19 System and method for object identification and behavior characterization using video analysis WO2002043352A2 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP01987014A EP1337962B9 (en) 2000-11-24 2001-11-19 System and method for object identification and behavior characterization using video analysis
JP2002544950A JP2004514975A (en) 2000-11-24 2001-11-19 System and method for object identification and behavior characterization using video analysis
AU2002239272A AU2002239272A1 (en) 2000-11-24 2001-11-19 System and method for object identification and behavior characterization using video analysis

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US09/718,374 US6678413B1 (en) 2000-11-24 2000-11-24 System and method for object identification and behavior characterization using video analysis
US09/718,374 2000-11-24

Publications (2)

Publication Number Publication Date
WO2002043352A2 true WO2002043352A2 (en) 2002-05-30
WO2002043352A3 WO2002043352A3 (en) 2003-01-09

Family

ID=24885865

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2001/043282 WO2002043352A2 (en) 2000-11-24 2001-11-19 System and method for object identification and behavior characterization using video analysis

Country Status (5)

Country Link
US (9) US6678413B1 (en)
EP (1) EP1337962B9 (en)
JP (1) JP2004514975A (en)
AU (1) AU2002239272A1 (en)
WO (1) WO2002043352A2 (en)

Cited By (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
ES2242484A1 (en) * 2003-01-24 2005-11-01 Pedro Monagas Asensio Mood analysing device for mammals
WO2007019140A2 (en) * 2005-08-03 2007-02-15 Honeywell International Inc. Boolean complement methods and systems for video image processing a region of interest
WO2007064559A1 (en) * 2005-11-28 2007-06-07 Honeywell International Inc. Detection of abnormal crowd behavior
US7269516B2 (en) 2001-05-15 2007-09-11 Psychogenics, Inc. Systems and methods for monitoring behavior informatics
WO2007110555A1 (en) * 2006-03-28 2007-10-04 The University Court Of The University Of Edinburgh A method for automatically characterizing the behavior of one or more objects
WO2009045578A2 (en) * 2007-06-18 2009-04-09 The Boeing Company Object detection incorporating background clutter removal
US7643655B2 (en) 2000-11-24 2010-01-05 Clever Sys, Inc. System and method for animal seizure detection and classification using video analysis
WO2010032247A2 (en) * 2008-09-17 2010-03-25 Ramot At Tel-Aviv University Ltd. System and method for analyzing exploratory behavior
US7817824B2 (en) 2000-11-24 2010-10-19 Clever Sys, Inc. Unified system and method for animal behavior characterization from top view using video analysis
JP2011081823A (en) * 2002-06-28 2011-04-21 Koninkl Philips Electronics Nv Method and apparatus for modeling behavior using probability distribution function
CN102970519A (en) * 2012-11-29 2013-03-13 河海大学常州校区 Non-rigid target behavior observation device and method based on visual perception network
EP2609858A1 (en) * 2011-12-28 2013-07-03 Samsung Electronics Co., Ltd Method for measuring quantity of exercise and display apparatus thereof
EP2521070A3 (en) * 2011-05-06 2013-12-25 Deutsche Telekom AG Method and system for recording a static or dynamic scene, for determining raw events and detecting free areas in an area under observation
US8634635B2 (en) 2008-10-30 2014-01-21 Clever Sys, Inc. System and method for stereo-view multiple animal behavior characterization
US9565398B2 (en) 2001-06-11 2017-02-07 Arrowsight, Inc. Caching graphical interface for displaying video and ancillary data from a saved video
WO2019032306A1 (en) 2017-08-07 2019-02-14 Standard Cognition, Corp. Predicting inventory events using semantic diffing
US10410371B2 (en) 2017-12-21 2019-09-10 The Boeing Company Cluttered background removal from imagery for object detection
US11023850B2 (en) 2017-08-07 2021-06-01 Standard Cognition, Corp. Realtime inventory location management using deep learning
US20210315186A1 (en) * 2020-04-14 2021-10-14 The United States Of America, As Represented By Secretary Of Agriculture Intelligent dual sensory species-specific recognition trigger system
US11195146B2 (en) 2017-08-07 2021-12-07 Standard Cognition, Corp. Systems and methods for deep learning-based shopper tracking
US11200692B2 (en) 2017-08-07 2021-12-14 Standard Cognition, Corp Systems and methods to check-in shoppers in a cashier-less store
US11232687B2 (en) 2017-08-07 2022-01-25 Standard Cognition, Corp Deep learning-based shopper statuses in a cashier-less store
US11232575B2 (en) 2019-04-18 2022-01-25 Standard Cognition, Corp Systems and methods for deep learning-based subject persistence
US11250376B2 (en) 2017-08-07 2022-02-15 Standard Cognition, Corp Product correlation analysis using deep learning
CN114241521A (en) * 2021-12-13 2022-03-25 北京华夏电通科技股份有限公司 Method, device and equipment for identifying court trial video picture normal area
US11295270B2 (en) 2017-08-07 2022-04-05 Standard Cognition, Corp. Deep learning-based store realograms
US11303853B2 (en) 2020-06-26 2022-04-12 Standard Cognition, Corp. Systems and methods for automated design of camera placement and cameras arrangements for autonomous checkout
US11361468B2 (en) 2020-06-26 2022-06-14 Standard Cognition, Corp. Systems and methods for automated recalibration of sensors for autonomous checkout
US11538186B2 (en) 2017-08-07 2022-12-27 Standard Cognition, Corp. Systems and methods to check-in shoppers in a cashier-less store
US11544866B2 (en) 2017-08-07 2023-01-03 Standard Cognition, Corp Directional impression analysis using deep learning
US11551079B2 (en) 2017-03-01 2023-01-10 Standard Cognition, Corp. Generating labeled training images for use in training a computational neural network for object or action recognition
US11790682B2 (en) 2017-03-10 2023-10-17 Standard Cognition, Corp. Image analysis using neural networks for pose and action identification
EP4046066A4 (en) * 2019-11-07 2023-11-15 Google LLC Monitoring animal pose dynamics from monocular images

Families Citing this family (547)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7076102B2 (en) * 2001-09-27 2006-07-11 Koninklijke Philips Electronics N.V. Video monitoring system employing hierarchical hidden markov model (HMM) event learning and classification
US7484172B2 (en) * 1997-05-23 2009-01-27 Walker Digital, Llc System and method for providing a customized index with hyper-footnotes
GB2352076B (en) * 1999-07-15 2003-12-17 Mitsubishi Electric Inf Tech Method and apparatus for representing and searching for an object in an image
US20050146605A1 (en) * 2000-10-24 2005-07-07 Lipton Alan J. Video surveillance system employing video primitives
GB2371936A (en) * 2001-02-03 2002-08-07 Hewlett Packard Co Surveillance system for tracking a moving object
US6778705B2 (en) * 2001-02-27 2004-08-17 Koninklijke Philips Electronics N.V. Classification of objects through model ensembles
JP3926572B2 (en) * 2001-03-02 2007-06-06 株式会社日立製作所 Image monitoring method, image monitoring apparatus, and storage medium
US20090231436A1 (en) * 2001-04-19 2009-09-17 Faltesek Anthony E Method and apparatus for tracking with identification
US6810086B1 (en) 2001-06-05 2004-10-26 At&T Corp. System and method of filtering noise
US6909745B1 (en) 2001-06-05 2005-06-21 At&T Corp. Content adaptive video encoder
US6970513B1 (en) 2001-06-05 2005-11-29 At&T Corp. System for content adaptive video decoding
US6968006B1 (en) 2001-06-05 2005-11-22 At&T Corp. Method of content adaptive video decoding
US7773670B1 (en) 2001-06-05 2010-08-10 At+T Intellectual Property Ii, L.P. Method of content adaptive video encoding
JP4596221B2 (en) * 2001-06-26 2010-12-08 ソニー株式会社 Image processing apparatus and method, recording medium, and program
US20030004913A1 (en) * 2001-07-02 2003-01-02 Koninklijke Philips Electronics N.V. Vision-based method and apparatus for detecting an event requiring assistance or documentation
JP2003087771A (en) * 2001-09-07 2003-03-20 Oki Electric Ind Co Ltd Monitoring system and monitoring method
US20030058111A1 (en) * 2001-09-27 2003-03-27 Koninklijke Philips Electronics N.V. Computer vision based elderly care monitoring system
US7043075B2 (en) * 2001-09-27 2006-05-09 Koninklijke Philips Electronics N.V. Computer vision system and method employing hierarchical object classification scheme
US7369680B2 (en) * 2001-09-27 2008-05-06 Koninklijke Phhilips Electronics N.V. Method and apparatus for detecting an event based on patterns of behavior
US7110569B2 (en) * 2001-09-27 2006-09-19 Koninklijke Philips Electronics N.V. Video based detection of fall-down and other events
US7432940B2 (en) * 2001-10-12 2008-10-07 Canon Kabushiki Kaisha Interactive animation of sprites in a video production
JP2003125401A (en) * 2001-10-17 2003-04-25 Mitsubishi Electric Corp Video data reproducing method
US6944421B2 (en) * 2001-11-15 2005-09-13 T.F.H. Publications, Inc. Method and apparatus for providing training information regarding a pet
US20030105880A1 (en) * 2001-12-04 2003-06-05 Koninklijke Philips Electronics N.V. Distributed processing, storage, and transmision of multimedia information
US20030115215A1 (en) * 2001-12-18 2003-06-19 Daniel Swarovski Method and system for watching and tracking birds
US7552030B2 (en) * 2002-01-22 2009-06-23 Honeywell International Inc. System and method for learning patterns of behavior and operating a monitoring and response system based thereon
US7683929B2 (en) * 2002-02-06 2010-03-23 Nice Systems, Ltd. System and method for video content analysis-based detection, surveillance and alarm management
JP2004021495A (en) * 2002-06-14 2004-01-22 Mitsubishi Electric Corp Monitoring system and monitoring method
ES2241509T1 (en) * 2002-07-15 2005-11-01 Baylor College Of Medicine USER INTERFACE FOR COMPUTER THAT FACILITATES THE ACQUISITION AND ANALYSIS OF BIOLOGICAL FEATURES OF SPECIMENS.
US7773112B2 (en) * 2002-08-20 2010-08-10 Tektronix, Inc. Automatic measurement of video parameters
US7200266B2 (en) * 2002-08-27 2007-04-03 Princeton University Method and apparatus for automated video activity analysis
JP2004096557A (en) * 2002-09-02 2004-03-25 Canon Inc Image processor and image processing method
ATE285590T1 (en) * 2002-10-25 2005-01-15 Evotec Technologies Gmbh METHOD AND APPARATUS FOR CAPTURING THREE-DIMENSIONAL IMAGERY OF FLOATED MICROOBJECTS USING HIGH-RESOLUTION MICROSCOPY
US7375731B2 (en) * 2002-11-01 2008-05-20 Mitsubishi Electric Research Laboratories, Inc. Video mining using unsupervised clustering of video content
US20050134685A1 (en) * 2003-12-22 2005-06-23 Objectvideo, Inc. Master-slave automated video-based surveillance system
US7956889B2 (en) * 2003-06-04 2011-06-07 Model Software Corporation Video surveillance system
US7606417B2 (en) 2004-08-16 2009-10-20 Fotonation Vision Limited Foreground/background segmentation in digital images with differential exposure calculations
US7680342B2 (en) * 2004-08-16 2010-03-16 Fotonation Vision Limited Indoor/outdoor classification in digital images
US7590643B2 (en) * 2003-08-21 2009-09-15 Microsoft Corporation Systems and methods for extensions and inheritance for units of information manageable by a hardware/software interface system
US7106502B1 (en) * 2003-08-21 2006-09-12 The United States Of America As Represented By The Administrator Of National Aeronautics And Space Administration Operation of a Cartesian robotic system in a compact microscope imaging system with intelligent controls
US8238696B2 (en) * 2003-08-21 2012-08-07 Microsoft Corporation Systems and methods for the implementation of a digital images schema for organizing units of information manageable by a hardware/software interface system
US8166101B2 (en) 2003-08-21 2012-04-24 Microsoft Corporation Systems and methods for the implementation of a synchronization schemas for units of information manageable by a hardware/software interface system
US7835572B2 (en) * 2003-09-30 2010-11-16 Sharp Laboratories Of America, Inc. Red eye reduction technique
US7280673B2 (en) * 2003-10-10 2007-10-09 Intellivid Corporation System and method for searching for changes in surveillance video
US7333633B2 (en) * 2003-10-31 2008-02-19 Plexon, Inc. Inter-frame video techniques for behavioral analysis of laboratory animals
US20050104958A1 (en) * 2003-11-13 2005-05-19 Geoffrey Egnal Active camera video-based surveillance systems and methods
KR100601933B1 (en) * 2003-11-18 2006-07-14 삼성전자주식회사 Method and apparatus of human detection and privacy protection method and system employing the same
US7664292B2 (en) * 2003-12-03 2010-02-16 Safehouse International, Inc. Monitoring an output from a camera
US20050163345A1 (en) * 2003-12-03 2005-07-28 Safehouse International Limited Analysing image data
US8675059B2 (en) 2010-07-29 2014-03-18 Careview Communications, Inc. System and method for using a video monitoring system to prevent and manage decubitus ulcers in patients
US9311540B2 (en) 2003-12-12 2016-04-12 Careview Communications, Inc. System and method for predicting patient falls
US7447333B1 (en) * 2004-01-22 2008-11-04 Siemens Corporate Research, Inc. Video and audio monitoring for syndromic surveillance for infectious diseases
JP4479267B2 (en) * 2004-02-18 2010-06-09 株式会社日立製作所 Surveillance camera video distribution system
US7486815B2 (en) * 2004-02-20 2009-02-03 Microsoft Corporation Method and apparatus for scene learning and three-dimensional tracking using stereo video cameras
US7831094B2 (en) * 2004-04-27 2010-11-09 Honda Motor Co., Ltd. Simultaneous localization and mapping using multiple view feature descriptors
US7263472B2 (en) * 2004-06-28 2007-08-28 Mitsubishi Electric Research Laboratories, Inc. Hidden markov model based object tracking and similarity metrics
US20060007307A1 (en) * 2004-07-12 2006-01-12 Chao-Hung Chang Partial image saving system and method
US7562299B2 (en) * 2004-08-13 2009-07-14 Pelco, Inc. Method and apparatus for searching recorded video
JP4433948B2 (en) * 2004-09-02 2010-03-17 株式会社セガ Background image acquisition program, video game apparatus, background image acquisition method, and computer-readable recording medium recording the program
US20080166015A1 (en) * 2004-09-24 2008-07-10 Object Video, Inc. Method for finding paths in video
US7469060B2 (en) * 2004-11-12 2008-12-23 Honeywell International Inc. Infrared face detection and recognition system
US7602942B2 (en) * 2004-11-12 2009-10-13 Honeywell International Inc. Infrared and visible fusion face recognition system
RU2323475C2 (en) * 2004-11-12 2008-04-27 Общество с ограниченной ответственностью "Центр Нейросетевых Технологий - Интеллектуальные Системы Безопасности" (ООО "ИСС") Method (variants) and device (variants) for automated detection of intentional or incidental disruptions of technological procedure by operator
US20060245500A1 (en) * 2004-12-15 2006-11-02 David Yonovitz Tunable wavelet target extraction preprocessor system
EP1834486A1 (en) * 2004-12-24 2007-09-19 Ultrawaves design holding B. V. Intelligent distributed image processing
US20060187230A1 (en) * 2005-01-31 2006-08-24 Searete Llc Peripheral shared image device sharing
US20060221197A1 (en) * 2005-03-30 2006-10-05 Jung Edward K Image transformation estimator of an imaging device
US20060187227A1 (en) * 2005-01-31 2006-08-24 Jung Edward K Storage aspects for imaging device
US8902320B2 (en) * 2005-01-31 2014-12-02 The Invention Science Fund I, Llc Shared image device synchronization or designation
US20060173972A1 (en) * 2005-01-31 2006-08-03 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Audio sharing
US20060285150A1 (en) * 2005-01-31 2006-12-21 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Regional proximity for shared image device(s)
US20060174203A1 (en) * 2005-01-31 2006-08-03 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Viewfinder for shared image device
US9082456B2 (en) 2005-01-31 2015-07-14 The Invention Science Fund I Llc Shared image device designation
US20060171603A1 (en) * 2005-01-31 2006-08-03 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Resampling of transformed shared image techniques
US20060170956A1 (en) * 2005-01-31 2006-08-03 Jung Edward K Shared image devices
US7920169B2 (en) * 2005-01-31 2011-04-05 Invention Science Fund I, Llc Proximity of shared image devices
US20070236505A1 (en) * 2005-01-31 2007-10-11 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Resampling of transformed shared image techniques
US8606383B2 (en) 2005-01-31 2013-12-10 The Invention Science Fund I, Llc Audio sharing
US9124729B2 (en) * 2005-01-31 2015-09-01 The Invention Science Fund I, Llc Shared image device synchronization or designation
US20060187228A1 (en) * 2005-01-31 2006-08-24 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Sharing including peripheral shared image device
US9489717B2 (en) 2005-01-31 2016-11-08 Invention Science Fund I, Llc Shared image device
US9325781B2 (en) 2005-01-31 2016-04-26 Invention Science Fund I, Llc Audio sharing
US7876357B2 (en) * 2005-01-31 2011-01-25 The Invention Science Fund I, Llc Estimating shared image device operational capabilities or resources
US9910341B2 (en) * 2005-01-31 2018-03-06 The Invention Science Fund I, Llc Shared image device designation
US7903141B1 (en) * 2005-02-15 2011-03-08 Videomining Corporation Method and system for event detection by multi-scale image invariant analysis
US7710452B1 (en) 2005-03-16 2010-05-04 Eric Lindberg Remote video monitoring of non-urban outdoor sites
US7286056B2 (en) * 2005-03-22 2007-10-23 Lawrence Kates System and method for pest detection
US8139896B1 (en) * 2005-03-28 2012-03-20 Grandeye, Ltd. Tracking moving objects accurately on a wide-angle video
US7760908B2 (en) * 2005-03-31 2010-07-20 Honeywell International Inc. Event packaged video sequence
US7801328B2 (en) * 2005-03-31 2010-09-21 Honeywell International Inc. Methods for defining, detecting, analyzing, indexing and retrieving events using video image processing
US8704668B1 (en) * 2005-04-20 2014-04-22 Trevor Darrell System for monitoring and alerting based on animal behavior in designated environments
US8233042B2 (en) * 2005-10-31 2012-07-31 The Invention Science Fund I, Llc Preservation and/or degradation of a video/audio data stream
US20070222865A1 (en) * 2006-03-15 2007-09-27 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Enhanced video/still image correlation
US9967424B2 (en) * 2005-06-02 2018-05-08 Invention Science Fund I, Llc Data storage usage protocol
US9191611B2 (en) * 2005-06-02 2015-11-17 Invention Science Fund I, Llc Conditional alteration of a saved image
US20090144391A1 (en) * 2007-11-30 2009-06-04 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Audio sharing
US8964054B2 (en) * 2006-08-18 2015-02-24 The Invention Science Fund I, Llc Capturing selected image objects
US7872675B2 (en) * 2005-06-02 2011-01-18 The Invention Science Fund I, Llc Saved-image management
US9621749B2 (en) * 2005-06-02 2017-04-11 Invention Science Fund I, Llc Capturing selected image objects
US20070008326A1 (en) * 2005-06-02 2007-01-11 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Dual mode image capture technique
US9942511B2 (en) 2005-10-31 2018-04-10 Invention Science Fund I, Llc Preservation/degradation of video/audio aspects of a data stream
US8681225B2 (en) * 2005-06-02 2014-03-25 Royce A. Levien Storage access technique for captured data
US9819490B2 (en) * 2005-05-04 2017-11-14 Invention Science Fund I, Llc Regional proximity for shared image device(s)
US8072501B2 (en) * 2005-10-31 2011-12-06 The Invention Science Fund I, Llc Preservation and/or degradation of a video/audio data stream
US9001215B2 (en) * 2005-06-02 2015-04-07 The Invention Science Fund I, Llc Estimating shared image device operational capabilities or resources
US9451200B2 (en) * 2005-06-02 2016-09-20 Invention Science Fund I, Llc Storage access technique for captured data
US9167195B2 (en) * 2005-10-31 2015-10-20 Invention Science Fund I, Llc Preservation/degradation of video/audio aspects of a data stream
US9076208B2 (en) * 2006-02-28 2015-07-07 The Invention Science Fund I, Llc Imagery processing
US9093121B2 (en) 2006-02-28 2015-07-28 The Invention Science Fund I, Llc Data management of an audio data stream
US20070109411A1 (en) * 2005-06-02 2007-05-17 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Composite image selectivity
US8253821B2 (en) * 2005-10-31 2012-08-28 The Invention Science Fund I, Llc Degradation/preservation management of captured data
US7782365B2 (en) * 2005-06-02 2010-08-24 Searete Llc Enhanced video/still image correlation
US20070139529A1 (en) * 2005-06-02 2007-06-21 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Dual mode image capture technique
US20070098348A1 (en) * 2005-10-31 2007-05-03 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Degradation/preservation management of captured data
US10003762B2 (en) 2005-04-26 2018-06-19 Invention Science Fund I, Llc Shared image devices
US20060260624A1 (en) * 2005-05-17 2006-11-23 Battelle Memorial Institute Method, program, and system for automatic profiling of entities
US20060274153A1 (en) * 2005-06-02 2006-12-07 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Third party storage of captured data
US7720257B2 (en) * 2005-06-16 2010-05-18 Honeywell International Inc. Object tracking system
US20060291697A1 (en) * 2005-06-21 2006-12-28 Trw Automotive U.S. Llc Method and apparatus for detecting the presence of an occupant within a vehicle
US7944468B2 (en) * 2005-07-05 2011-05-17 Northrop Grumman Systems Corporation Automated asymmetric threat detection using backward tracking and behavioral analysis
CN101228555A (en) * 2005-07-07 2008-07-23 独创目标实验室公司 System for 3D monitoring and analysis of motion behavior of targets
US7545954B2 (en) * 2005-08-22 2009-06-09 General Electric Company System for recognizing events
US20070047834A1 (en) * 2005-08-31 2007-03-01 International Business Machines Corporation Method and apparatus for visual background subtraction with one or more preprocessing modules
US20070058717A1 (en) * 2005-09-09 2007-03-15 Objectvideo, Inc. Enhanced processing for scanning video
US20070071404A1 (en) * 2005-09-29 2007-03-29 Honeywell International Inc. Controlled video event presentation
US7382280B2 (en) * 2005-10-17 2008-06-03 Cleverdevices, Inc. Parking violation recording system and method
US7806604B2 (en) * 2005-10-20 2010-10-05 Honeywell International Inc. Face detection and tracking in a wide field of view
US20070120980A1 (en) 2005-10-31 2007-05-31 Searete Llc, A Limited Liability Corporation Of The State Of Delaware Preservation/degradation of video/audio aspects of a data stream
US20070203595A1 (en) * 2006-02-28 2007-08-30 Searete Llc, A Limited Liability Corporation Data management of an audio data stream
US8228382B2 (en) * 2005-11-05 2012-07-24 Ram Pattikonda System and method for counting people
US20100310120A1 (en) * 2005-11-05 2010-12-09 Charlie Keith Method and system for tracking moving objects in a scene
US7692696B2 (en) * 2005-12-27 2010-04-06 Fotonation Vision Limited Digital image acquisition system with portrait mode
US8265392B2 (en) * 2006-02-07 2012-09-11 Qualcomm Incorporated Inter-mode region-of-interest video object segmentation
US7822227B2 (en) * 2006-02-07 2010-10-26 International Business Machines Corporation Method and system for tracking images
US8265349B2 (en) * 2006-02-07 2012-09-11 Qualcomm Incorporated Intra-mode region-of-interest video object segmentation
US7986827B2 (en) * 2006-02-07 2011-07-26 Siemens Medical Solutions Usa, Inc. System and method for multiple instance learning for computer aided detection
US8150155B2 (en) 2006-02-07 2012-04-03 Qualcomm Incorporated Multi-mode region-of-interest video object segmentation
WO2007095477A2 (en) * 2006-02-14 2007-08-23 Fotonation Vision Limited Image blurring
IES20060559A2 (en) * 2006-02-14 2006-11-01 Fotonation Vision Ltd Automatic detection and correction of non-red flash eye defects
JP4607797B2 (en) * 2006-03-06 2011-01-05 株式会社東芝 Behavior discrimination device, method and program
JP4589261B2 (en) * 2006-03-31 2010-12-01 パナソニック株式会社 Surveillance camera device
IES20060564A2 (en) * 2006-05-03 2006-11-01 Fotonation Vision Ltd Improved foreground / background separation
US8121361B2 (en) 2006-05-19 2012-02-21 The Queen's Medical Center Motion tracking system for real time adaptive imaging and spectroscopy
AU2006345533B2 (en) * 2006-05-31 2013-01-24 Thomson Licensing Multi-tracking of video objects
US7983448B1 (en) * 2006-06-02 2011-07-19 University Of Central Florida Research Foundation, Inc. Self correcting tracking of moving objects in video
US20080123959A1 (en) * 2006-06-26 2008-05-29 Ratner Edward R Computer-implemented method for automated object recognition and classification in scenes using segment-based object extraction
KR100716708B1 (en) * 2006-07-11 2007-05-09 영남대학교 산학협력단 Automatic velocity control running machine using pressure sensor array and fuzzy-logic
US7930204B1 (en) 2006-07-25 2011-04-19 Videomining Corporation Method and system for narrowcasting based on automatic analysis of customer behavior in a retail store
US7974869B1 (en) 2006-09-20 2011-07-05 Videomining Corporation Method and system for automatically measuring and forecasting the behavioral characterization of customers to help customize programming contents in a media network
US20080112593A1 (en) * 2006-11-03 2008-05-15 Ratner Edward R Automated method and apparatus for robust image object recognition and/or classification using multiple temporal views
US7734623B2 (en) * 2006-11-07 2010-06-08 Cycorp, Inc. Semantics-based method and apparatus for document analysis
JP5479907B2 (en) * 2006-11-20 2014-04-23 アデレード リサーチ アンド イノヴェーション ピーティーワイ エルティーディー Network monitoring system
US8165405B2 (en) * 2006-12-18 2012-04-24 Honda Motor Co., Ltd. Leveraging temporal, contextual and ordering constraints for recognizing complex activities in video
US8189926B2 (en) * 2006-12-30 2012-05-29 Videomining Corporation Method and system for automatically analyzing categories in a physical space based on the visual characterization of people
US8269834B2 (en) 2007-01-12 2012-09-18 International Business Machines Corporation Warning a user about adverse behaviors of others within an environment based on a 3D captured image stream
US8665333B1 (en) * 2007-01-30 2014-03-04 Videomining Corporation Method and system for optimizing the observation and annotation of complex human behavior from video sources
US20080184245A1 (en) * 2007-01-30 2008-07-31 March Networks Corporation Method and system for task-based video analytics processing
EP2119235A4 (en) * 2007-02-02 2011-12-21 Honeywell Int Inc Systems and methods for managing live video data
PL2118864T3 (en) 2007-02-08 2015-03-31 Behavioral Recognition Sys Inc Behavioral recognition system
NZ553146A (en) * 2007-02-09 2011-05-27 Say Systems Ltd Improvements relating to monitoring and displaying activities
US7667596B2 (en) * 2007-02-16 2010-02-23 Panasonic Corporation Method and system for scoring surveillance system footage
US8456528B2 (en) * 2007-03-20 2013-06-04 International Business Machines Corporation System and method for managing the interaction of object detection and tracking systems in video surveillance
US7957565B1 (en) * 2007-04-05 2011-06-07 Videomining Corporation Method and system for recognizing employees in a physical space based on automatic behavior analysis
EP3594853A3 (en) * 2007-05-03 2020-04-08 Sony Deutschland GmbH Method for detecting moving objects in a blind spot region of a vehicle and blind spot detection device
US8103109B2 (en) * 2007-06-19 2012-01-24 Microsoft Corporation Recognizing hand poses and/or object classes
WO2009006605A2 (en) * 2007-07-03 2009-01-08 Pivotal Vision, Llc Motion-validating remote monitoring system
US8411935B2 (en) 2007-07-11 2013-04-02 Behavioral Recognition Systems, Inc. Semantic representation module of a machine-learning engine in a video analysis system
US8005262B2 (en) * 2007-07-16 2011-08-23 Hugh Griffin System and method for video object identification
KR101375665B1 (en) * 2007-08-08 2014-03-18 삼성전자주식회사 Method and apparatus for estimating a background change, and method and apparatus for detecting a motion
US20090062002A1 (en) * 2007-08-30 2009-03-05 Bay Tek Games, Inc. Apparatus And Method of Detecting And Tracking Objects In Amusement Games
US9135491B2 (en) 2007-08-31 2015-09-15 Accenture Global Services Limited Digital point-of-sale analyzer
US7949568B2 (en) * 2007-08-31 2011-05-24 Accenture Global Services Limited Determination of product display parameters based on image processing
US8189855B2 (en) 2007-08-31 2012-05-29 Accenture Global Services Limited Planogram extraction based on image processing
US8009864B2 (en) 2007-08-31 2011-08-30 Accenture Global Services Limited Determination of inventory conditions based on image processing
US8630924B2 (en) * 2007-08-31 2014-01-14 Accenture Global Services Limited Detection of stock out conditions based on image processing
JP2011510521A (en) * 2007-09-12 2011-03-31 ディジセンサリー・テクノロジーズ・プロプライアタリー・リミテッド On-chip smart network camera system
US8300924B2 (en) * 2007-09-27 2012-10-30 Behavioral Recognition Systems, Inc. Tracker component for behavioral recognition system
US8200011B2 (en) * 2007-09-27 2012-06-12 Behavioral Recognition Systems, Inc. Context processor for video analysis system
US8175333B2 (en) * 2007-09-27 2012-05-08 Behavioral Recognition Systems, Inc. Estimator identifier component for behavioral recognition system
US8218811B2 (en) 2007-09-28 2012-07-10 Uti Limited Partnership Method and system for video interaction based on motion swarms
CN101420595B (en) * 2007-10-23 2012-11-21 华为技术有限公司 Method and equipment for describing and capturing video object
JP5055092B2 (en) * 2007-11-02 2012-10-24 株式会社日立国際電気 Video processing apparatus and video processing method
US9171454B2 (en) * 2007-11-14 2015-10-27 Microsoft Technology Licensing, Llc Magic wand
US20090137933A1 (en) * 2007-11-28 2009-05-28 Ishoe Methods and systems for sensing equilibrium
KR100936115B1 (en) * 2007-12-20 2010-01-11 김세호 Mouse Activity Measuring Instrument
US8337404B2 (en) 2010-10-01 2012-12-25 Flint Hills Scientific, Llc Detecting, quantifying, and/or classifying seizures using multimodal data
US8571643B2 (en) 2010-09-16 2013-10-29 Flint Hills Scientific, Llc Detecting or validating a detection of a state change from a template of heart rate derivative shape or heart beat wave complex
US8382667B2 (en) 2010-10-01 2013-02-26 Flint Hills Scientific, Llc Detecting, quantifying, and/or classifying seizures using multimodal data
US8098888B1 (en) * 2008-01-28 2012-01-17 Videomining Corporation Method and system for automatic analysis of the trip of people in a retail space using multiple cameras
US20090195382A1 (en) * 2008-01-31 2009-08-06 Sensormatic Electronics Corporation Video sensor and alarm system and method with object and event classification
AU2008200926B2 (en) * 2008-02-28 2011-09-29 Canon Kabushiki Kaisha On-camera summarisation of object relationships
US8284249B2 (en) 2008-03-25 2012-10-09 International Business Machines Corporation Real time processing of video frames for triggering an alert
JP5213237B2 (en) * 2008-04-17 2013-06-19 パナソニック株式会社 Imaging position determination method and imaging position determination apparatus
US9866797B2 (en) 2012-09-28 2018-01-09 Careview Communications, Inc. System and method for monitoring a fall state of a patient while minimizing false alarms
US9579047B2 (en) 2013-03-15 2017-02-28 Careview Communications, Inc. Systems and methods for dynamically identifying a patient support surface and patient monitoring
US10645346B2 (en) 2013-01-18 2020-05-05 Careview Communications, Inc. Patient video monitoring systems and methods having detection algorithm recovery from changes in illumination
US9959471B2 (en) 2008-05-06 2018-05-01 Careview Communications, Inc. Patient video monitoring systems and methods for thermal detection of liquids
US9794523B2 (en) 2011-12-19 2017-10-17 Careview Communications, Inc. Electronic patient sitter management system and method for implementing
US8952894B2 (en) * 2008-05-12 2015-02-10 Microsoft Technology Licensing, Llc Computer vision-based multi-touch sensing using infrared lasers
US8009863B1 (en) 2008-06-30 2011-08-30 Videomining Corporation Method and system for analyzing shopping behavior using multiple sensor tracking
EP2230629A3 (en) 2008-07-16 2012-11-21 Verint Systems Inc. A system and method for capturing, storing, analyzing and displaying data relating to the movements of objects
US8396247B2 (en) * 2008-07-31 2013-03-12 Microsoft Corporation Recognizing actions of animate objects in video
US20100031202A1 (en) * 2008-08-04 2010-02-04 Microsoft Corporation User-defined gesture set for surface computing
US8847739B2 (en) 2008-08-04 2014-09-30 Microsoft Corporation Fusing RFID and vision for surface object tracking
US7710830B2 (en) * 2008-09-02 2010-05-04 Accuwalk Llc Outing record device
US8121968B2 (en) * 2008-09-11 2012-02-21 Behavioral Recognition Systems, Inc. Long-term memory in a video analysis system
US8126833B2 (en) * 2008-09-11 2012-02-28 Behavioral Recognition Systems, Inc. Detecting anomalous events using a long-term memory in a video analysis system
US9633275B2 (en) 2008-09-11 2017-04-25 Wesley Kenneth Cobb Pixel-level based micro-feature extraction
JPWO2010035752A1 (en) * 2008-09-24 2012-02-23 株式会社ニコン Image generation apparatus, imaging apparatus, image reproduction apparatus, and image reproduction program
US9141862B2 (en) * 2008-09-26 2015-09-22 Harris Corporation Unattended surveillance device and associated methods
US8694443B2 (en) 2008-11-03 2014-04-08 International Business Machines Corporation System and method for automatically distinguishing between customers and in-store employees
DE102008058020A1 (en) * 2008-11-19 2010-05-20 Zebris Medical Gmbh Arrangement for training the gear
US8471899B2 (en) 2008-12-02 2013-06-25 Careview Communications, Inc. System and method for documenting patient procedures
US9373055B2 (en) * 2008-12-16 2016-06-21 Behavioral Recognition Systems, Inc. Hierarchical sudden illumination change detection using radiance consistency within a spatial neighborhood
US20100157051A1 (en) * 2008-12-23 2010-06-24 International Business Machines Corporation System and method for detecting and deterring rfid tag related fraud
US8218877B2 (en) * 2008-12-23 2012-07-10 National Chiao Tung University Tracking vehicle method by using image processing
EP2380143A4 (en) * 2008-12-24 2012-06-13 Vehicle Monitoring Systems Pty Ltd Method and system for detecting vehicle offences
US20100169169A1 (en) * 2008-12-31 2010-07-01 International Business Machines Corporation System and method for using transaction statistics to facilitate checkout variance investigation
US20100182445A1 (en) * 2009-01-22 2010-07-22 Upi Semiconductor Corporation Processing Device, Method, And Electronic System Utilizing The Same
US8295546B2 (en) * 2009-01-30 2012-10-23 Microsoft Corporation Pose tracking pipeline
US8285046B2 (en) * 2009-02-18 2012-10-09 Behavioral Recognition Systems, Inc. Adaptive update of background pixel thresholds using sudden illumination change detection
WO2010099575A1 (en) 2009-03-04 2010-09-10 Honeywell International Inc. Systems and methods for managing video data
US20100293194A1 (en) * 2009-03-11 2010-11-18 Andersen Timothy L Discrimination between multi-dimensional models using difference distributions
US8416296B2 (en) * 2009-04-14 2013-04-09 Behavioral Recognition Systems, Inc. Mapper component for multiple art networks in a video analysis system
WO2010122174A1 (en) * 2009-04-24 2010-10-28 Commissariat A L'energie Atomique Et Aux Energies Alternatives System and method for determining the posture of a person
US9047742B2 (en) * 2009-05-07 2015-06-02 International Business Machines Corporation Visual security for point of sale terminals
US8608481B2 (en) * 2009-05-13 2013-12-17 Medtronic Navigation, Inc. Method and apparatus for identifying an instrument location based on measuring a characteristic
US9417700B2 (en) 2009-05-21 2016-08-16 Edge3 Technologies Gesture recognition systems and related methods
US20100299140A1 (en) * 2009-05-22 2010-11-25 Cycorp, Inc. Identifying and routing of documents of potential interest to subscribers using interest determination rules
US8320619B2 (en) * 2009-05-29 2012-11-27 Microsoft Corporation Systems and methods for tracking a model
US9740977B1 (en) * 2009-05-29 2017-08-22 Videomining Corporation Method and system for recognizing the intentions of shoppers in retail aisles based on their trajectories
US8649594B1 (en) 2009-06-04 2014-02-11 Agilence, Inc. Active and adaptive intelligent video surveillance system
US20100315506A1 (en) * 2009-06-10 2010-12-16 Microsoft Corporation Action detection in video through sub-volume mutual information maximization
US8571259B2 (en) * 2009-06-17 2013-10-29 Robert Allan Margolis System and method for automatic identification of wildlife
US8462987B2 (en) * 2009-06-23 2013-06-11 Ut-Battelle, Llc Detecting multiple moving objects in crowded environments with coherent motion regions
US11004093B1 (en) 2009-06-29 2021-05-11 Videomining Corporation Method and system for detecting shopping groups based on trajectory dynamics
US20100332140A1 (en) * 2009-06-30 2010-12-30 Jonathan Livingston Joyce Method of assessing the eating experience of a companion animal
TWI386239B (en) * 2009-07-24 2013-02-21 Univ Far East Animal experiment gait recording method
JP5350928B2 (en) * 2009-07-30 2013-11-27 オリンパスイメージング株式会社 Camera and camera control method
US8625884B2 (en) * 2009-08-18 2014-01-07 Behavioral Recognition Systems, Inc. Visualizing and updating learned event maps in surveillance systems
US8280153B2 (en) * 2009-08-18 2012-10-02 Behavioral Recognition Systems Visualizing and updating learned trajectories in video surveillance systems
US8493409B2 (en) * 2009-08-18 2013-07-23 Behavioral Recognition Systems, Inc. Visualizing and updating sequences and segments in a video surveillance system
US8340352B2 (en) * 2009-08-18 2012-12-25 Behavioral Recognition Systems, Inc. Inter-trajectory anomaly detection using adaptive voting experts in a video surveillance system
US20110043689A1 (en) * 2009-08-18 2011-02-24 Wesley Kenneth Cobb Field-of-view change detection
US9805271B2 (en) * 2009-08-18 2017-10-31 Omni Ai, Inc. Scene preset identification using quadtree decomposition analysis
US8295591B2 (en) * 2009-08-18 2012-10-23 Behavioral Recognition Systems, Inc. Adaptive voting experts for incremental segmentation of sequences with prediction in a video surveillance system
US8358834B2 (en) * 2009-08-18 2013-01-22 Behavioral Recognition Systems Background model for complex and dynamic scenes
US8379085B2 (en) * 2009-08-18 2013-02-19 Behavioral Recognition Systems, Inc. Intra-trajectory anomaly detection using adaptive voting experts in a video surveillance system
US8797405B2 (en) * 2009-08-31 2014-08-05 Behavioral Recognition Systems, Inc. Visualizing and updating classifications in a video surveillance system
US8167430B2 (en) * 2009-08-31 2012-05-01 Behavioral Recognition Systems, Inc. Unsupervised learning of temporal anomalies for a video surveillance system
US8270733B2 (en) * 2009-08-31 2012-09-18 Behavioral Recognition Systems, Inc. Identifying anomalous object types during classification
US8270732B2 (en) * 2009-08-31 2012-09-18 Behavioral Recognition Systems, Inc. Clustering nodes in a self-organizing map using an adaptive resonance theory network
US8786702B2 (en) 2009-08-31 2014-07-22 Behavioral Recognition Systems, Inc. Visualizing and updating long-term memory percepts in a video surveillance system
US8285060B2 (en) * 2009-08-31 2012-10-09 Behavioral Recognition Systems, Inc. Detecting anomalous trajectories in a video surveillance system
US8218818B2 (en) * 2009-09-01 2012-07-10 Behavioral Recognition Systems, Inc. Foreground object tracking
US8218819B2 (en) * 2009-09-01 2012-07-10 Behavioral Recognition Systems, Inc. Foreground object detection in a video surveillance system
US8180105B2 (en) * 2009-09-17 2012-05-15 Behavioral Recognition Systems, Inc. Classifier anomalies for observed behaviors in a video surveillance system
US8170283B2 (en) * 2009-09-17 2012-05-01 Behavioral Recognition Systems Inc. Video surveillance system configured to analyze complex behaviors using alternating layers of clustering and sequencing
FR2950989B1 (en) * 2009-10-05 2011-10-28 Alcatel Lucent DEVICE FOR INTERACTING WITH AN INCREASED OBJECT.
US8320621B2 (en) * 2009-12-21 2012-11-27 Microsoft Corporation Depth projector system with integrated VCSEL array
JP2011210139A (en) * 2010-03-30 2011-10-20 Sony Corp Image processing apparatus and method, and program
US20110246123A1 (en) * 2010-03-30 2011-10-06 Welch Allyn, Inc. Personal status monitoring
US8831732B2 (en) 2010-04-29 2014-09-09 Cyberonics, Inc. Method, apparatus and system for validating and quantifying cardiac beat data quality
US8562536B2 (en) 2010-04-29 2013-10-22 Flint Hills Scientific, Llc Algorithm for detecting a seizure from cardiac data
US8649871B2 (en) 2010-04-29 2014-02-11 Cyberonics, Inc. Validity test adaptive constraint modification for cardiac data used for detection of state changes
US8396252B2 (en) 2010-05-20 2013-03-12 Edge 3 Technologies Systems and related methods for three dimensional gesture recognition in vehicles
EP2395456A1 (en) * 2010-06-12 2011-12-14 Toyota Motor Europe NV/SA Methods and systems for semantic label propagation
US8670029B2 (en) 2010-06-16 2014-03-11 Microsoft Corporation Depth camera illuminator with superluminescent light-emitting diode
US8483481B2 (en) 2010-07-27 2013-07-09 International Business Machines Corporation Foreground analysis based on tracking information
US8641646B2 (en) 2010-07-30 2014-02-04 Cyberonics, Inc. Seizure detection using coordinate data
EP2580738A4 (en) * 2010-08-10 2018-01-03 LG Electronics Inc. Region of interest based video synopsis
US8582866B2 (en) 2011-02-10 2013-11-12 Edge 3 Technologies, Inc. Method and apparatus for disparity computation in stereo images
US8467599B2 (en) 2010-09-02 2013-06-18 Edge 3 Technologies, Inc. Method and apparatus for confusion learning
US8666144B2 (en) 2010-09-02 2014-03-04 Edge 3 Technologies, Inc. Method and apparatus for determining disparity of texture
US8655093B2 (en) 2010-09-02 2014-02-18 Edge 3 Technologies, Inc. Method and apparatus for performing segmentation of an image
WO2012040554A2 (en) 2010-09-23 2012-03-29 Stryker Corporation Video monitoring system
US8684921B2 (en) 2010-10-01 2014-04-01 Flint Hills Scientific Llc Detecting, assessing and managing epilepsy using a multi-variate, metric-based classification analysis
US20120094600A1 (en) 2010-10-19 2012-04-19 Welch Allyn, Inc. Platform for patient monitoring
KR20120052739A (en) * 2010-11-16 2012-05-24 삼성전자주식회사 Display driving device and method for compressing and decompressing image data in the same
US9432639B2 (en) * 2010-11-19 2016-08-30 Honeywell International Inc. Security video detection of personal distress and gesture commands
JP5718632B2 (en) * 2010-12-22 2015-05-13 綜合警備保障株式会社 Part recognition device, part recognition method, and part recognition program
AU2010257454B2 (en) * 2010-12-24 2014-03-06 Canon Kabushiki Kaisha Summary view of video objects sharing common attributes
GB2486913A (en) * 2010-12-30 2012-07-04 Delaval Holding Ab Control and monitoring system for an animal installation
US11080513B2 (en) * 2011-01-12 2021-08-03 Gary S. Shuster Video and still image data alteration to enhance privacy
US8970589B2 (en) 2011-02-10 2015-03-03 Edge 3 Technologies, Inc. Near-touch interaction with a stereo camera grid structured tessellations
US10025388B2 (en) * 2011-02-10 2018-07-17 Continental Automotive Systems, Inc. Touchless human machine interface
US9504390B2 (en) 2011-03-04 2016-11-29 Globalfoundries Inc. Detecting, assessing and managing a risk of death in epilepsy
US9498162B2 (en) 2011-04-25 2016-11-22 Cyberonics, Inc. Identifying seizures using heart data from two or more windows
US9402550B2 (en) 2011-04-29 2016-08-02 Cybertronics, Inc. Dynamic heart rate threshold for neurological event detection
TWI454150B (en) * 2011-05-06 2014-09-21 Altek Corp Processing method for image file
US8810640B2 (en) 2011-05-16 2014-08-19 Ut-Battelle, Llc Intrinsic feature-based pose measurement for imaging motion compensation
DE102011101939A1 (en) * 2011-05-18 2012-11-22 Biobserve GmbH A method of creating a behavioral analysis of a rodent in an arena and method of creating an image of the rodent
CN102221996A (en) * 2011-05-20 2011-10-19 广州市久邦数码科技有限公司 Implementation method for performing interaction between dynamic wallpaper and desktop component
CN103608854B (en) * 2011-05-30 2016-12-28 皇家飞利浦有限公司 Equipment and method for the detection body gesture when sleep
US8526734B2 (en) 2011-06-01 2013-09-03 Microsoft Corporation Three-dimensional background removal for vision system
US9594430B2 (en) 2011-06-01 2017-03-14 Microsoft Technology Licensing, Llc Three-dimensional foreground selection for vision system
CN102831442A (en) * 2011-06-13 2012-12-19 索尼公司 Abnormal behavior detection method and equipment and method and equipment for generating abnormal behavior detection equipment
RU2455676C2 (en) * 2011-07-04 2012-07-10 Общество с ограниченной ответственностью "ТРИДИВИ" Method of controlling device using gestures and 3d sensor for realising said method
WO2013018070A1 (en) 2011-08-03 2013-02-07 Yeda Research And Development Co. Ltd. Method for automatic behavioral phenotyping
EP2747641A4 (en) 2011-08-26 2015-04-01 Kineticor Inc Methods, systems, and devices for intra-scan motion correction
KR101903407B1 (en) * 2011-09-08 2018-10-02 엘지전자 주식회사 Health care system based on video in remote health care solution and method for providing health care service
TWI590193B (en) * 2011-09-29 2017-07-01 國立清華大學 Image method for classifying insects and insect classifying process
US9124783B2 (en) 2011-09-30 2015-09-01 Camiolog, Inc. Method and system for automated labeling at scale of motion-detected events in video surveillance
US9549677B2 (en) 2011-10-14 2017-01-24 Flint Hills Scientific, L.L.C. Seizure detection methods, apparatus, and systems using a wavelet transform maximum modulus algorithm
US8442265B1 (en) * 2011-10-19 2013-05-14 Facebook Inc. Image selection from captured video sequence based on social components
US8437500B1 (en) * 2011-10-19 2013-05-07 Facebook Inc. Preferred images from captured video sequence
US9177208B2 (en) * 2011-11-04 2015-11-03 Google Inc. Determining feature vectors for video volumes
US9672609B1 (en) 2011-11-11 2017-06-06 Edge 3 Technologies, Inc. Method and apparatus for improved depth-map estimation
US20130273969A1 (en) * 2011-12-01 2013-10-17 Finding Rover, Inc. Mobile app that generates a dog sound to capture data for a lost pet identifying system
US9342735B2 (en) * 2011-12-01 2016-05-17 Finding Rover, Inc. Facial recognition lost pet identifying system
JP5868426B2 (en) * 2011-12-13 2016-02-24 株式会社日立製作所 How to estimate the orientation of a stationary person
US20150030252A1 (en) * 2011-12-16 2015-01-29 The Research Foundation For The State University Of New York Methods of recognizing activity in video
US8811938B2 (en) 2011-12-16 2014-08-19 Microsoft Corporation Providing a user interface experience based on inferred vehicle state
AU2012355375A1 (en) * 2011-12-19 2014-07-10 Birds In The Hand, Llc Method and system for sharing object information
US8948449B2 (en) * 2012-02-06 2015-02-03 GM Global Technology Operations LLC Selecting visible regions in nighttime images for performing clear path detection
US10076109B2 (en) 2012-02-14 2018-09-18 Noble Research Institute, Llc Systems and methods for trapping animals
IN2014DN08349A (en) 2012-03-15 2015-05-08 Behavioral Recognition Sys Inc
CN103325124B (en) * 2012-03-21 2015-11-04 东北大学 A kind of background subtraction target detection tracker based on FPGA and method
US9317751B2 (en) * 2012-04-18 2016-04-19 Vixs Systems, Inc. Video processing system with video to text description generation, search system and methods for use therewith
US10448839B2 (en) 2012-04-23 2019-10-22 Livanova Usa, Inc. Methods, systems and apparatuses for detecting increased risk of sudden death
US9681836B2 (en) 2012-04-23 2017-06-20 Cyberonics, Inc. Methods, systems and apparatuses for detecting seizure and non-seizure states
WO2013170129A1 (en) * 2012-05-10 2013-11-14 President And Fellows Of Harvard College A system and method for automatically discovering, characterizing, classifying and semi-automatically labeling animal behavior and quantitative phenotyping of behaviors in animals
TWI484941B (en) * 2012-05-10 2015-05-21 Animal gait detection system and method
RU2531876C2 (en) * 2012-05-15 2014-10-27 Общество с ограниченной ответственностью "Синезис" Indexing method of video data by means of card
US9911043B2 (en) 2012-06-29 2018-03-06 Omni Ai, Inc. Anomalous object interaction detection and reporting
US9111353B2 (en) 2012-06-29 2015-08-18 Behavioral Recognition Systems, Inc. Adaptive illuminance filter in a video analysis system
US9317908B2 (en) 2012-06-29 2016-04-19 Behavioral Recognition System, Inc. Automatic gain control filter in a video analysis system
US9723271B2 (en) 2012-06-29 2017-08-01 Omni Ai, Inc. Anomalous stationary object detection and reporting
US9113143B2 (en) 2012-06-29 2015-08-18 Behavioral Recognition Systems, Inc. Detecting and responding to an out-of-focus camera in a video analytics system
EP2867860A4 (en) 2012-06-29 2016-07-27 Behavioral Recognition Sys Inc Unsupervised learning of feature anomalies for a video surveillance system
WO2014031615A1 (en) 2012-08-20 2014-02-27 Behavioral Recognition Systems, Inc. Method and system for detecting sea-surface oil
CN104641248A (en) * 2012-09-06 2015-05-20 三立方有限公司 Position and behavioral tracking system and uses thereof
US20140122488A1 (en) * 2012-10-29 2014-05-01 Elwha Llc Food Supply Chain Automation Farm Testing System And Method
US20140121807A1 (en) 2012-10-29 2014-05-01 Elwha Llc Food Supply Chain Automation Farm Tracking System and Method
CN104662585B (en) * 2012-09-25 2017-06-13 Sk电信有限公司 The method and the event monitoring device using the method for event rules are set
WO2014053436A1 (en) * 2012-10-01 2014-04-10 Stephan Hammelbacher Method and device for organising at least one object
US10860683B2 (en) * 2012-10-25 2020-12-08 The Research Foundation For The State University Of New York Pattern change discovery between high dimensional data sets
US9232140B2 (en) 2012-11-12 2016-01-05 Behavioral Recognition Systems, Inc. Image stabilization techniques for video surveillance systems
DE102012111452B3 (en) * 2012-11-27 2014-03-20 Karlsruher Institut für Technologie Optical arrangement for recording e.g. behaviors of non-human biological object in biology field, has planar matrix forming pattern, and optical filter passing wavelength of light beam, where wavelength lying within internal is weakened
CA2892753A1 (en) * 2012-12-02 2014-06-05 Agricam Ab Systems and methods for predicting the outcome of a state of a subject
US10220211B2 (en) 2013-01-22 2019-03-05 Livanova Usa, Inc. Methods and systems to diagnose depression
US9305365B2 (en) 2013-01-24 2016-04-05 Kineticor, Inc. Systems, devices, and methods for tracking moving targets
US10327708B2 (en) 2013-01-24 2019-06-25 Kineticor, Inc. Systems, devices, and methods for tracking and compensating for patient motion during a medical imaging scan
US9717461B2 (en) 2013-01-24 2017-08-01 Kineticor, Inc. Systems, devices, and methods for tracking and compensating for patient motion during a medical imaging scan
CN109008972A (en) 2013-02-01 2018-12-18 凯内蒂科尔股份有限公司 The motion tracking system of real-time adaptive motion compensation in biomedical imaging
KR101993010B1 (en) * 2013-02-28 2019-06-25 고려대학교 산학협력단 Method and apparatus for analyzing video based on spatiotemporal patterns
KR101930990B1 (en) 2013-03-01 2018-12-19 클레버펫 엘엘씨 Animal interaction device, system, and method
EP2777490B1 (en) * 2013-03-11 2021-12-08 Biomedical International R + D GmbH Non-invasive temperature and physical activity measurement of animals
JP6057786B2 (en) * 2013-03-13 2017-01-11 ヤフー株式会社 Time-series data analysis device, time-series data analysis method, and program
US10721448B2 (en) 2013-03-15 2020-07-21 Edge 3 Technologies, Inc. Method and apparatus for adaptive exposure bracketing, segmentation and scene organization
KR102203884B1 (en) * 2013-04-12 2021-01-15 삼성전자주식회사 Imaging apparatus and controlling method thereof
US10346680B2 (en) * 2013-04-12 2019-07-09 Samsung Electronics Co., Ltd. Imaging apparatus and control method for determining a posture of an object
AU2014302060B2 (en) * 2013-06-28 2017-08-31 The United States Of America, As Represented By The Secretary, Department Of Health And Human Services Systems and methods of video monitoring for vivarium cages
AU2014290148A1 (en) * 2013-07-16 2016-02-11 Pinterest, Inc. Object based contextual menu controls
US20150022329A1 (en) * 2013-07-16 2015-01-22 Forget You Not, LLC Assisted Animal Communication
EP3031004A4 (en) 2013-08-09 2016-08-24 Behavioral Recognition Sys Inc Cognitive information security using a behavior recognition system
US9117144B2 (en) 2013-08-14 2015-08-25 Qualcomm Incorporated Performing vocabulary-based visual search using multi-resolution feature descriptors
CN103488148B (en) * 2013-09-24 2016-03-09 华北电力大学（保定） A kind of animal behavior intelligent monitor system based on Internet of Things and computer vision
US9355306B2 (en) * 2013-09-27 2016-05-31 Konica Minolta Laboratory U.S.A., Inc. Method and system for recognition of abnormal behavior
WO2015066460A2 (en) 2013-11-01 2015-05-07 Children's Medical Center Corporation Devices and methods for analyzing rodent behavior
CN105745598B (en) * 2013-11-27 2019-10-01 惠普发展公司，有限责任合伙企业 Determine the shape of the expression of object
US9230159B1 (en) * 2013-12-09 2016-01-05 Google Inc. Action recognition and detection on videos
US9495601B2 (en) 2013-12-09 2016-11-15 Mirsani, LLC Detecting and reporting improper activity involving a vehicle
US9396256B2 (en) * 2013-12-13 2016-07-19 International Business Machines Corporation Pattern based audio searching method and system
CN103676886A (en) * 2013-12-17 2014-03-26 山东大学 Standardized henhouse environment and breeding information monitoring and managing system
JP6411373B2 (en) * 2013-12-17 2018-10-24 シャープ株式会社 Recognition data transmission device, recognition data recording device, and recognition data recording method
AU2013273778A1 (en) * 2013-12-20 2015-07-09 Canon Kabushiki Kaisha Text line fragments for text line analysis
US10986223B1 (en) 2013-12-23 2021-04-20 Massachusetts Mutual Life Insurance Systems and methods for presenting content based on user behavior
US10178222B1 (en) 2016-03-22 2019-01-08 Massachusetts Mutual Life Insurance Company Systems and methods for presenting content based on user behavior
SG10201501052XA (en) * 2014-02-11 2015-09-29 Agency Science Tech & Res Method And System For Monitoring Activity Of An Animal
DE102014203749A1 (en) * 2014-02-28 2015-09-17 Robert Bosch Gmbh Method and device for monitoring at least one interior of a building and assistance system for at least one interior of a building
WO2015138384A1 (en) 2014-03-10 2015-09-17 Gojo Industries, Inc. Hygiene tracking compliance
CN106572810A (en) 2014-03-24 2017-04-19 凯内蒂科尔股份有限公司 Systems, methods, and devices for removing prospective motion correction from medical imaging scans
US9237743B2 (en) 2014-04-18 2016-01-19 The Samuel Roberts Noble Foundation, Inc. Systems and methods for trapping animals
CN104079872A (en) * 2014-05-16 2014-10-01 大连理工大学 Video image processing and human-computer interaction method based on content
US9843360B2 (en) 2014-08-14 2017-12-12 Sony Corporation Method and system for use in configuring multiple near field antenna systems
US10277280B2 (en) 2014-05-29 2019-04-30 Sony Interactive Entertainment LLC Configuration of data and power transfer in near field communications
US9577463B2 (en) 2014-05-29 2017-02-21 Sony Corporation Portable device to portable device wireless power transfer methods and systems
US10965159B2 (en) 2014-05-29 2021-03-30 Sony Corporation Scalable antenna system
TWI562636B (en) * 2014-06-16 2016-12-11 Altek Semiconductor Corp Image capture apparatus and image compensating method thereof
WO2015198767A1 (en) * 2014-06-27 2015-12-30 日本電気株式会社 Abnormality detection device and abnormality detection method
US9361802B2 (en) 2014-07-16 2016-06-07 Sony Corporation Vehicle ad hoc network (VANET)
US9906897B2 (en) 2014-07-16 2018-02-27 Sony Corporation Applying mesh network to pet carriers
US9900748B2 (en) 2014-07-16 2018-02-20 Sony Corporation Consumer electronics (CE) device and related method for providing stadium services
US10127601B2 (en) 2014-07-16 2018-11-13 Sony Corporation Mesh network applied to fixed establishment with movable items therein
US9426610B2 (en) 2014-07-16 2016-08-23 Sony Corporation Applying mesh network to luggage
US9516461B2 (en) 2014-07-16 2016-12-06 Sony Corporation Mesh network applied to arena events
EP3188660A4 (en) 2014-07-23 2018-05-16 Kineticor, Inc. Systems, devices, and methods for tracking and compensating for patient motion during a medical imaging scan
WO2016029893A1 (en) * 2014-08-29 2016-03-03 Csb-System Ag Apparatus and method for assessing compliance with animal welfare on an animal for slaughter
CA2908992A1 (en) 2014-10-22 2016-04-22 Parsin Haji Reza Photoacoustic remote sensing (pars)
US9449230B2 (en) * 2014-11-26 2016-09-20 Zepp Labs, Inc. Fast object tracking framework for sports video recognition
CN104469299A (en) * 2014-12-02 2015-03-25 柳州市瑞蚨电子科技有限公司 Network camera shooting device
CN104361724B (en) * 2014-12-03 2017-01-18 京东方科技集团股份有限公司 Device and method for detecting peeing of baby
US10409910B2 (en) 2014-12-12 2019-09-10 Omni Ai, Inc. Perceptual associative memory for a neuro-linguistic behavior recognition system
US10409909B2 (en) 2014-12-12 2019-09-10 Omni Ai, Inc. Lexical analyzer for a neuro-linguistic behavior recognition system
US9305216B1 (en) * 2014-12-15 2016-04-05 Amazon Technologies, Inc. Context-based detection and classification of actions
US9710712B2 (en) 2015-01-16 2017-07-18 Avigilon Fortress Corporation System and method for detecting, tracking, and classifiying objects
US10380486B2 (en) * 2015-01-20 2019-08-13 International Business Machines Corporation Classifying entities by behavior
US10121064B2 (en) 2015-04-16 2018-11-06 California Institute Of Technology Systems and methods for behavior detection using 3D tracking and machine learning
US9619701B2 (en) 2015-05-20 2017-04-11 Xerox Corporation Using motion tracking and image categorization for document indexing and validation
UA124378C2 (en) * 2015-07-01 2021-09-08 Вікінг Генетікс Фмба System and method for identification of individual animals based on images of the back
US9943247B2 (en) 2015-07-28 2018-04-17 The University Of Hawai'i Systems, devices, and methods for detecting false movements for motion correction during a medical imaging scan
US10650228B2 (en) 2015-09-18 2020-05-12 Children's Medical Center Corporation Devices and methods for analyzing animal behavior
CA3001063C (en) 2015-10-14 2023-09-19 President And Fellows Of Harvard College A method for analyzing motion of a subject representative of behaviour, and classifying animal behaviour
GB2544324A (en) * 2015-11-13 2017-05-17 Cathx Res Ltd Method and system for processing image data
WO2017091479A1 (en) 2015-11-23 2017-06-01 Kineticor, Inc. Systems, devices, and methods for tracking and compensating for patient motion during a medical imaging scan
KR101817583B1 (en) * 2015-11-30 2018-01-12 한국생산기술연구원 System and method for analyzing behavior pattern using depth image
CN105574501B (en) * 2015-12-15 2019-03-15 上海微桥电子科技有限公司 A kind of stream of people's video detecting analysis system
CN105512640B (en) * 2015-12-30 2019-04-02 重庆邮电大学 A kind of people flow rate statistical method based on video sequence
US10327646B2 (en) 2016-02-02 2019-06-25 Illumisonics Inc. Non-interferometric photoacoustic remote sensing (NI-PARS)
US9993182B2 (en) 2016-02-19 2018-06-12 Conduent Business Services, Llc Computer vision system for ambient long-term gait assessment
US11036219B2 (en) 2016-02-22 2021-06-15 Ketchup On, Inc. Self-propelled device
US9600717B1 (en) * 2016-02-25 2017-03-21 Zepp Labs, Inc. Real-time single-view action recognition based on key pose analysis for sports videos
CN105809711B (en) * 2016-03-02 2019-03-12 华南农业大学 A kind of pig movement big data extracting method and its system based on video frequency tracking
US10750717B2 (en) * 2016-03-04 2020-08-25 Indiana University Research And Technology Corporation Method and apparatus for spatial cognitive assessment of a lab animal
CN105828030A (en) * 2016-03-14 2016-08-03 珠海经济特区远宏科技有限公司 Video investigation mobile terminal system
CA3017518A1 (en) * 2016-03-18 2017-09-21 President And Fellows Of Harvard College Automatically classifying animal behavior
CN107221133B (en) * 2016-03-22 2018-12-11 杭州海康威视数字技术股份有限公司 A kind of area monitoring alarm system and alarm method
US10306311B1 (en) 2016-03-24 2019-05-28 Massachusetts Mutual Life Insurance Company Intelligent and context aware reading systems
US10360254B1 (en) 2016-03-24 2019-07-23 Massachusetts Mutual Life Insurance Company Intelligent and context aware reading systems
CN105894536A (en) * 2016-03-30 2016-08-24 中国农业大学 Method and system for analyzing livestock behaviors on the basis of video tracking
US9576205B1 (en) * 2016-03-31 2017-02-21 Pointgrab Ltd. Method and system for determining location of an occupant
CN108780576B (en) 2016-04-06 2022-02-25 赫尔实验室有限公司 System and method for ghost removal in video segments using object bounding boxes
US10241514B2 (en) 2016-05-11 2019-03-26 Brain Corporation Systems and methods for initializing a robot to autonomously travel a trained route
US10282849B2 (en) 2016-06-17 2019-05-07 Brain Corporation Systems and methods for predictive/reconstructive visual object tracker
US10016896B2 (en) 2016-06-30 2018-07-10 Brain Corporation Systems and methods for robotic behavior around moving bodies
IL247101B (en) 2016-08-03 2018-10-31 Pointgrab Ltd Method and system for detecting an occupant in an image
CN106264569B (en) * 2016-08-10 2020-03-06 深圳先进技术研究院 Shared emotion nerve experiment system based on observational fear acquisition
WO2018080547A1 (en) 2016-10-31 2018-05-03 Hewlett-Packard Development Company, L.P. Video monitoring
US10274325B2 (en) 2016-11-01 2019-04-30 Brain Corporation Systems and methods for robotic mapping
US10001780B2 (en) 2016-11-02 2018-06-19 Brain Corporation Systems and methods for dynamic route planning in autonomous navigation
CN106778537B (en) * 2016-11-28 2021-02-02 中国科学院心理研究所 Animal social network structure acquisition and analysis system and method based on image processing
US10723018B2 (en) 2016-11-28 2020-07-28 Brain Corporation Systems and methods for remote operating and/or monitoring of a robot
US20180150697A1 (en) * 2017-01-09 2018-05-31 Seematics Systems Ltd System and method for using subsequent behavior to facilitate learning of visual event detectors
US10713792B1 (en) * 2017-01-13 2020-07-14 Amazon Technologies, Inc. System and apparatus for image processing
US10852730B2 (en) 2017-02-08 2020-12-01 Brain Corporation Systems and methods for robotic mobile platforms
US10310471B2 (en) * 2017-02-28 2019-06-04 Accenture Global Solutions Limited Content recognition and communication system
US10627338B2 (en) 2017-03-23 2020-04-21 Illumisonics Inc. Camera-based photoacoustic remote sensing (C-PARS)
JP6909960B2 (en) * 2017-03-31 2021-07-28 パナソニックＩｐマネジメント株式会社 Detection device, detection method and detection program
WO2018185718A1 (en) * 2017-04-07 2018-10-11 Smaluet Solutions Private Limited A device and a method of learning a behavior of a pet in response to instructions provided to the pet
US10034645B1 (en) * 2017-04-13 2018-07-31 The Board Of Trustees Of The Leland Stanford Junior University Systems and methods for detecting complex networks in MRI image data
US10373316B2 (en) * 2017-04-20 2019-08-06 Ford Global Technologies, Llc Images background subtraction for dynamic lighting scenarios
WO2018208319A1 (en) 2017-05-12 2018-11-15 Children's Medical Center Corporation Devices and methods for analyzing animal behavior
CN107292889B (en) * 2017-06-14 2020-09-25 上海联影医疗科技有限公司 Tumor segmentation method, system and readable medium
US10157476B1 (en) * 2017-06-15 2018-12-18 Satori Worldwide, Llc Self-learning spatial recognition system
US10482613B2 (en) 2017-07-06 2019-11-19 Wisconsin Alumni Research Foundation Movement monitoring system
US10810414B2 (en) 2017-07-06 2020-10-20 Wisconsin Alumni Research Foundation Movement monitoring system
US11450148B2 (en) 2017-07-06 2022-09-20 Wisconsin Alumni Research Foundation Movement monitoring system
WO2019028016A1 (en) * 2017-07-31 2019-02-07 Cubic Corporation Automated scenario recognition and reporting using neural networks
US10489654B1 (en) * 2017-08-04 2019-11-26 Amazon Technologies, Inc. Video analysis method and system
US10445694B2 (en) 2017-08-07 2019-10-15 Standard Cognition, Corp. Realtime inventory tracking using deep learning
CN109583452B (en) * 2017-09-29 2021-02-19 大连恒锐科技股份有限公司 Human identity identification method and system based on barefoot footprints
CN107751011B (en) * 2017-11-07 2020-12-04 山东天智信息科技有限公司 Drinking water equipment based on drinking water adjunctie therapy
CN108133737B (en) * 2017-12-26 2021-08-31 深圳先进技术研究院 Rodent fear experiment video analysis method and device
BR102018002876A2 (en) * 2018-02-14 2019-09-10 Guimaraes Hummig Ednilson object locating platform
CN108401177B (en) * 2018-02-27 2021-04-27 上海哔哩哔哩科技有限公司 Video playing method, server and video playing system
EP3769510A1 (en) 2018-05-07 2021-01-27 Apple Inc. User interfaces for viewing live video feeds and recorded video
US11132893B2 (en) * 2018-05-11 2021-09-28 Seagate Technology, Llc Multi-sensor edge computing system
CN108664942B (en) * 2018-05-17 2021-10-22 西安理工大学 Extraction method of mouse video multi-dimensional characteristic values and video classification method
CN110505412B (en) * 2018-05-18 2021-01-29 杭州海康威视数字技术股份有限公司 Method and device for calculating brightness value of region of interest
US11576348B2 (en) 2018-05-21 2023-02-14 Companion Labs, Inc. Method for autonomously training an animal to respond to oral commands
US11700836B2 (en) 2018-05-21 2023-07-18 Companion Labs, Inc. System and method for characterizing and monitoring health of an animal based on gait and postural movements
US11205508B2 (en) 2018-05-23 2021-12-21 Verb Surgical Inc. Machine-learning-oriented surgical video analysis system
CN108846326A (en) * 2018-05-23 2018-11-20 盐城工学院 The recognition methods of pig posture, device and electronic equipment
US10905105B2 (en) * 2018-06-19 2021-02-02 Farm Jenny LLC Farm asset tracking, monitoring, and alerts
WO2020018469A1 (en) * 2018-07-16 2020-01-23 The Board Of Trustees Of The Leland Stanford Junior University System and method for automatic evaluation of gait using single or multi-camera recordings
US11048973B1 (en) 2018-07-31 2021-06-29 Objectvideo Labs, Llc Action classification using aggregated background subtraction images
US10810432B2 (en) * 2018-08-02 2020-10-20 Motorola Solutions, Inc. Methods and systems for differentiating one or more objects in a video
CN109272518B (en) * 2018-08-17 2020-05-05 东南大学 Morris water maze experiment image analysis system and method
US10769799B2 (en) * 2018-08-24 2020-09-08 Ford Global Technologies, Llc Foreground detection
US10679743B2 (en) 2018-09-12 2020-06-09 Verb Surgical Inc. Method and system for automatically tracking and managing inventory of surgical tools in operating rooms
US11803974B2 (en) 2018-10-05 2023-10-31 The Trustees Of Princeton University Automated system to measure multi-animal body part dynamics
US11715308B2 (en) * 2018-10-10 2023-08-01 Delaval Holding Ab Animal identification using vision techniques
CN113163733A (en) * 2018-10-17 2021-07-23 集团罗-曼公司 Livestock monitoring equipment
US11312594B2 (en) 2018-11-09 2022-04-26 Otis Elevator Company Conveyance system video analytics
US11093749B2 (en) 2018-12-20 2021-08-17 L'oreal Analysis and feedback system for personal care routines
CN109784208B (en) * 2018-12-26 2023-04-18 武汉工程大学 Image-based pet behavior detection method
JP7297455B2 (en) * 2019-01-31 2023-06-26 キヤノン株式会社 Image processing device, image processing method, and program
CN111614703A (en) * 2019-02-25 2020-09-01 南京爱体智能科技有限公司 Method for combining Internet of things sensor with video analysis
CN109831634A (en) * 2019-02-28 2019-05-31 北京明略软件系统有限公司 The density information of target object determines method and device
US11331006B2 (en) 2019-03-05 2022-05-17 Physmodo, Inc. System and method for human motion detection and tracking
WO2020181136A1 (en) 2019-03-05 2020-09-10 Physmodo, Inc. System and method for human motion detection and tracking
WO2020188386A1 (en) * 2019-03-15 2020-09-24 Illumisonics Inc. Single source photoacoustic remote sensing (ss-pars)
KR102228350B1 (en) * 2019-05-03 2021-03-16 주식회사 엘지유플러스 Apparatus and method for monitering pet
US11363071B2 (en) 2019-05-31 2022-06-14 Apple Inc. User interfaces for managing a local network
US10904029B2 (en) 2019-05-31 2021-01-26 Apple Inc. User interfaces for managing controllable external devices
US20200383299A1 (en) * 2019-06-06 2020-12-10 Edgar Josue Bermudez Contreras Systems and methods of homecage monitoring
CN110516535A (en) * 2019-07-12 2019-11-29 杭州电子科技大学 A kind of mouse liveness detection method and system and hygienic appraisal procedure based on deep learning
CN110427865B (en) * 2019-07-29 2023-08-25 三峡大学 Human behavior video feature picture extraction and reconstruction method for high-voltage forbidden region
CN110301364B (en) * 2019-08-02 2021-09-24 中国人民解放军军事科学院军事医学研究院 Experiment box for research on social behaviors of mice
CN110456831B (en) * 2019-08-16 2022-06-14 南开大学 Mouse contact behavior tracking platform based on active vision
CN110490161B (en) * 2019-08-23 2022-01-07 安徽农业大学 Captive animal behavior analysis method based on deep learning
US11213015B2 (en) * 2019-09-17 2022-01-04 Eknauth Persaud System and a method of lab animal observation
US11321927B1 (en) * 2019-09-23 2022-05-03 Apple Inc. Temporal segmentation
AU2020104459A4 (en) * 2019-10-14 2021-10-28 TBIAS Pty Ltd An automated behavioural monitoring unit
TWI731442B (en) * 2019-10-18 2021-06-21 宏碁股份有限公司 Electronic apparatus and object information recognition method by using touch data thereof
US11557151B2 (en) 2019-10-24 2023-01-17 Deere & Company Object identification on a mobile work machine
CN112764594B (en) * 2019-11-01 2023-06-09 宏碁股份有限公司 Electronic device and object information identification method using touch data thereof
US11587361B2 (en) 2019-11-08 2023-02-21 Wisconsin Alumni Research Foundation Movement monitoring system
US11109586B2 (en) * 2019-11-13 2021-09-07 Bird Control Group, Bv System and methods for automated wildlife detection, monitoring and control
CN110866559A (en) * 2019-11-14 2020-03-06 上海中信信息发展股份有限公司 Poultry behavior analysis method and device
US11284824B2 (en) * 2019-12-02 2022-03-29 Everseen Limited Method and system for determining a human social behavior classification
CN111062436B (en) * 2019-12-15 2024-04-16 深圳市具安科技有限公司 Analysis method and device for cockroach mating behavior, computer equipment and storage medium
AU2019479570A1 (en) 2019-12-19 2022-08-18 Illumisonics Inc. Photoacoustic remote sensing (PARS), and related methods of use
US11755989B2 (en) 2020-03-27 2023-09-12 Toshiba Global Commerce Solutions Holdings Corporation Preventing theft at retail stores
CN113469180A (en) * 2020-03-31 2021-10-01 阿里巴巴集团控股有限公司 Medical image processing method and system and data processing method
US11482049B1 (en) 2020-04-14 2022-10-25 Bank Of America Corporation Media verification system
US11238634B2 (en) * 2020-04-28 2022-02-01 Adobe Inc. Motion model refinement based on contact analysis and optimization
US11079913B1 (en) 2020-05-11 2021-08-03 Apple Inc. User interface for status indicators
US11786128B2 (en) 2020-06-18 2023-10-17 Illumisonics Inc. PARS imaging methods
US11122978B1 (en) 2020-06-18 2021-09-21 Illumisonics Inc. PARS imaging methods
US11589010B2 (en) 2020-06-03 2023-02-21 Apple Inc. Camera and visitor user interfaces
US11657614B2 (en) 2020-06-03 2023-05-23 Apple Inc. Camera and visitor user interfaces
US11918370B2 (en) * 2020-06-10 2024-03-05 The Board Of Trustees Of The Leland Stanford Junior University Systems and methods for estimation of Parkinson's Disease gait impairment severity from videos using MDS-UPDRS
CN111967321B (en) * 2020-07-15 2024-04-05 菜鸟智能物流控股有限公司 Video data processing method, device, electronic equipment and storage medium
CN116075870A (en) * 2020-07-30 2023-05-05 杰克逊实验室 Automated phenotypic analysis of behavior
WO2022035424A1 (en) * 2020-08-11 2022-02-17 Hitachi America, Ltd. Situation recognition method and system for manufacturing collaborative robots
EP4189682A1 (en) 2020-09-05 2023-06-07 Apple Inc. User interfaces for managing audio for media items
CN112189588B (en) * 2020-10-10 2022-04-05 东北农业大学 Cow image information collecting and processing method and system
CN112215160B (en) * 2020-10-13 2023-11-24 厦门大学 Video three-dimensional human body posture estimation algorithm utilizing long-short period information fusion
AU2021359652A1 (en) 2020-10-14 2023-06-22 One Cup Productions Ltd. Animal visual identification, tracking, monitoring and assessment systems and methods thereof
AU2021414124A1 (en) * 2020-12-29 2023-07-13 The Jackson Laboratory Gait and posture analysis
US11928187B1 (en) 2021-02-17 2024-03-12 Bank Of America Corporation Media hosting system employing a secured video stream
US11594032B1 (en) 2021-02-17 2023-02-28 Bank Of America Corporation Media player and video verification system
US11527106B1 (en) 2021-02-17 2022-12-13 Bank Of America Corporation Automated video verification
US11790694B1 (en) 2021-02-17 2023-10-17 Bank Of America Corporation Video player for secured video stream
US20220335446A1 (en) * 2021-04-14 2022-10-20 Sunshine Energy Technology Co., Ltd. Real Food Honesty Display System
CN113205032B (en) * 2021-04-27 2022-11-01 安徽正华生物仪器设备有限公司 Automatic analysis system and method for mouse suspension experiment based on deep learning
CA3222789A1 (en) 2021-05-27 2022-12-01 Ai Thinktank Llc 3d avatar generation and robotic limbs using biomechanical analysis
US11640725B2 (en) 2021-05-28 2023-05-02 Sportsbox.ai Inc. Quantitative, biomechanical-based analysis with outcomes and context
US12008839B2 (en) 2021-05-28 2024-06-11 Sportsbox.ai Inc. Golf club and other object fitting using quantitative biomechanical-based analysis
US11526548B1 (en) 2021-06-24 2022-12-13 Bank Of America Corporation Image-based query language system for performing database operations on images and videos
US11941051B1 (en) 2021-06-24 2024-03-26 Bank Of America Corporation System for performing programmatic operations using an image-based query language
US11784975B1 (en) * 2021-07-06 2023-10-10 Bank Of America Corporation Image-based firewall system
US12028319B1 (en) 2021-07-06 2024-07-02 Bank Of America Corporation Image-based firewall for synthetic media prevention
CN117980946A (en) 2021-09-28 2024-05-03 富士通株式会社 Image processing program, image processing apparatus, and image processing method
KR102714247B1 (en) * 2021-11-29 2024-10-08 주식회사 바딧 Method, system and non-transitory computer-readable recording medium for supporting labeling to sensor data
US20230206615A1 (en) * 2021-12-29 2023-06-29 Halliburton Energy Services, Inc. Systems and methods to determine an activity associated with an object of interest
CN114533040B (en) * 2022-01-12 2024-04-09 北京京仪仪器仪表研究总院有限公司 Method for monitoring specific activity of personnel in fixed space
USD1035720S1 (en) 2022-04-20 2024-07-16 Sportsbox.ai Inc. Display screen with transitional graphical user interface
USD1035721S1 (en) 2022-04-20 2024-07-16 Sportsbox.ai Inc. Display screen with transitional graphical user interface
USD1036464S1 (en) 2022-04-20 2024-07-23 Sportsbox.ai Inc. Display screen with transitional graphical user interface
EP4276772A1 (en) * 2022-05-12 2023-11-15 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Method, computer program and system for analysing one or more moving objects in a video
CN114916452A (en) * 2022-05-26 2022-08-19 浙江理工大学 Device for testing influence of IVC environmental parameters on thermal comfort of SPF experimental animals
CN115281604B (en) * 2022-08-24 2023-11-21 深圳市具安科技有限公司 Animal eye movement-based vertical axis rotation analysis method, device and medium
WO2024166039A1 (en) 2023-02-08 2024-08-15 Illumisonics Inc. Photon absorption remote sensing system for histological assessment of tissues
CN116778420A (en) * 2023-06-26 2023-09-19 潍坊医学院 Medicine use monitoring feedback method and system based on big data video image analysis

Family Cites Families (70)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3100473A (en) 1961-01-30 1963-08-13 Mead Johnson & Co Apparatus for measuring animal activity
US3304911A (en) 1964-08-24 1967-02-21 Shionogi & Co Apparatus for automatically measuring the movement of an animal
US3485213A (en) * 1967-10-23 1969-12-23 Edward J Scanlon Animal exercising,conditioning and therapy and apparatus therefor
DE2152406C3 (en) 1971-10-21 1974-09-26 Institut Dr. Friedrich Foerster Pruefgeraetebau, 7410 Reutlingen Arrangement for determining the activity of test animals
US3974798A (en) * 1975-04-21 1976-08-17 Meetze Jr Murray O Method and apparatus for studying laboratory animal behavior
US4337726A (en) 1980-07-07 1982-07-06 Czekajewski Jan A Animal activity monitor and behavior processor
JPS58184810U (en) * 1982-06-01 1983-12-08 鐘淵化学工業株式会社 magnetic circuit device
US4517593A (en) * 1983-04-29 1985-05-14 The United States Of America As Represented By The Secretary Of The Navy Video multiplexer
US4631676A (en) * 1983-05-25 1986-12-23 Hospital For Joint Diseases Or Computerized video gait and motion analysis system and method
US4574734A (en) 1984-05-25 1986-03-11 Omnitech Electronics, Inc. Universal animal activity monitoring system
US4600016A (en) * 1985-08-26 1986-07-15 Biomechanical Engineering Corporation Method and apparatus for gait recording and analysis
JPH0785080B2 (en) * 1986-11-25 1995-09-13 株式会社日立製作所 Fish condition monitor
US4888703A (en) * 1986-09-09 1989-12-19 Hitachi Engineering Co., Ltd. Apparatus for monitoring the toxicant contamination of water by using aquatic animals
JPH07108285B2 (en) 1988-10-14 1995-11-22 東洋産業株式会社 Experimental animal behavior observer
WO1993006779A1 (en) * 1991-10-10 1993-04-15 Neurocom International, Inc. Apparatus and method for characterizing gait
JP3244798B2 (en) 1992-09-08 2002-01-07 株式会社東芝 Moving image processing device
US5428723A (en) * 1992-09-09 1995-06-27 International Business Machines Corporation Method and apparatus for capturing the motion of an object in motion video
US5299454A (en) * 1992-12-10 1994-04-05 K.K. Holding Ag Continuous foot-strike measuring system and method
US5377258A (en) * 1993-08-30 1994-12-27 National Medical Research Council Method and apparatus for an automated and interactive behavioral guidance system
US5414644A (en) * 1993-11-24 1995-05-09 Ethnographics, Inc. Repetitive event analysis system
US6165747A (en) * 1993-12-30 2000-12-26 President & Fellows Of Harvard College Nucleic acids encoding hedgehog proteins
US20030186357A1 (en) * 1993-12-30 2003-10-02 Philip W. Ingham Vertebrate embryonic pattern-inducing proteins, and uses related thereto
JP3123587B2 (en) * 1994-03-09 2001-01-15 日本電信電話株式会社 Moving object region extraction method using background subtraction
JPH0863603A (en) * 1994-06-15 1996-03-08 Olympus Optical Co Ltd Image analyzer
US5708767A (en) 1995-02-03 1998-01-13 The Trustees Of Princeton University Method and apparatus for video browsing based on content and structure
US5821945A (en) 1995-02-03 1998-10-13 The Trustees Of Princeton University Method and apparatus for video browsing based on content and structure
US5872865A (en) * 1995-02-08 1999-02-16 Apple Computer, Inc. Method and system for automatic classification of video images
US6343188B1 (en) * 1995-03-02 2002-01-29 Canon Kabushiki Kaisha Vibration correction apparatus and optical device
JP3683929B2 (en) * 1995-03-02 2005-08-17 キヤノン株式会社 Blur correction device and optical device
GB9506324D0 (en) * 1995-03-28 1995-05-17 Vinten Group Plc Improvements in or relating to linear force actuators
US5870138A (en) * 1995-03-31 1999-02-09 Hitachi, Ltd. Facial image processing
JP3377659B2 (en) * 1995-09-07 2003-02-17 株式会社日立国際電気 Object detection device and object detection method
US6088468A (en) * 1995-05-17 2000-07-11 Hitachi Denshi Kabushiki Kaisha Method and apparatus for sensing object located within visual field of imaging device
US6231527B1 (en) * 1995-09-29 2001-05-15 Nicholas Sol Method and apparatus for biomechanical correction of gait and posture
US5546439A (en) * 1995-11-02 1996-08-13 General Electric Company Systems, methods and apparatus for incrementally reconstructing overlapped images in a CT system implementing a helical scan
US5969755A (en) * 1996-02-05 1999-10-19 Texas Instruments Incorporated Motion based event detection system and method
US6310270B1 (en) * 1996-03-15 2001-10-30 The General Hospital Corporation Endothelial NOS knockout mice and methods of use
JP3540494B2 (en) * 1996-03-15 2004-07-07 株式会社東芝 Cooperative work adjusting device and cooperative work adjusting method
EP0816986B1 (en) * 1996-07-03 2006-09-06 Hitachi, Ltd. System for recognizing motions
JP3679512B2 (en) * 1996-07-05 2005-08-03 キヤノン株式会社 Image extraction apparatus and method
JP3436293B2 (en) * 1996-07-25 2003-08-11 沖電気工業株式会社 Animal individual identification device and individual identification system
EP0837418A3 (en) 1996-10-18 2006-03-29 Kabushiki Kaisha Toshiba Method and apparatus for generating information input using reflected light image of target object
JP3512992B2 (en) * 1997-01-07 2004-03-31 株式会社東芝 Image processing apparatus and image processing method
US6215898B1 (en) * 1997-04-15 2001-04-10 Interval Research Corporation Data processing system and method
US5816256A (en) 1997-04-17 1998-10-06 Bioanalytical Systems, Inc. Movement--responsive system for conducting tests on freely-moving animals
US6263088B1 (en) * 1997-06-19 2001-07-17 Ncr Corporation System and method for tracking movement of objects in a scene
US6295367B1 (en) * 1997-06-19 2001-09-25 Emtera Corporation System and method for tracking movement of objects in a scene using correspondence graphs
US6334187B1 (en) * 1997-07-03 2001-12-25 Matsushita Electric Industrial Co., Ltd. Information embedding method, information extracting method, information embedding apparatus, information extracting apparatus, and recording media
JPH1152215A (en) * 1997-07-29 1999-02-26 Nikon Corp Lens driving device
US6061088A (en) 1998-01-20 2000-05-09 Ncr Corporation System and method for multi-resolution background adaptation
US6212510B1 (en) * 1998-01-30 2001-04-03 Mitsubishi Electric Research Laboratories, Inc. Method for minimizing entropy in hidden Markov models of physical signals
US6242456B1 (en) * 1998-03-09 2001-06-05 Trustees Of Tufts College Treatment of stereotypic, self-injurious and compulsive behaviors in man and animals using antagonists of NMDA receptors
JP3270005B2 (en) * 1998-03-20 2002-04-02 勝義 川崎 Automated method of observing behavior of experimental animals
US6072496A (en) 1998-06-08 2000-06-06 Microsoft Corporation Method and system for capturing and representing 3D geometry, color and shading of facial expressions and other animated objects
IL125940A (en) * 1998-08-26 2002-05-23 Bar Shalom Avshalom Device, method and system for automatic identification of sound patterns made by animals
US6721454B1 (en) * 1998-10-09 2004-04-13 Sharp Laboratories Of America, Inc. Method for automatic extraction of semantically significant events from video
CN1332726A (en) * 1998-11-02 2002-01-23 卫福有限公司 Pyrrolidine compounds and pharmaceutical use thereof
JP4392886B2 (en) * 1999-01-22 2010-01-06 キヤノン株式会社 Image extraction method and apparatus
US7133537B1 (en) * 1999-05-28 2006-11-07 It Brokerage Services Pty Limited Method and apparatus for tracking a moving object
WO2001033953A1 (en) * 1999-11-11 2001-05-17 Kowa Co., Ltd. Method and device for measuring frequency of specific behavior of animal
GB2358098A (en) * 2000-01-06 2001-07-11 Sharp Kk Method of segmenting a pixelled image
US6311644B1 (en) * 2000-02-03 2001-11-06 Carl S. Pugh Apparatus and method for animal behavior tracking, predicting and signaling
ATE289161T1 (en) * 2000-05-16 2005-03-15 Max Planck Gesellschaft NEW SCREENING DEVICE FOR ANALYZING THE BEHAVIOR OF LABORATORY ANIMALS
US6601010B1 (en) * 2000-06-05 2003-07-29 The University Of Kansas Force plate actometer
US7643655B2 (en) * 2000-11-24 2010-01-05 Clever Sys, Inc. System and method for animal seizure detection and classification using video analysis
US6678413B1 (en) * 2000-11-24 2004-01-13 Yiqing Liang System and method for object identification and behavior characterization using video analysis
US7269516B2 (en) * 2001-05-15 2007-09-11 Psychogenics, Inc. Systems and methods for monitoring behavior informatics
JP2005529580A (en) * 2001-08-06 2005-10-06 サイコジェニクス インク Programmable electronic maze for use in animal behavior assessment
CA2460832A1 (en) * 2001-09-17 2003-03-27 The Curavita Corporation Monitoring locomotion kinematics in ambulating animals
US6929586B2 (en) * 2002-07-15 2005-08-16 Reginald A. Johnson Balance and gait training board

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
None

Cited By (51)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7643655B2 (en) 2000-11-24 2010-01-05 Clever Sys, Inc. System and method for animal seizure detection and classification using video analysis
US8514236B2 (en) 2000-11-24 2013-08-20 Cleversys, Inc. System and method for animal gait characterization from bottom view using video analysis
US7817824B2 (en) 2000-11-24 2010-10-19 Clever Sys, Inc. Unified system and method for animal behavior characterization from top view using video analysis
US7882135B2 (en) 2001-05-15 2011-02-01 Psychogenics, Inc. Method for predicting treatment classes using behavior informatics
US7269516B2 (en) 2001-05-15 2007-09-11 Psychogenics, Inc. Systems and methods for monitoring behavior informatics
US7580798B2 (en) 2001-05-15 2009-08-25 Psychogenics, Inc. Method for predicting treatment classes using animal behavior informatics
US9565398B2 (en) 2001-06-11 2017-02-07 Arrowsight, Inc. Caching graphical interface for displaying video and ancillary data from a saved video
JP2011081823A (en) * 2002-06-28 2011-04-21 Koninkl Philips Electronics Nv Method and apparatus for modeling behavior using probability distribution function
ES2242484A1 (en) * 2003-01-24 2005-11-01 Pedro Monagas Asensio Mood analysing device for mammals
GB2442673A (en) * 2005-08-03 2008-04-09 Honeywell Int Inc Boolean complement methods and systems for video image processing a region of interest
WO2007019140A3 (en) * 2005-08-03 2007-07-26 Honeywell Int Inc Boolean complement methods and systems for video image processing a region of interest
WO2007019140A2 (en) * 2005-08-03 2007-02-15 Honeywell International Inc. Boolean complement methods and systems for video image processing a region of interest
US7558404B2 (en) 2005-11-28 2009-07-07 Honeywell International Inc. Detection of abnormal crowd behavior
WO2007064559A1 (en) * 2005-11-28 2007-06-07 Honeywell International Inc. Detection of abnormal crowd behavior
WO2007110555A1 (en) * 2006-03-28 2007-10-04 The University Court Of The University Of Edinburgh A method for automatically characterizing the behavior of one or more objects
CN101410855B (en) * 2006-03-28 2011-11-30 爱丁堡大学评议会 Method for automatically attributing one or more object behaviors
WO2009045578A3 (en) * 2007-06-18 2009-05-22 Boeing Co Object detection incorporating background clutter removal
WO2009045578A2 (en) * 2007-06-18 2009-04-09 The Boeing Company Object detection incorporating background clutter removal
WO2010032247A3 (en) * 2008-09-17 2010-05-27 Ramot At Tel-Aviv University Ltd. System and method for analyzing exploratory behavior
WO2010032247A2 (en) * 2008-09-17 2010-03-25 Ramot At Tel-Aviv University Ltd. System and method for analyzing exploratory behavior
US8634635B2 (en) 2008-10-30 2014-01-21 Clever Sys, Inc. System and method for stereo-view multiple animal behavior characterization
EP2521070A3 (en) * 2011-05-06 2013-12-25 Deutsche Telekom AG Method and system for recording a static or dynamic scene, for determining raw events and detecting free areas in an area under observation
US20130172154A1 (en) * 2011-12-28 2013-07-04 Samsung Electronics Co., Ltd. Method for measuring quantity of exercise and display apparatus thereof
EP2609858A1 (en) * 2011-12-28 2013-07-03 Samsung Electronics Co., Ltd Method for measuring quantity of exercise and display apparatus thereof
CN102970519A (en) * 2012-11-29 2013-03-13 河海大学常州校区 Non-rigid target behavior observation device and method based on visual perception network
US11551079B2 (en) 2017-03-01 2023-01-10 Standard Cognition, Corp. Generating labeled training images for use in training a computational neural network for object or action recognition
US11790682B2 (en) 2017-03-10 2023-10-17 Standard Cognition, Corp. Image analysis using neural networks for pose and action identification
US11023850B2 (en) 2017-08-07 2021-06-01 Standard Cognition, Corp. Realtime inventory location management using deep learning
US11250376B2 (en) 2017-08-07 2022-02-15 Standard Cognition, Corp Product correlation analysis using deep learning
US12056660B2 (en) 2017-08-07 2024-08-06 Standard Cognition, Corp. Tracking inventory items in a store for identification of inventory items to be re-stocked and for identification of misplaced items
US11195146B2 (en) 2017-08-07 2021-12-07 Standard Cognition, Corp. Systems and methods for deep learning-based shopper tracking
US11200692B2 (en) 2017-08-07 2021-12-14 Standard Cognition, Corp Systems and methods to check-in shoppers in a cashier-less store
US11232687B2 (en) 2017-08-07 2022-01-25 Standard Cognition, Corp Deep learning-based shopper statuses in a cashier-less store
EP3665615A4 (en) * 2017-08-07 2020-12-30 Standard Cognition, Corp. Predicting inventory events using semantic diffing
US11544866B2 (en) 2017-08-07 2023-01-03 Standard Cognition, Corp Directional impression analysis using deep learning
US11270260B2 (en) 2017-08-07 2022-03-08 Standard Cognition Corp. Systems and methods for deep learning-based shopper tracking
US12026665B2 (en) 2017-08-07 2024-07-02 Standard Cognition, Corp. Identifying inventory items using multiple confidence levels
US11295270B2 (en) 2017-08-07 2022-04-05 Standard Cognition, Corp. Deep learning-based store realograms
US11810317B2 (en) 2017-08-07 2023-11-07 Standard Cognition, Corp. Systems and methods to check-in shoppers in a cashier-less store
WO2019032306A1 (en) 2017-08-07 2019-02-14 Standard Cognition, Corp. Predicting inventory events using semantic diffing
US11538186B2 (en) 2017-08-07 2022-12-27 Standard Cognition, Corp. Systems and methods to check-in shoppers in a cashier-less store
US10410371B2 (en) 2017-12-21 2019-09-10 The Boeing Company Cluttered background removal from imagery for object detection
US11232575B2 (en) 2019-04-18 2022-01-25 Standard Cognition, Corp Systems and methods for deep learning-based subject persistence
US11948313B2 (en) 2019-04-18 2024-04-02 Standard Cognition, Corp Systems and methods of implementing multiple trained inference engines to identify and track subjects over multiple identification intervals
EP4046066A4 (en) * 2019-11-07 2023-11-15 Google LLC Monitoring animal pose dynamics from monocular images
US20210315186A1 (en) * 2020-04-14 2021-10-14 The United States Of America, As Represented By Secretary Of Agriculture Intelligent dual sensory species-specific recognition trigger system
US11361468B2 (en) 2020-06-26 2022-06-14 Standard Cognition, Corp. Systems and methods for automated recalibration of sensors for autonomous checkout
US11303853B2 (en) 2020-06-26 2022-04-12 Standard Cognition, Corp. Systems and methods for automated design of camera placement and cameras arrangements for autonomous checkout
US11818508B2 (en) 2020-06-26 2023-11-14 Standard Cognition, Corp. Systems and methods for automated design of camera placement and cameras arrangements for autonomous checkout
US12079769B2 (en) 2020-06-26 2024-09-03 Standard Cognition, Corp. Automated recalibration of sensors for autonomous checkout
CN114241521A (en) * 2021-12-13 2022-03-25 北京华夏电通科技股份有限公司 Method, device and equipment for identifying court trial video picture normal area

Also Published As

Publication number Publication date
US8514236B2 (en) 2013-08-20
US20040131254A1 (en) 2004-07-08
US20040141635A1 (en) 2004-07-22
JP2004514975A (en) 2004-05-20
AU2002239272A1 (en) 2002-06-03
US7068842B2 (en) 2006-06-27
US20070229522A1 (en) 2007-10-04
US20090296992A1 (en) 2009-12-03
US20040141636A1 (en) 2004-07-22
EP1337962A2 (en) 2003-08-27
US7209588B2 (en) 2007-04-24
EP1337962B1 (en) 2012-09-26
US20090285452A1 (en) 2009-11-19
EP1337962A4 (en) 2007-02-28
WO2002043352A3 (en) 2003-01-09
US20110007946A1 (en) 2011-01-13
US7817824B2 (en) 2010-10-19
US6678413B1 (en) 2004-01-13
US20070175406A1 (en) 2007-08-02
EP1337962B9 (en) 2013-02-13

Similar Documents

Publication Publication Date Title
US6678413B1 (en) System and method for object identification and behavior characterization using video analysis
US8774532B2 (en) Calibration of video object classification
US8520899B2 (en) Video object classification
US7995843B2 (en) Monitoring device which monitors moving objects
EP2192549B1 (en) Target tracking device and target tracking method
Hong et al. Fast multi-feature pedestrian detection algorithm based on histogram of oriented gradient using discrete wavelet transform
Wang et al. Towards a kinect-based behavior recognition and analysis system for small animals
CN114549371B (en) Image analysis method and device
Twining et al. Robust tracking and posture description for laboratory rodents using active shape models
CN107886060A (en) Pedestrian&#39;s automatic detection and tracking based on video
Farah et al. Catching a rat by its edglets
Latecki et al. Motion detection based on local variation of spatiotemporal texture
JP6893812B2 (en) Object detector
CN115690554A (en) Target identification method, system, electronic device and storage medium
Leroy et al. Computer vision based recognition of behavior phenotypes of laying hens
JP2000125288A5 (en)
Zurn et al. Video-based rodent activity measurement using near-infrared illumination
CN117854114B (en) Intelligent identification method, equipment and medium for coupling behavior of zebra fish
CN118247581B (en) Method and device for labeling and analyzing gestures of key points of animal images
Sepúlveda et al. Evaluation of background subtraction algorithms using MuHAVi, a multicamera human action video dataset
US11257238B2 (en) Unsupervised object sizing method for single camera viewing
JP2021125048A (en) Information processing apparatus, information processing method, image processing apparatus, and program
Latecki et al. Activity and motion detection based on measuring texture change
French Visual Tracking: From An Individual To Groups Of Animals
Al-Raziqi et al. Detection of object interactions in video sequences

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NO NZ OM PH PL PT RO RU SD SE SG SI SK SL TJ TM TR TT TZ UA UG UZ VN YU ZA ZW

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
WWE Wipo information: entry into national phase

Ref document number: 2001987014

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2002544950

Country of ref document: JP

WWP Wipo information: published in national office

Ref document number: 2001987014

Country of ref document: EP

REG Reference to national code

Ref country code: DE

Ref legal event code: 8642