CN112016414A - Method and device for detecting high-altitude parabolic event and intelligent floor monitoring system - Google Patents
Method and device for detecting high-altitude parabolic event and intelligent floor monitoring system Download PDFInfo
- Publication number
- CN112016414A CN112016414A CN202010817165.3A CN202010817165A CN112016414A CN 112016414 A CN112016414 A CN 112016414A CN 202010817165 A CN202010817165 A CN 202010817165A CN 112016414 A CN112016414 A CN 112016414A
- Authority
- CN
- China
- Prior art keywords
- image
- moving target
- altitude parabolic
- moving
- pixel coordinate
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 82
- 238000012544 monitoring process Methods 0.000 title claims abstract description 12
- 238000006073 displacement reaction Methods 0.000 claims description 70
- 238000001514 detection method Methods 0.000 claims description 33
- 230000015654 memory Effects 0.000 claims description 17
- 238000007781 pre-processing Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 230000005484 gravity Effects 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 230000008034 disappearance Effects 0.000 claims description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 7
- 238000013527 convolutional neural network Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000002829 reductive effect Effects 0.000 description 5
- 230000001133 acceleration Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000013145 classification model Methods 0.000 description 4
- 230000002708 enhancing effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 241000238631 Hexapoda Species 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003707 image sharpening Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 208000003443 Unconsciousness Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010205 computational analysis Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000010419 fine particle Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30232—Surveillance
-
- 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
- G06T2207/30241—Trajectory
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention relates to the technical field of artificial intelligence, in particular to a method and a device for detecting a high-altitude parabolic event and a floor intelligent monitoring system.
Description
Technical Field
The embodiment of the invention relates to the technical field of artificial intelligence, in particular to a method and a device for detecting a high-altitude parabolic event and a floor intelligent monitoring system.
Background
The high-altitude throwing is called 'pain over the city', is an uneconomical behavior and brings great hidden dangers to social safety, for example, falling objects can not only smash nearby equipment and buildings, but also hurt the life safety of pedestrians. In addition, the event occurrence places are high-altitude floors, witnesses are few, and the parabolic events are short, so that law responsibilities of the parabolic persons are difficult to follow by law enforcement departments. Therefore, the monitoring and tracing ability of the high altitude parabola needs to be improved.
In the process of implementing the embodiment of the present invention, the inventor of the present invention finds that: at present, the traditional monitoring camera simply shoots and obtains evidence, has no intelligent identification capability and real-time alarm and early warning capability, is not enough to urge an unconscious resident to stop throwing objects at high altitude, and cannot provide early warning of throwing objects at high altitude for pedestrians approaching downstairs. In addition, the existing recognition algorithm cannot distinguish the difference between scenes such as 'bird flying' or 'leaf falling' and the like and 'high-altitude parabolic', and the recognition accuracy is low.
Disclosure of Invention
The embodiment of the invention mainly solves the technical problem of providing a method for detecting a high-altitude parabolic event, which can accurately identify and track the high-altitude parabolic event.
In order to solve the technical problem, the embodiment of the invention adopts the following technical scheme:
in order to solve the above technical problem, in a first aspect, an embodiment of the present invention provides a method for detecting a high altitude parabolic event, including:
acquiring a frame image from a real-time video of a floor;
detecting whether a moving target exists according to the frame image;
if so, acquiring the motion track of the motion target;
and determining whether the moving target is a high-altitude parabolic event or not according to the motion track.
In some embodiments, the step of determining whether the moving object is a high altitude parabolic event according to the motion trajectory further includes:
calculating a time interval from the detection of the moving object in the real-time video to the disappearance of the moving object in the real-time video as a moving time of the moving object;
if the motion time is less than the preset time, determining that the moving target is not a high-altitude parabolic event;
if the motion time is greater than or equal to the preset time, acquiring a motion track of the moving target within the preset time;
and determining whether the moving target is a high-altitude parabolic event or not according to the moving track of the moving target in the preset time.
In some embodiments, the step of determining whether the moving object is a high altitude parabolic event according to the moving trajectory of the moving object within the preset time further includes:
extracting frame images according to a preset interval frame number within the preset time to generate an image sequence;
respectively calculating the vertical pixel coordinate displacement and the horizontal pixel coordinate displacement of the moving target in each two adjacent frames of images according to the image sequence so as to respectively obtain a vertical pixel coordinate displacement sequence and a horizontal pixel coordinate displacement sequence;
judging whether the vertical pixel coordinate displacement in the vertical pixel coordinate displacement sequence is in the gravity direction and gradually increases;
if so, judging whether horizontal pixel coordinate displacement which is greater than or equal to a preset threshold value exists in the horizontal pixel coordinate displacement sequence;
and if the horizontal pixel coordinate displacement which is greater than or equal to a preset threshold value does not exist in the horizontal pixel coordinate displacement sequence, determining that the moving target is a high-altitude parabolic event.
In some implementations, prior to the step of determining that the moving object is a high altitude parabolic event, further comprising:
if the horizontal pixel coordinate displacement which is greater than or equal to a preset threshold value does not exist in the horizontal pixel coordinate displacement sequence, adopting a neural network identification algorithm to identify the type of the moving target;
and determining whether the moving target is a high-altitude parabolic event or not according to the type of the moving target.
In some embodiments, the step of detecting whether the moving object exists according to the real-time video frame image further comprises:
performing first image preprocessing on the frame image;
and determining whether the moving target exists or not by adopting an interframe difference method.
In some embodiments, the inter-frame differencing method is an adjacent frame differencing method or an adjacent three-frame differencing method.
In some embodiments, further comprising:
performing second image preprocessing on the frame image with the gray difference;
marking a connected region in the frame image with the gray difference;
and verifying the moving target according to the form and the size of the communication area.
In some embodiments, further comprising:
when a high altitude parabolic event is detected, a warning alert is sent.
In order to solve the above technical problem, in a second aspect, an embodiment of the present invention provides an apparatus for detecting a high altitude parabolic event, including:
the first acquisition module is used for acquiring a frame image from a real-time video of a floor;
the detection module is used for detecting whether a moving target exists or not according to the frame image;
the second acquisition module is used for acquiring the motion track of the moving target if the moving target exists;
and the first determination module is used for determining whether the moving target is a high-altitude parabolic event or not according to the motion track.
In order to solve the above technical problem, in a third aspect, an embodiment of the present invention provides an intelligent floor monitoring system, including:
the image acquisition module is used for acquiring frame images from a real-time video of the floor;
at least one processor connected with the image acquisition module; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect as described above.
In order to solve the above technical problem, in a fourth aspect, an embodiment of the present invention provides a non-volatile computer-readable storage medium, which stores computer-executable instructions that, when executed by an electronic device, cause the electronic device to perform the method according to the first aspect.
The embodiment of the invention has the following beneficial effects: different from the situation of the prior art, the method for detecting the high-altitude parabolic events provided by the embodiment of the invention detects whether a moving target exists or not by acquiring the frame image from the real-time video of the floor according to the frame image, acquires the motion track of the moving target under the condition that the moving target exists, and identifies the high-altitude parabolic events according to the motion track and by combining the kinematics law of free falling bodies, so that the high-altitude parabolic events can be accurately identified and tracked, and the difference between scenes such as 'bird flying over' or 'leaf flying' and the like and 'high-altitude parabolic' is distinguished.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
FIG. 1a is a schematic diagram of an exemplary system architecture for an embodiment of a method of detecting high altitude parabolic events as applied to the present invention;
FIG. 1b is a schematic diagram of another exemplary system architecture for an embodiment of a method of detecting high altitude parabolic events as applied to the present invention;
FIG. 1c is a schematic diagram of another exemplary system architecture for an embodiment of a method of detecting high altitude parabolic events as applied to the present invention;
FIG. 2a is a schematic diagram of the hardware architecture of an exemplary system for use in an embodiment of the method of detecting high altitude parabolic events of the present invention;
FIG. 2b is another hardware configuration diagram of an exemplary system for use in an embodiment of the method of detecting high altitude parabolic events of the present invention;
FIG. 2c is another hardware configuration diagram of an exemplary system for use in an embodiment of the method of detecting high altitude parabolic events of the present invention;
FIG. 3 is a flow chart of a method for detecting a high altitude parabolic event according to an embodiment of the present invention;
FIG. 4 is a sub-flowchart of step 220 of the method of FIG. 3;
FIG. 5 is another sub-flow diagram of step 220 of the method of FIG. 3;
FIG. 6 is a sub-flowchart of step 240 of the method of FIG. 3;
FIG. 7 is a sub-flowchart of step 244 of the method of FIG. 6;
FIG. 8 is a schematic diagram of the moving object displayed on the display terminal in the method shown in FIG. 7;
FIG. 9 is a flow chart of another method for detecting a high altitude parabolic event provided by embodiments of the present invention;
FIG. 10 is a schematic structural diagram of an apparatus for detecting high altitude parabolas according to an embodiment of the present invention;
fig. 11 is a schematic hardware structure diagram of a floor intelligent monitoring system for executing the method for detecting the high altitude parabola according to the embodiment of the invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It should be noted that, if not conflicted, the various features of the embodiments of the invention may be combined with each other within the scope of protection of the present application. Additionally, while functional block divisions are performed in apparatus schematics, with logical sequences shown in flowcharts, in some cases, steps shown or described may be performed in sequences other than block divisions in apparatus or flowcharts. Further, the terms "first," "second," "third," and the like, as used herein, do not limit the data and the execution order, but merely distinguish the same items or similar items having substantially the same functions and actions.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Please refer to fig. 1a, which is a schematic diagram of an exemplary system structure applied to an embodiment of the method for detecting a high altitude parabolic event of the present invention. As shown in fig. 1a, the system architecture comprises: image acquisition equipment 10, detection equipment 20 and building body 30.
The image capturing device 10 is communicatively connected to the detecting device 20, wherein the communication connection may be a network connection, and may include various connection types, such as a wired connection, a wireless connection, or a fiber optic cable. The detection device 20 can acquire the image shot by the image acquisition device 10 or the image in the recorded video, analyze whether the moving object in the image is a high-altitude parabolic event, and send out warning information when the high-altitude parabolic event is monitored. The detection device 20 has an image recognition function, a calculation and analysis function, and an information output function, and can acquire and analyze images such as videos or photos, and determine whether to output corresponding warning information according to an analysis result.
The image capturing apparatus 10 is a device capable of capturing an image, where the image may be a video or a picture, and the video is taken as an example in the embodiment of the present invention. The image capturing device 10 may be a device for capturing images, such as a camera, a camera phone, a video recorder, a video camera, or a night vision device, and the image capturing device 10 may be in communication with the detection device 20 to transmit the images captured in real time to the detection device 20. The image captured by the image capturing device 10 includes the floor of the building 30. In this embodiment, the image capture device 10 is being aimed at a floor to obtain real-time video data of the floor. It will be appreciated that in some embodiments, in order to protect the privacy of the resident residing in the building, the image capture device 10 is mounted to the side of the building 30, as shown in fig. 1b, to capture real-time video data of the floor, while avoiding the daily life of the resident. In some embodiments, as shown in fig. 1c, the image capturing apparatus 10 is fixed to the side of the building 30 by a mounting rod 40, the image capturing apparatus 10 can capture real-time video data of the floor, and the image capturing apparatus 10 can be well fixed to reduce lens jumping.
In some embodiments, as shown in fig. 2a, the image capturing device 10 may be multiple, and multiple image capturing devices 10 may capture video data of one floor in different areas, or capture video data of respective corresponding floors. Each image acquisition device 10 is in communication connection with a corresponding detection device 20, the plurality of detection devices 20 are in communication connection with a network switch 50, the network switch 50 is connected with a server 80, a storage device 60 and a display terminal 70, and the server 80 may be a cloud server. Wherein, the communication connection can be wireless connection such as wifi, 4G or 5G. The plurality of detection devices 20 respectively send the detection results and the recorded real-time video data to the network switch 50, the network switch 50 uploads the detection results to the server 80, sends the real-time video data to the storage device 60 for storage, and displays the detection results and/or the real-time video data in the display terminal 70, so that a user can simultaneously view the monitoring conditions of the whole floor or a plurality of floors and corresponding alarm information, and the high-altitude parabolic events can be effectively traced. It is understood that the display terminal 70 may be a computer, a mobile phone, an ipad, or the like.
In some implementations, as shown in fig. 2b, the detection device 20 is integrated inside the image capture device 10, forming a device that integrates capturing and computational analysis. In some embodiments, as shown in fig. 2c, one detection device 20 corresponds to a plurality of image capturing devices 10, i.e. the detection device 20 can process real-time video data of a plurality of image capturing devices 10 simultaneously. It is to be understood that the detecting device 20 may also be a storage medium storing a computing program, and is integrated in the storage device 60 or the display terminal 70, which is well known in the art, and can be adjusted and set by those skilled in the art according to the needs of the actual situation, and will not be described herein.
An embodiment of the present invention provides a method for detecting high altitude parabolic events, which can be executed by the above-mentioned detection apparatus 20, and refer to fig. 3, which shows a flowchart of a method for detecting high altitude parabolic events according to the above-mentioned system structure, and the method includes but is not limited to the following steps:
210: acquiring a frame image from a real-time video of a floor;
the floor refers to a wall surface of the building body, wherein the wall surface comprises a window from which objects may fall, i.e. there is a risk of high altitude parabolic motion. The real-time video of the floor is recorded in real time by the image acquisition equipment in the application system, and the frame image comprises image information of the floor. The number of frames of the frame images included in the real-time video of the floor within a certain time is the same, for example, 25 frames per 1 second, and the like, and can be specifically set by those skilled in the art according to actual situations. It is to be understood that for the accuracy of the detection, in some embodiments, whether a high-rise scene exists or not, that is, whether a high-rise is included in the frame image or not, may be detected from the frame image, and the subsequent steps may be performed in the case that a high-rise exists.
Step 220: detecting whether a moving target exists according to the frame image; if so, step 230 is performed.
Typically, the frame images are static, i.e. no pixel changes between successive frame images, no high altitude parabolic events occur. If a moving target appears, which indicates that there is a risk of a high-altitude parabolic event, the moving target needs to be followed further to detect whether the moving target belongs to the high-altitude parabolic event or whether the moving target is a floating object without harm, such as a flying bird or a fallen leaf. Therefore, before the high-altitude parabolic event is identified, whether a moving target exists or not needs to be detected, effective screening can be performed, high-altitude parabolic event identification calculation is avoided for each frame of image, and therefore the calculation amount can be reduced. Wherein the moving object is an object in a moving state in the frame image. When the moving object occurs, a pixel change occurs between the successive frame images. In some embodiments, the inter-frame difference method is used to detect whether the moving object exists, specifically, referring to fig. 4, the step 220 specifically includes:
step 221: and performing first image preprocessing on the frame image.
In order to improve the image recognition accuracy, before a moving object is recognized, first image preprocessing is performed on the frame image. The first image pre-processing comprises at least one of:
and image conversion, which is to convert pixels in the frame image, for example, to convert an RGB space to a grayscale space or an HSV space, so that the amount of raw data of the frame image can be reduced, and the amount of calculation is reduced in subsequent processing.
And smoothing the image, wherein wide areas, low-frequency components and trunk parts in the frame image can be highlighted, or image noise and interference high-frequency components are suppressed, so that obvious clutter signals can be filtered.
And image sharpening, namely reducing blurring in the frame image by enhancing high-frequency components, enhancing detail edges and contours of the frame image, enhancing gray contrast and facilitating identification and processing of a target at a later stage. In some embodiments, the image sharpening process may be performed using a differentiation method and a high-pass filtering method.
The three image preprocessing methods are well known to those skilled in the art, and can be selected by those skilled in the art according to the needs of actual situations, and the processing method corresponding to the first image preprocessing is determined.
It should be noted that the "first" does not limit the data and execution order, and only distinguishes the same item or similar items having substantially the same function and action, that is, the "first image preprocessing" is different from the "second image preprocessing".
Step 222: and determining whether the moving target exists or not by adopting an interframe difference method.
When a moving object exists in the real-time video, the gray scales of different frame images can be different, and whether the moving object exists can be determined through the gray scale difference. In some embodiments, the inter-frame differencing method is an adjacent frame differencing method or an adjacent three-frame differencing method.
And for the adjacent frame difference method, directly carrying out difference operation on two adjacent frames of images in the real-time video, and comparing an absolute value of the difference operation with a preset threshold value to determine whether a difference image between the two adjacent frames of images is a foreground or a background, wherein if the difference image is the foreground, the difference image represents that a moving target exists in the current frame of image, and if the difference image is the background, the difference image represents that no moving target exists in the current frame of image. The following formula is shown in detail:
d is a difference image between two consecutive frame images, I (T) and I (T-1) are frame images at T and T-1, respectively, T is a preset threshold selected during binarization of the difference image, D ═ 1 represents a foreground, and D ═ 0 represents a background. Wherein the foreground corresponds to moving objects and the background corresponds to stationary or very slow moving objects
And for the adjacent three-frame difference method, performing gray level difference on the previous two frames of images, performing gray level difference on the current frame of image and the previous frame of image, and performing logic AND judgment according to the result of the two gray level differences to obtain a difference result. The following formula is shown in detail:
D＝D1&D2
wherein D1 is the gray difference between the previous two frames, D2 is the gray difference between the current frame and the previous frame, and D is the difference image. And I (T +1), I (T) and I (T-1) are frame images at the moments of T +1, T and T-1 respectively, T is a preset threshold value selected during binarization of the differential image, D-1 represents a foreground, and D-0 represents a background. Wherein the foreground corresponds to moving objects and the background corresponds to stationary or very slow moving objects
For a stationary object, such as a floor, there is no change in gray scale, the gray scale difference is 0 in the region corresponding to the stationary object, and the gray scale difference is not 0 in the region corresponding to the moving object. The preset threshold T is a critical value of the gray scale difference, and can be set by a person skilled in the art through experiments or experience.
To verify the moving object, in some embodiments, referring to fig. 5, the method further includes:
step 223: and carrying out second image preprocessing on the frame image with the gray difference.
The frame image with the gray difference comprises the moving object. And performing second image preprocessing on the frame image with the gray difference, namely performing second image preprocessing on the frame image with the moving target, wherein the second image preprocessing comprises Gaussian filtering and/or binarization and the like so as to filter out fine particle interference.
Step 224: and marking the connected regions in the frame images with the gray level difference.
The connected region is an image region which is formed by pixel points with the same pixel value and adjacent positions in the frame image. Since the corresponding areas of the moving object in the frame image have the same pixel value, the connected areas in the frame image with the gray level difference are marked, and the shape and the size of the moving object can be determined.
Step 225: and verifying the moving target according to the form and the size of the communication area.
Verifying the moving object refers to verifying whether the moving object is an actual moving object, i.e. performing further verification on the moving object determined in step 222. Whether the moving target is a real moving target or not can be verified according to the shape and size data of the connected region so as to eliminate interference. In some embodiments, the pixel data of the connected region may be input into a preset two-classification model to obtain whether the moving object is a real moving object, wherein the preset two-classification model may be a classification model such as a logistic regression or an SVM.
Step 230: and acquiring the motion trail of the motion target.
The motion track of the moving target refers to a track of the moving target in the real-time video, and can be represented as a track formed by a coordinate point sequence in a three-dimensional space or a track formed by a coordinate point sequence in a two-dimensional space. From this, the illustrated motion trajectory has a temporal attribute and a positional attribute. In some embodiments, the three-dimensional coordinates of the moving object in the two-dimensional image can be reconstructed through three-dimensional space modeling, and a plurality of three-dimensional coordinates of the moving object are connected to form a motion track of the moving object. In some embodiments, the position change of the moving object in the time-continuous multi-frame images can be calculated through the position of the moving object in each frame image, and the motion track vector, i.e. the motion track, can be determined according to the position change.
Step 240: and determining whether the moving target is a high-altitude parabolic event or not according to the motion track.
Since the high altitude parabola belongs to the free falling body motion with a certain speed in the horizontal direction, the motion track of the high altitude parabola should accord with the kinematics law of the free falling body, for example, the downward acceleration exists in the vertical direction, the displacement in unit time is larger and larger, the displacement of the horizontal pixel coordinate is smaller, and the like. Therefore, whether the moving target is a high altitude parabolic event or not can be determined according to the motion track. In some embodiments, the whole motion trajectory vector of the moving object is input into a trained classification model for recognition to determine whether the event is a high altitude parabolic event, which in this embodiment requires a lot of computation and takes a long time.
In order to identify the high altitude parabolic event more quickly and in preparation, referring to fig. 6, the step 240 specifically includes:
step 241: calculating a time interval from the detection of the moving object in the real-time video to the disappearance of the moving object in the real-time video as a moving time of the moving object.
The motion time refers to a time interval from the detection of the moving object in the real-time video to the disappearance of the moving object in the real-time video. Specifically, since the number of frames of the frame images included in the real-time video of the floor in a unit time is the same, for example, 25 frames per second, the moving time of the moving object appearing in the real-time video can be obtained by calculating the number of consecutive frames of the frame images including the moving object. For example, when a moving object is detected, images are extracted every 5 frames to form an image sequence (P0, P1, P2, P3,, PN), the frame images in the image sequence are sequentially identified to detect whether the moving object is included, the number of continuous frames of the frame images including the moving object in the image sequence is counted, and the product of the number of continuous frames of the frame images including the moving object and the number of interval frames and the interval time between each frame in the video is the moving time. The images are extracted by spacing the frame number, the moving target is identified, the identification frequency can be reduced, and the calculation time can be shortened.
Step 242: and if the movement time is less than the preset time, determining that the object is not a high-altitude parabolic event.
When the motion time of the motion target is less than the preset time, the occurrence time of the motion target in the real-time video is short, and the kinematics rule is not satisfied, so that the situation that the motion target is not a high-altitude parabolic event can be determined. On one hand, objects passing through instantly, such as birds flying quickly, can be effectively eliminated, and the calculation of the motion track of the non-high-altitude parabolic events can be avoided; on the other hand, considering the movement time, the accuracy of detection can be increased. It is noted that the preset time can be set by a person skilled in the art according to experiments or experience.
Step 243: and if the motion time is greater than or equal to the preset time, acquiring the motion track of the moving target within the preset time.
And if the movement time is greater than or equal to the preset time, further acquiring the movement track of the moving target within the preset time so as to carry out the next step.
Step 244: and determining whether the moving target is a high-altitude parabolic event or not according to the moving track of the moving target in the preset time.
When the motion track of the moving target in the preset time accords with the kinematics law of free fall, determining the moving target to be a high-altitude parabolic event; and when the motion trail of the moving target in the preset time does not conform to the kinematics rule of the free falling body, determining that the moving target is not a high-altitude parabolic event. The motion track of the moving target in the preset time is used as data for recognition, so that the data volume is small, the recognition speed is high, and the recognition accuracy is not influenced.
In some embodiments, referring to fig. 7, the step 244 specifically includes:
step 2441: and extracting frame images according to a preset interval frame number in the preset time to generate an image sequence.
The preset time includes consecutive multi-frame images, and frame images are extracted by a preset interval frame number, for example, the preset interval frame number is 5, that is, one frame image is extracted every 5 frames, an image sequence (P0, P1, P2, P3, P4, P5,, PM) is generated, wherein 5 frames are extracted between the image P0 and the image P1, 5 frames are extracted between the image P1 and the image P2, and so on, and M frame images are extracted within the preset time.
Step 2442: respectively calculating the vertical pixel coordinate displacement and the horizontal pixel coordinate displacement of the moving target in each two adjacent frames of images according to the image sequence so as to respectively obtain a vertical pixel coordinate displacement sequence and a horizontal pixel coordinate displacement sequence;
and calculating the coordinates of the moving object in each image according to the image sequence through an image recognition algorithm. Further, a vertical pixel coordinate displacement and a horizontal pixel coordinate displacement of the moving object in each adjacent two frames of images in the image sequence are respectively calculated, so that a vertical pixel coordinate displacement sequence (Y1, Y2, Y3, Y4,, YM) and a horizontal pixel coordinate displacement sequence (X1, X2, X3, X4, XM) can be respectively obtained, where Y1 is a displacement in a vertical direction when the moving object moves from a location in the image P0 to a location in the image P1, and X1 is a displacement in a horizontal direction when the moving object moves from a location in the image P0 to a location in the image P1; y2 is the displacement in the vertical direction when the moving object moves from the location in image P1 to the location in image P2, X2 is the displacement in the horizontal direction when the moving object moves from the location in image P1 to the location in image P2, and so on. It is understood that when the moving object is a parabolic event, the vertical pixel coordinate displacement sequence and the horizontal pixel coordinate displacement sequence thereof should also satisfy the free-fall kinematics law.
Step 2443: and judging whether the vertical pixel coordinate displacement in the vertical pixel coordinate displacement sequence is in the gravity direction and is gradually increased, if so, executing a step 2444.
When the moving object handles free-fall motion, its displacement per unit time in the vertical direction gradually increases due to the presence of gravitational acceleration, and the direction is the direction of gravity, i.e. does not extend upwards. Therefore, if the vertical pixel coordinate displacement in the vertical pixel coordinate displacement sequence does not satisfy the law of gradual increase and gravity direction, it is determined that the event is not a high altitude parabolic event. If the vertical pixel coordinate displacement in the vertical pixel coordinate displacement sequence gradually increases and the direction is the gravity direction, it indicates that there is a possibility of a high altitude parabolic event, and then step 2444 is further performed.
Step 2444: and judging whether the horizontal pixel coordinate displacement which is greater than or equal to a preset threshold value exists in the horizontal pixel coordinate displacement sequence, if not, executing a step 2447.
Because only the initial speed exists in the horizontal direction and no acceleration exists, under the condition that the initial speed of throwing is constant, the initial speed does not deviate greatly in the unit time in the horizontal direction. Therefore, whether the horizontal pixel coordinate displacement which is larger than or equal to the preset threshold value exists in the horizontal pixel coordinate displacement sequence or not is judged, if not, the situation that only the initial speed exists in the horizontal direction and the acceleration in the horizontal direction does not exist is shown, the law of free fall kinematics is met, and therefore the high-altitude parabolic event can be determined. It will be appreciated that the predetermined horizontal pixel coordinate displacement may be determined experimentally or empirically by one skilled in the art.
In this embodiment, the high altitude parabolic event is determined according to whether the vertical pixel coordinate displacement, the horizontal pixel coordinate displacement and the motion direction of the moving target in the preset time meet the free fall kinematics rule, on one hand, the calculated amount can be greatly reduced, the recognition speed is improved, on the other hand, the motion track is decomposed into three aspects of the vertical pixel coordinate displacement, the horizontal pixel coordinate displacement and the motion direction, rules are searched from the three aspects, and the high altitude parabolic event can be accurately recognized and tracked.
Step 2447: and determining as a high altitude parabolic event.
In some embodiments, a warning alert is sent when a high altitude parabolic event is detected. Wherein the warning reminder may be at least one of voice, light, or text on the display terminal 70. It can be understood that the graphics on the display terminal 70 may include a throwing track of the moving object 31, as shown in fig. 8, so that a user located in front of the display terminal 70 may clearly trace back the throwing position of the moving object 31, thereby facilitating finding a person responsible for the high-altitude parabolic event, and on the other hand, may prompt a pedestrian to avoid quickly, thereby avoiding causing injury to personnel.
In some embodiments, before step 2447, the method further comprises:
step 2445: and if the horizontal pixel coordinate displacement which is greater than or equal to a preset threshold value does not exist in the horizontal pixel coordinate displacement sequence, adopting a neural network identification algorithm to identify the type of the moving target.
Step 2446: and determining whether the moving target is a high-altitude parabolic event or not according to the type of the moving target.
Intercepting the area image where the moving target is located in the moving track, inputting the area image into a neural network recognition algorithm, and obtaining the category of the area image, so as to distinguish whether the moving target is an interferent such as fallen leaves, flying birds, flying insects, rainwater, hail, cloud and the like. And combining the results, if the motion trail satisfies the free-fall kinematics rule and the motion target is not an interferent such as fallen leaves, flying birds, flying insects, rainwater, hail, clouds and the like, determining that the motion trail is a high-altitude parabolic event. It is worth mentioning that the neural network is an existing image recognition model.
In the embodiment, a frame image is obtained from a real-time video of a floor, whether a moving target exists or not is detected according to the frame image, a moving track of the moving target is obtained under the condition that the moving target exists, a free-fall kinematics law is combined according to the moving track, a high-altitude parabolic event is identified, the high-altitude parabolic event can be accurately identified and tracked, and the difference between scenes such as 'bird flying over' or 'leaf flying' and the like and the high-altitude parabolic event is distinguished.
In some embodiments, when detecting the floor correspondence, an abnormal condition is also detected, specifically, referring to fig. 9, the method further includes:
step 250: and determining a candidate frame containing the moving target in the frame image according to a preset target detection model.
The target detection model can solve the classification problem of the detected target category and the regression problem of the predicted target frame position, two types of target detection algorithms, namely one-stage and two-stage, can be adopted, and a person skilled in the art can select a proper target detection algorithm to train the target detection model according to the actual situation.
The two-stage target detection algorithm firstly generates a series of candidate frames serving as samples, and carries out sample classification and positioning through a convolutional neural network, namely firstly carrying out region extraction on a picture, selecting a region with an object as a candidate picture, simultaneously inhibiting a large number of negative samples such as background and the like, then using the candidate picture as a subgraph, and carrying out classification and positioning of specific classes on the subgraphs. Thus, a candidate frame in the frame image that contains the moving object may be determined. It is understood that the candidate frame containing the moving object should be larger than the area of the moving object, for example, the candidate frame containing the moving object is twice the area of the moving object.
Step 260: and taking the image contained in the candidate frame as the motion target image.
The image contained in the candidate frame is the moving target image, and the candidate frame only comprises the moving target, so that the subsequent identification is not interfered, and the identification accuracy can be improved.
Step 270: and inputting the moving target image into a preset convolutional neural network model, and identifying the type of the moving target.
The preset convolutional neural network model is a convolutional neural network model which is trained and learned in advance through a large amount of image data containing multiple types of articles, and the types of the articles can be identified. Therefore, the moving target image is input into a preset convolutional neural network model, and the type of the moving target can be identified.
Step 280: and judging whether the type of the moving target belongs to an abnormal object, if so, executing step 290.
The abnormal object is an object which is positioned and installed on the floor and is in a fixed state for a long time, such as an air conditioner hanging machine, a wall surface and wall surface decoration, an advertisement, a window and the like. When the type of the moving target belongs to the abnormal object, the fixed object is moved, for example, the air conditioner is loosened and has a falling tendency, a broken window is stolen, and the like. In this case, the first warning reminder corresponding to the type of the moving object is sent at the first time, that is, step 290 is executed, so that the loss can be recovered. It is understood that the first warning reminder may be a voice, a light, or a graphic corresponding to the type of the moving object, for example, when the air conditioner is not in motion, the user is reminded to handle the moving object in time by displaying the air conditioner in motion and the position of the air conditioner in a voice or an image.
Step 290: and sending a first warning prompt corresponding to the type of the moving target.
In this embodiment, the first warning prompt is sent out in time by monitoring the abnormal object, so that the user can conveniently stop the danger in time.
An embodiment of the present invention further provides an apparatus for detecting a high altitude parabolic event, please refer to fig. 10, which illustrates a structure of the apparatus for detecting a high altitude parabolic event according to an embodiment of the present application, where the apparatus 300 includes: a first acquisition module 310, a detection module 320, a second acquisition module 330, and a first determination module 340.
The first obtaining module 310 is configured to obtain a frame image from a real-time video of a floor. A detecting module 320, configured to detect whether a moving object exists according to the frame image. A second obtaining module 330, configured to obtain a motion trajectory of the moving object if the moving object exists. The first determining module 340 is configured to determine whether the moving object is a high altitude parabolic event according to the motion trajectory.
In some embodiments, the first determining module 340 further includes a calculating unit, a first determining unit, an obtaining unit, and a second determining unit (not shown). The calculation unit is used for calculating a time interval from the detection of the moving target in the real-time video to the disappearance of the moving target in the real-time video as the moving time of the moving target. The first determination unit is used for determining that the high-altitude parabolic event does not occur if the movement time is less than a preset time. The obtaining unit is used for obtaining the motion track of the motion target within the preset time if the motion time is greater than or equal to the preset time. The second determining unit is used for determining whether the moving target is a high-altitude parabolic event or not according to the moving track of the moving target in the preset time.
In some embodiments, the second determining unit is specifically configured to extract frame images according to a preset number of frame intervals within the preset time, and generate an image sequence; respectively calculating the vertical pixel coordinate displacement and the horizontal pixel coordinate displacement of the moving target in each two adjacent frames of images according to the image sequence so as to respectively obtain a vertical pixel coordinate displacement sequence and a horizontal pixel coordinate displacement sequence; judging whether the vertical pixel coordinate displacement in the vertical pixel coordinate displacement sequence is in the gravity direction and gradually increases; if so, judging whether horizontal pixel coordinate displacement which is greater than or equal to a preset threshold value exists in the horizontal pixel coordinate displacement sequence; and if the horizontal pixel coordinate displacement which is greater than or equal to a preset threshold value does not exist in the horizontal pixel coordinate displacement sequence, determining that the moving target is a high-altitude parabolic event.
In some embodiments, the second determining unit is further specifically configured to identify the type of the moving object by using a neural network identification algorithm if the horizontal pixel coordinate displacement greater than or equal to a preset threshold does not exist in the horizontal pixel coordinate displacement sequence; and determining whether the moving target is a high-altitude parabolic event or not according to the type of the moving target.
In some embodiments, the detection module 320 is specifically configured to perform a first image preprocessing on the frame image; and determining whether the moving target exists or not by adopting an interframe difference method. The inter-frame difference method is an adjacent frame difference method or an adjacent three-frame difference method.
In some embodiments, the detecting module 320 is further specifically configured to perform a second image preprocessing on the frame image with the gray level difference; marking a connected region in the frame image with the gray level difference; and verifying the moving target according to the form and the size of the communication area.
In some embodiments, the apparatus 300 further includes a second determination module 350, an image generation module 360, an identification module 370, a determination module 380, and a first alert module 390.
The second determining module 350 is configured to determine, according to a preset target detection model, a candidate frame containing the moving target in the frame image. The image generation module 360 is configured to use the image contained in the candidate frame as the moving object image. The identification module 370 is configured to input the moving object image into a preset convolutional neural network model, and identify the type of the moving object. The determining module 380 is configured to determine whether the type of the moving target belongs to an abnormal object. The first warning module 390 is configured to send a first warning prompt corresponding to the category of the moving object when the category of the moving object belongs to an abnormal object.
It is to be appreciated that in some embodiments, the apparatus 300 further comprises a second alert module 391 for sending a second warning alert when a high altitude parabolic event is detected.
In this embodiment, a frame image is obtained from a real-time video of a floor through the first obtaining module 310, the detecting module 320 detects whether a moving target exists according to the frame image, the second obtaining module 330 obtains a motion track of the moving target under the condition that the moving target exists, and the first determining module 340 identifies a high-altitude parabolic event according to the motion track and by combining with a free-fall kinematics law, can accurately identify and track the high-altitude parabolic event, and distinguishes the difference between scenes such as 'birds flying over' or 'leaves flying' and the like and the 'high-altitude parabolic'.
The embodiment of the present invention further provides a floor intelligent monitoring system 400, please refer to fig. 11, which includes an image obtaining module 410 for obtaining frame images from a real-time video of a floor, and at least one processor 420 connected to the image obtaining module 410; and a memory 430, such as one processor in fig. 9, communicatively coupled to the at least one processor 420.
The memory 430 stores instructions executable by the at least one processor 420 to enable the at least one processor 420 to perform the method of detecting high altitude parabolic events described above in fig. 3-9. The processor 420 and the memory 430 may be connected by a bus or other means, and fig. 11 illustrates the connection by a bus as an example.
Memory 430, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules of the method for detecting high altitude parabolic events in embodiments of the present application, for example, the various modules shown in fig. 10. The processor 420 executes various functional applications of the server and data processing by executing nonvolatile software programs, instructions and modules stored in the memory 430, namely, implements the method for detecting the high altitude parabolic event in the above method embodiment.
The memory 430 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of a device for detecting a high altitude parabolic event, and the like. Further, the memory 430 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 430 optionally includes memory remotely located from the processor, and these remote memories may be connected to the means for detecting high altitude parabolic events via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 430, and when executed by the one or more processors 420, perform the method for detecting high altitude parabolic events in any of the method embodiments described above, e.g., perform the method steps of fig. 3-9 described above, to implement the functions of the modules in fig. 10.
The product can execute the method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the methods provided in the embodiments of the present application.
An embodiment of the present invention further provides a non-transitory computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by an electronic device, the electronic device is caused to perform the method for detecting a high altitude parabolic event in any one of the method embodiments, for example, the method steps in fig. 3 to 9 above are executed, so as to implement the functions of the modules in fig. 10.
In the embodiment, a frame image is obtained from a real-time video of a floor, whether a moving target exists or not is detected according to the frame image, a moving track of the moving target is obtained under the condition that the moving target exists, a free-fall kinematics law is combined according to the moving track, a high-altitude parabolic event is identified, the high-altitude parabolic event can be accurately identified and tracked, and the difference between scenes such as 'bird flying over' or 'leaf falling' and the like and the high-altitude parabolic event is distinguished.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; within the idea of the invention, also technical features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (11)
1. A method of detecting a high altitude parabolic event, comprising:
acquiring a frame image from a real-time video of a floor;
detecting whether a moving target exists according to the frame image;
if so, acquiring the motion track of the motion target;
and determining whether the moving target is a high-altitude parabolic event or not according to the motion track.
2. The method of claim 1, wherein the step of determining whether the moving object is a high altitude parabolic event according to the motion trajectory further comprises:
calculating a time interval from the detection of the moving object in the real-time video to the disappearance of the moving object in the real-time video as a moving time of the moving object;
if the motion time is less than the preset time, determining that the moving target is not a high-altitude parabolic event;
if the motion time is greater than or equal to the preset time, acquiring a motion track of the moving target within the preset time;
and determining whether the moving target is a high-altitude parabolic event or not according to the moving track of the moving target in the preset time.
3. The method according to claim 2, wherein the step of determining whether the moving object is a high altitude parabolic event according to the moving track of the moving object within the preset time further comprises:
extracting frame images according to a preset interval frame number within the preset time to generate an image sequence;
respectively calculating the vertical pixel coordinate displacement and the horizontal pixel coordinate displacement of the moving target in each two adjacent frames of images according to the image sequence so as to respectively obtain a vertical pixel coordinate displacement sequence and a horizontal pixel coordinate displacement sequence;
judging whether the vertical pixel coordinate displacement in the vertical pixel coordinate displacement sequence is in the gravity direction and gradually increases;
if so, judging whether horizontal pixel coordinate displacement which is greater than or equal to a preset threshold value exists in the horizontal pixel coordinate displacement sequence;
and if the horizontal pixel coordinate displacement which is greater than or equal to a preset threshold value does not exist in the horizontal pixel coordinate displacement sequence, determining that the moving target is a high-altitude parabolic event.
4. The method of claim 3, further comprising, prior to the step of determining that the moving object is a high altitude parabolic event:
if the horizontal pixel coordinate displacement which is greater than or equal to a preset threshold value does not exist in the horizontal pixel coordinate displacement sequence, adopting a neural network identification algorithm to identify the type of the moving target;
and determining whether the moving target is a high-altitude parabolic event or not according to the type of the moving target.
5. The method of claim 1, wherein the step of detecting whether the moving object exists according to the real-time video frame image further comprises:
performing first image preprocessing on the frame image;
and determining whether the moving target exists or not by adopting an interframe difference method.
6. The method of claim 5, wherein the inter-frame differencing method is an adjacent frame differencing method or an adjacent three-frame differencing method.
7. The method of claim 6, further comprising:
performing second image preprocessing on the frame image with the gray difference;
marking a connected region in the frame image with the gray difference;
and verifying the moving target according to the form and the size of the communication area.
8. The method of claim 1, further comprising:
when a high altitude parabolic event is detected, a warning alert is sent.
9. An apparatus for detecting a high altitude parabolic event, comprising:
the first acquisition module is used for acquiring a frame image from a real-time video of a floor;
the detection module is used for detecting whether a moving target exists or not according to the frame image;
the second acquisition module is used for acquiring the motion track of the moving target if the moving target exists;
and the first determination module is used for determining whether the high-altitude parabolic event exists according to the motion track.
10. An intelligent floor monitoring system, comprising:
the image acquisition module is used for acquiring frame images from a real-time video of the floor;
at least one processor connected with the image acquisition module; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
11. A non-transitory computer-readable storage medium having stored thereon computer-executable instructions that, when executed by an electronic device, cause the electronic device to perform the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010817165.3A CN112016414A (en) | 2020-08-14 | 2020-08-14 | Method and device for detecting high-altitude parabolic event and intelligent floor monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010817165.3A CN112016414A (en) | 2020-08-14 | 2020-08-14 | Method and device for detecting high-altitude parabolic event and intelligent floor monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112016414A true CN112016414A (en) | 2020-12-01 |
Family
ID=73504444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010817165.3A Pending CN112016414A (en) | 2020-08-14 | 2020-08-14 | Method and device for detecting high-altitude parabolic event and intelligent floor monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112016414A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112509012A (en) * | 2020-12-14 | 2021-03-16 | 青岛聚好联科技有限公司 | Detection method of high-altitude object throwing |
| CN112634299A (en) * | 2020-12-22 | 2021-04-09 | 通号通信信息集团有限公司 | Remnant detection method for eliminating interference of winged insects |
| CN112733690A (en) * | 2020-12-31 | 2021-04-30 | 北京易华录信息技术股份有限公司 | High-altitude parabolic detection method and device and electronic equipment |
| CN112731369A (en) * | 2020-12-25 | 2021-04-30 | 上海为彪汽配制造有限公司 | High-altitude parabolic early warning method and system |
| CN112800846A (en) * | 2020-12-30 | 2021-05-14 | 深圳云天励飞技术股份有限公司 | High-altitude parabolic monitoring method and device, electronic equipment and storage medium |
| CN112926445A (en) * | 2021-02-24 | 2021-06-08 | 北京爱笔科技有限公司 | Parabolic behavior recognition method, model training method and related device |
| CN112991680A (en) * | 2021-04-27 | 2021-06-18 | 广州弘一信息科技股份有限公司 | Safety protection alarm system based on Internet of things |
| CN113033440A (en) * | 2021-03-31 | 2021-06-25 | 杭州海康威视系统技术有限公司 | Event alarm method, device, electronic equipment, storage medium and system |
| CN113034397A (en) * | 2021-03-30 | 2021-06-25 | 北京睿芯高通量科技有限公司 | Real-time multi-environment self-adaptive track automatic tracing high-altitude parabolic detection method |
| CN113052878A (en) * | 2021-03-30 | 2021-06-29 | 北京睿芯高通量科技有限公司 | Multi-path high-altitude parabolic detection method and system for edge equipment in security system |
| CN113065454A (en) * | 2021-03-30 | 2021-07-02 | 青岛海信智慧生活科技股份有限公司 | High-altitude parabolic target identification and comparison method and device |
| CN113139478A (en) * | 2021-04-27 | 2021-07-20 | 广东博智林机器人有限公司 | High-altitude parabolic detection method and device, electronic equipment and storage medium |
| CN113158926A (en) * | 2021-04-26 | 2021-07-23 | 广东博智林机器人有限公司 | High-altitude parabolic track distinguishing method, device, equipment and storage medium |
| CN113239802A (en) * | 2021-05-13 | 2021-08-10 | 上海汇焰智能科技有限公司 | Safety monitoring method, device, medium and electronic equipment |
| CN113438456A (en) * | 2021-08-26 | 2021-09-24 | 广州洛克韦陀安防科技有限公司 | Monitoring method and monitoring system for improving positioning accuracy of falling object |
| CN113822913A (en) * | 2021-11-25 | 2021-12-21 | 江西科技学院 | High-altitude parabolic detection method and system based on computer vision |
| CN113869166A (en) * | 2021-09-18 | 2021-12-31 | 沈阳帝信人工智能产业研究院有限公司 | Substation outdoor operation monitoring method and device |
| CN114202721A (en) * | 2021-11-19 | 2022-03-18 | 中科计算技术创新研究院 | Detection method of low-altitude aircraft |
| CN114339367A (en) * | 2021-12-29 | 2022-04-12 | 杭州海康威视数字技术股份有限公司 | Video frame processing method, device and equipment |
| CN114782490A (en) * | 2022-04-18 | 2022-07-22 | 盛视科技股份有限公司 | High-altitude parabolic detection method based on image, readable storage medium and detection device |
| CN114998794A (en) * | 2022-05-31 | 2022-09-02 | 天翼爱音乐文化科技有限公司 | High-altitude parabolic recognition method, system, device and storage medium |
| CN115082864A (en) * | 2022-07-25 | 2022-09-20 | 青岛亨通建设有限公司 | Building construction safety monitoring system |
| CN115294744A (en) * | 2022-07-29 | 2022-11-04 | 杭州海康威视数字技术股份有限公司 | Image display system, method, device and equipment |
| WO2023273010A1 (en) * | 2021-06-29 | 2023-01-05 | 深圳市商汤科技有限公司 | High-rise littering detection method, apparatus, and device, and computer storage medium |
| CN116994201A (en) * | 2023-07-20 | 2023-11-03 | 山东产研鲲云人工智能研究院有限公司 | Method for tracing and monitoring high-altitude parabolic objects and computing equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109309811A (en) * | 2018-08-31 | 2019-02-05 | 中建三局智能技术有限公司 | A kind of throwing object in high sky detection system based on computer vision and method |
| CN109614906A (en) * | 2018-12-03 | 2019-04-12 | 北京工业大学 | A kind of security system and security alarm method based on deep learning |
| CN109842787A (en) * | 2019-01-09 | 2019-06-04 | 武汉海慧技术有限公司 | A kind of method and system monitoring throwing object in high sky |
| CN110275220A (en) * | 2018-03-15 | 2019-09-24 | 阿里巴巴集团控股有限公司 | Detection method, the method for detecting position of target object, alarm method |
| CN110910415A (en) * | 2019-11-28 | 2020-03-24 | 重庆中星微人工智能芯片技术有限公司 | Parabolic detection method, device, server and computer readable medium |
| CN111260693A (en) * | 2020-01-20 | 2020-06-09 | 北京中科晶上科技股份有限公司 | Detection method of high-altitude object throwing |
| CN111401311A (en) * | 2020-04-09 | 2020-07-10 | 苏州海赛人工智能有限公司 | High-altitude parabolic recognition method based on image detection |
| CN111488799A (en) * | 2020-03-13 | 2020-08-04 | 安徽小眯当家信息技术有限公司 | Falling object identification method and system based on image identification |
-
2020
- 2020-08-14 CN CN202010817165.3A patent/CN112016414A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110275220A (en) * | 2018-03-15 | 2019-09-24 | 阿里巴巴集团控股有限公司 | Detection method, the method for detecting position of target object, alarm method |
| CN109309811A (en) * | 2018-08-31 | 2019-02-05 | 中建三局智能技术有限公司 | A kind of throwing object in high sky detection system based on computer vision and method |
| CN109614906A (en) * | 2018-12-03 | 2019-04-12 | 北京工业大学 | A kind of security system and security alarm method based on deep learning |
| CN109842787A (en) * | 2019-01-09 | 2019-06-04 | 武汉海慧技术有限公司 | A kind of method and system monitoring throwing object in high sky |
| CN110910415A (en) * | 2019-11-28 | 2020-03-24 | 重庆中星微人工智能芯片技术有限公司 | Parabolic detection method, device, server and computer readable medium |
| CN111260693A (en) * | 2020-01-20 | 2020-06-09 | 北京中科晶上科技股份有限公司 | Detection method of high-altitude object throwing |
| CN111488799A (en) * | 2020-03-13 | 2020-08-04 | 安徽小眯当家信息技术有限公司 | Falling object identification method and system based on image identification |
| CN111401311A (en) * | 2020-04-09 | 2020-07-10 | 苏州海赛人工智能有限公司 | High-altitude parabolic recognition method based on image detection |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112509012B (en) * | 2020-12-14 | 2022-12-09 | 青岛聚好联科技有限公司 | Detection method of high-altitude object throwing |
| CN112509012A (en) * | 2020-12-14 | 2021-03-16 | 青岛聚好联科技有限公司 | Detection method of high-altitude object throwing |
| CN112634299A (en) * | 2020-12-22 | 2021-04-09 | 通号通信信息集团有限公司 | Remnant detection method for eliminating interference of winged insects |
| CN112731369A (en) * | 2020-12-25 | 2021-04-30 | 上海为彪汽配制造有限公司 | High-altitude parabolic early warning method and system |
| CN112731369B (en) * | 2020-12-25 | 2024-03-01 | 上海为彪汽配制造有限公司 | High-altitude parabolic early warning method and system |
| CN112800846A (en) * | 2020-12-30 | 2021-05-14 | 深圳云天励飞技术股份有限公司 | High-altitude parabolic monitoring method and device, electronic equipment and storage medium |
| CN112733690A (en) * | 2020-12-31 | 2021-04-30 | 北京易华录信息技术股份有限公司 | High-altitude parabolic detection method and device and electronic equipment |
| CN112733690B (en) * | 2020-12-31 | 2024-02-20 | 北京易华录信息技术股份有限公司 | High-altitude parabolic detection method and device and electronic equipment |
| CN112926445A (en) * | 2021-02-24 | 2021-06-08 | 北京爱笔科技有限公司 | Parabolic behavior recognition method, model training method and related device |
| CN113034397A (en) * | 2021-03-30 | 2021-06-25 | 北京睿芯高通量科技有限公司 | Real-time multi-environment self-adaptive track automatic tracing high-altitude parabolic detection method |
| CN113052878A (en) * | 2021-03-30 | 2021-06-29 | 北京睿芯高通量科技有限公司 | Multi-path high-altitude parabolic detection method and system for edge equipment in security system |
| CN113034397B (en) * | 2021-03-30 | 2024-03-12 | 北京中科通量科技有限公司 | High-altitude parabolic detection method capable of realizing automatic tracing of self-adaptive track in multiple environments in real time |
| CN113065454A (en) * | 2021-03-30 | 2021-07-02 | 青岛海信智慧生活科技股份有限公司 | High-altitude parabolic target identification and comparison method and device |
| CN113052878B (en) * | 2021-03-30 | 2024-01-02 | 北京中科通量科技有限公司 | Multipath high-altitude parabolic detection method and system for edge equipment in security system |
| CN113033440A (en) * | 2021-03-31 | 2021-06-25 | 杭州海康威视系统技术有限公司 | Event alarm method, device, electronic equipment, storage medium and system |
| CN113158926A (en) * | 2021-04-26 | 2021-07-23 | 广东博智林机器人有限公司 | High-altitude parabolic track distinguishing method, device, equipment and storage medium |
| CN113158926B (en) * | 2021-04-26 | 2022-04-15 | 广东博智林机器人有限公司 | High-altitude parabolic track distinguishing method, device, equipment and storage medium |
| CN113139478A (en) * | 2021-04-27 | 2021-07-20 | 广东博智林机器人有限公司 | High-altitude parabolic detection method and device, electronic equipment and storage medium |
| CN112991680A (en) * | 2021-04-27 | 2021-06-18 | 广州弘一信息科技股份有限公司 | Safety protection alarm system based on Internet of things |
| CN113239802A (en) * | 2021-05-13 | 2021-08-10 | 上海汇焰智能科技有限公司 | Safety monitoring method, device, medium and electronic equipment |
| WO2023273010A1 (en) * | 2021-06-29 | 2023-01-05 | 深圳市商汤科技有限公司 | High-rise littering detection method, apparatus, and device, and computer storage medium |
| CN113438456A (en) * | 2021-08-26 | 2021-09-24 | 广州洛克韦陀安防科技有限公司 | Monitoring method and monitoring system for improving positioning accuracy of falling object |
| CN113869166A (en) * | 2021-09-18 | 2021-12-31 | 沈阳帝信人工智能产业研究院有限公司 | Substation outdoor operation monitoring method and device |
| CN114202721A (en) * | 2021-11-19 | 2022-03-18 | 中科计算技术创新研究院 | Detection method of low-altitude aircraft |
| CN113822913A (en) * | 2021-11-25 | 2021-12-21 | 江西科技学院 | High-altitude parabolic detection method and system based on computer vision |
| CN114339367B (en) * | 2021-12-29 | 2023-06-27 | 杭州海康威视数字技术股份有限公司 | Video frame processing method, device and equipment |
| CN114339367A (en) * | 2021-12-29 | 2022-04-12 | 杭州海康威视数字技术股份有限公司 | Video frame processing method, device and equipment |
| CN114782490A (en) * | 2022-04-18 | 2022-07-22 | 盛视科技股份有限公司 | High-altitude parabolic detection method based on image, readable storage medium and detection device |
| CN114782490B (en) * | 2022-04-18 | 2024-10-08 | 盛视科技股份有限公司 | Image-based high-altitude parabolic detection method, readable storage medium and detection device |
| CN114998794A (en) * | 2022-05-31 | 2022-09-02 | 天翼爱音乐文化科技有限公司 | High-altitude parabolic recognition method, system, device and storage medium |
| CN115082864A (en) * | 2022-07-25 | 2022-09-20 | 青岛亨通建设有限公司 | Building construction safety monitoring system |
| CN115294744A (en) * | 2022-07-29 | 2022-11-04 | 杭州海康威视数字技术股份有限公司 | Image display system, method, device and equipment |
| CN115294744B (en) * | 2022-07-29 | 2024-03-22 | 杭州海康威视数字技术股份有限公司 | Image display system, method, device and equipment |
| CN116994201A (en) * | 2023-07-20 | 2023-11-03 | 山东产研鲲云人工智能研究院有限公司 | Method for tracing and monitoring high-altitude parabolic objects and computing equipment |
| CN116994201B (en) * | 2023-07-20 | 2024-03-29 | 山东产研鲲云人工智能研究院有限公司 | Method for tracing and monitoring high-altitude parabolic objects and computing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112016414A (en) | Method and device for detecting high-altitude parabolic event and intelligent floor monitoring system | |
| Rakibe et al. | Background subtraction algorithm based human motion detection | |
| JP5325899B2 (en) | Intrusion alarm video processor | |
| US8744125B2 (en) | Clustering-based object classification | |
| KR101260847B1 (en) | Behavioral recognition system | |
| CN103093198B (en) | A kind of crowd density monitoring method and device | |
| CN111275910B (en) | Method and system for detecting border crossing behavior of escalator based on Gaussian mixture model | |
| CN104123544A (en) | Video analysis based abnormal behavior detection method and system | |
| KR20130032856A (en) | A method for monitoring a video and an apparatus using it | |
| WO2022078182A1 (en) | Throwing position acquisition method and apparatus, computer device and storage medium | |
| CN114639075B (en) | Method and system for identifying falling object of high altitude parabola and computer readable medium | |
| CN111881853A (en) | Method and device for identifying abnormal behaviors in oversized bridge and tunnel | |
| CN105930786A (en) | Abnormal behavior detection method for bank self-service hall | |
| KR101646000B1 (en) | Surveillance System And Method To Object And Area | |
| Malhi et al. | Vision based intelligent traffic management system | |
| CN112270253A (en) | High-altitude parabolic detection method and device | |
| CN108830161B (en) | Smog identification method based on video stream data | |
| KR101454644B1 (en) | Loitering Detection Using a Pedestrian Tracker | |
| Qureshi et al. | Highway traffic surveillance over uav dataset via blob detection and histogram of gradient | |
| CN113194249A (en) | Moving object real-time tracking system and method based on camera | |
| JP6275022B2 (en) | Image monitoring device | |
| KR101154350B1 (en) | Multiple Images Processing system using Detection of Objects and segmenting - recognizing of High- resolution Image and there of. | |
| Landabaso et al. | Robust tracking and object classification towards automated video surveillance | |
| Mishra et al. | Human motion detection and video surveillance using MATLAB | |
| Borkar et al. | Real time abandoned bag detection using OpenCV |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201201 |
|
| RJ01 | Rejection of invention patent application after publication |