US20090237508A1 - Method and apparatus for providing immersive surveillance - Google Patents
Method and apparatus for providing immersive surveillance Download PDFInfo
- Publication number
- US20090237508A1 US20090237508A1 US12/404,261 US40426109A US2009237508A1 US 20090237508 A1 US20090237508 A1 US 20090237508A1 US 40426109 A US40426109 A US 40426109A US 2009237508 A1 US2009237508 A1 US 2009237508A1
- Authority
- US
- United States
- Prior art keywords
- scene
- view
- model
- video
- display
- 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.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/10—Geometric effects
- G06T15/20—Perspective computation
- G06T15/205—Image-based rendering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/006—Mixed reality
-
- 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
- G06T7/251—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19608—Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19639—Details of the system layout
- G08B13/19641—Multiple cameras having overlapping views on a single scene
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19678—User interface
- G08B13/19691—Signalling events for better perception by user, e.g. indicating alarms by making display brighter, adding text, creating a sound
- G08B13/19693—Signalling events for better perception by user, e.g. indicating alarms by making display brighter, adding text, creating a sound using multiple video sources viewed on a single or compound screen
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- 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
Definitions
- the present invention generally relates to surveillance systems and, more particularly, relates to a method and apparatus for providing immersive surveillance.
- a surveillance or visualization display typically to allow a user to monitor or observe a scene with full awareness of the situation within the scene.
- Typical surveillance or visualization systems present video to a user from more than one camera on a single display. Such a display allows the user to observe different parts of the scene, or to observe the same part of the scene from different viewpoints.
- a typical surveillance display for example, has 16 videos of a scene shown in a 4 by 4 grid on a monitor. Each video is usually labeled by a fixed textual annotation displayed under the video segment to identify the image. For example, the text “lobby” or “front entrance” may be shown. If an event deserving attention is observed in one particular video, then the label can be used to locate the activity in the scene.
- an event deserving attention occurs in one particular video, then the user does not know how the activity relates to other locations in the scene without referring to or remembering a map or 3D model of the scene. For example, if activity is observed near “elevator 1” and the user knows that a guard is currently at “stairwell 5”, then without a map or 3D model, the user will not know if the guard is very close or very far from the activity in order to intervene.
- the process of referring to a map or 3D model either on paper or on a computer is typically time-consuming and error-prone since a human is involved in the association of the camera view to the map or model.
- the process of remembering a map or 3D model is also error-prone, and typically impossible when large numbers of cameras are used or if the site is large.
- the user can remember the orientation (pointing direction) of the camera with respect to a fixed coordinate system (for example, the compass directions).
- the user can recognize landmarks in the video and can use the landmarks to determine the approximate orientation of the camera with respect to a fixed coordinate system by remembering or referring to a map or 3D model of the scene.
- These two methods of predicting the new location of activity are error-prone, since typically the views from cameras are shown with respect to many different arbitrary coordinate systems that vary widely from camera to camera depending on how each camera was mounted during installation. As more cameras are added to the system, the more difficult it is for the user to remember their orientations or to recognize the landmarks in the scene. In addition, some parts of the scenes may contain no distinguishing landmarks at all.
- the resolution of each video has to be reduced in order to fit them into a display. This makes it difficult to observe the details of any event deserving attention in the video.
- the current solution to this problem is either to have an additional display that shows one selected video at high resolution, or to switch a single display between the view showing multiple reduced resolution videos and a view showing a single video at high resolution.
- the problem with this approach is that the user will miss any activity that may be occurring in other videos while they are focusing on the single high-resolution video.
- the present invention is a method and apparatus for providing immersive surveillance wherein a remote user may monitor a scene using a variety of imagery sources that are rendered upon a three-dimensional model to provide a three-dimensional contextual view of the scene.
- the surveillance system comprises a plurality of cameras supplying video and an image processor for applying the videos to a three dimensional (3D) model of the scene.
- the rendered model/video combination provides a 3D contextual view of the scene in which the user can be immersed.
- the user may dynamically select a specific view to be displayed from the contextual model, perform a virtual walk through of the scene, identify moving objects and select the best view of those moving objects, and so on.
- FIG. 1 depicts a high level block diagram of the present invention
- FIG. 2 depicts a detailed block diagram of the surveillance system in accordance with the present invention
- FIG. 3 depicts a flow chart of the operation of the present invention
- FIG. 4 depicts a process for identifying moving objects in accordance with the present invention
- FIG. 5 depicts a process for assigning icons to moving objects in accordance with the present invention
- FIG. 6 depicts a “birds eye” view of an illustrative hallway structure within a scene that can be monitored with the present invention
- FIG. 7 depicts examples of a display used for modeling moving objects within the hallway structure of FIG. 6 ;
- FIG. 8 depicts a display of a synthetic view of a moving object identified by the present invention.
- FIG. 9 depicts a block diagram of an alternative embodiment of the invention.
- FIG. 10 depicts a flow diagram of a method of the embodiment of FIG. 9 .
- FIG. 11A , 11 B, 11 C and 11 D depicts an example of the operation of the embodiment of FIG. 9 .
- FIG. 1 depicts a block diagram of a surveillance system 102 as applied to monitor activity in a simple hallway scene 100 .
- the hallway scene 100 comprises a first hallway 104 and a second hallway 106 that intersect and form a “T” shape.
- the hallway structure 100 is monitored by four cameras 108 , 110 , 112 and 114 . These cameras are coupled to an image processor 116 .
- the image processor processes the imagery from the cameras 108 , 110 , 112 and 114 to produce an image for display on an image display 118 (e.g., a video monitor).
- the particular view rendered from the various cameras is selectable using view selector 120 .
- a user e.g., a security guard 122
- a security guard 122 may be located either at the facility containing the scene 100 or may be remotely located from the scene 100 .
- the scene is modeled as a three-dimensional computer model and the imagery from the cameras 108 , 110 , 112 , 114 is overlaid upon the model to provide a three-dimensional contextual view of the hallway scene 100 to the security guard 122 .
- the security guard by manipulating the view selector, can take a virtual tour of the scene, can identify and isolate moving objects within the scene, can view the scene from either the camera locations or from locations between the cameras from a virtual viewpoint, can view the scene from a “bird's eye” view to identify moving objects or other locations to be viewed within the scene.
- FIG. 6 depicts a “bird's eye” view of the scene 100 of FIG. 1 .
- the cameras are place such that the scene, and especially the hallway junction, is covered by multiple views of the cameras.
- Each camera 108 , 110 , 112 and 114 has a particular viewing area respectively 602 , 604 , 606 and 608 .
- the three-dimensional model of the structure 100 will be “draped” with the imagery collected from each of the cameras 108 , 110 , 112 and 114 such that the security guard will view a contextual model of the scene that immerses the security guard in the surveillance situation.
- the cameras 108 , 110 , 112 , 114 are generally located to cover as much of the scene as possible and slightly overlap between the camera views to enable the model to align the various images with one another.
- the surveillance system of the present invention uses the model of the scene as the coordinate system for aligning all of the imagery of the scene such that overlapping of the camera views is not necessary.
- FIG. 2 depicts a block diagram of the surveillance system 102 of the present invention.
- System 102 comprises a camera assembly 212 , an image processor 116 , a model update source 200 , a view selector 120 and an image display 118 .
- the camera assembly comprises a plurality of cameras 108 , 110 , 112 and 114 coupled to a multiplexer 202 . Any number of cameras may be used and coupled to a plurality of multiplexers such that the camera assembly 212 may cover entire buildings or regions that are to be surveilled.
- the multiplexer 202 combines the video streams from the, for example, four cameras by splitting the screen into four quadrants and inserting one stream in each quadrant. The stream of video frames is coupled to the image processor 116 .
- the image processor 116 comprises a frame capture circuit 204 , a frame splitter 206 , an image rendering processor 208 and a 3D model generator 210 .
- a computer system that can be used as the image processor in accordance with the invention is a dual processor, dual PCI bus, general purpose computer comprising two Pentium 4 processors, an INVIDIA GeForce3 GPU-based video card and four frame capture circuits.
- the frame capture circuit 204 captures, in a known manner, each frame of video and temporarily stores that information in a memory.
- the frame splitter 206 is used to demux the video streams so that the video signal from each camera will be processed and stored independently.
- the 3D model generator 210 and the image rendering processor 208 work together to generate the contextual view of the scene.
- the 3D model of scene 100 is apriori generated as a wire frame or planar computer model.
- the model update source 200 provides the 3D model.
- the view of the model that is to be rendered is identified by the view selector 120 .
- the view selector comprises a joy stick, a mouse pointer, and a zoom control such that the security guard may move about the scene as well as zoom in or out on particular objects within the scene.
- the model is coupled to the image rendering processor where the various video images from the cameras are warped into alignment with the model and rendered upon or draped upon the model.
- the particular view of the model containing the view is displayed.
- the coordinate system of the model is used for aligning the video imagery.
- the video images are closely aligned to the common coordinate system so that the user is easily able to determine how activity in one video relates to activity in other videos without referring to or remembering a map or 3D model of the scene. For instance, if an event deserving attention occurs in a video from one camera view and the activity then moves out of the field of view of that camera in a particular direction, the user can easily predict the new location of the activity within the view of another camera. The user is able to do this without having to remember the orientation of the camera since all video from the cameras is now aligned.
- FIG. 3 depicts a flow diagram 300 of a process 300 by which the surveillance system 102 of the present invention operates.
- input imagery from the cameras is coupled to the image processor.
- the user selects a view of the scene and that view information is coupled to step 306 where the model is generated that depicts the model as viewed from the location selected in the view selection step 304 .
- the overall model of the scene is apriori rendered using various well-known modeling techniques.
- the model generation step 306 is used to produce the model from the selected viewpoint.
- an outline of the location or building is encoded in a 3D digital format.
- the outline model comprises the perimeter of the location or building and also the outline of key areas such as corridors, streets, buildings, and so on.
- the outline model may also contain simple attributes of the location such as room numbers.
- the source for the outline model can be from simple measurements recorded manually, followed by encoding into one of the 3D formats known in the art such as Alias/Wavefront OBJ, Open Inventor, VRML and the like.
- a technician marks the location of each camera on the outline model of the scene.
- the technician performs this process using information from the surrounding regions such as a room number, building shape or other distinguishing landmarks and by corresponding the camera locations manually to the outline model.
- the technician also defines the camera parameters such as height and orientation.
- the camera orientation comprise the pan, tilt and roll of the cameras with respect to a global coordinate system defined by the scene. There are many methods known in the art for measuring the pan, tilt and roll of a camera, any of which are useful in building the model of the scene.
- the result of the process for defining the camera parameters is a set of parameters that define location, height, pan, tilt and roll for each camera with respect to a global outline model of the scene.
- planar surfaces of the outline model of the scene are then modeled using well known 3D shape modeling techniques.
- one method for recovering polygons within a scene is for the installation technician to perform simple model building using captured imagery and knowledge of the 3D shape of the scene.
- the technician loads a single image from each camera view into a display.
- the technician selects a set of points in the image that define the boundaries of a single planar surface in the scene, such as a wall.
- the surface need not be entirely planar, objects that are attached to the surface such as heaters may be defined as belonging to a single plane.
- the technician then records whether the plane is approximately vertical or horizontal, or any other predetermined orientation.
- the technician then repeats the process for other planar surfaces in the scene and for each camera view.
- the technician records the floor upon which each camera is located in a multi-floor building.
- the result of the process is a set of points in the coordinate system of the images, a set of flags defining the orientation of the surfaces in 3D and a set of numbers defining the floor upon which each camera is located.
- the model from the selected viewpoint and the input imagery are combined to render a view of the scene as directed by the security guard.
- the camera locations are static, but from the following description it will be clear that the cameras may pan and tilt dynamically and the imagery updated dynamically to reflect the pan and tilt motion.
- the rendered view of the scene does not, at this point, contain moving objects.
- the rendering process is performed as described in U.S. patent application Ser. No. 09/800,550, filed Mar. 7, 2001 (Attorney Docket No. SAR 13825) or a similar rendering process.
- the video from each camera is aligned to the model and warped into position.
- the warped video from each camera is applied to the model and merged to form the contextual view of the scene.
- the hallway structure of scene 100 will contain walls represented with video imagery from the cameras.
- the user is presented with a “real” 3D view of the scene 100 .
- Moving objects within the scene are processed at step 310 .
- the input imagery is processed to identify moving objects and then produce icons that are inserted into the rendered view such that the security guard may identify movement within the scene.
- the process for identifying movement is described with respect to FIG. 4 and the process for generating icons to represent the motion is described with respect to FIG. 5 below.
- the icons are inserted into the rendered imagery.
- the process 300 queries whether the rendered imagery should be stored. If the query at step 316 is answered affirmatively, the imagery is stored either on video tape or in digital memory at step 318 . Such storage allows the model and its constituent video to be “rewound” and “replayed” by the security guard, if desired.
- a rendered image and icons are displayed for the security guard.
- the process 300 queries whether a new view is selected by the security guard. If a new view is not selected, the process returns to step 302 and processes more of the video streams from the cameras. If a new view has been selected, then the process returns to both steps 302 and 304 to generate a new model of the new view as well as apply the new imagery to the new view of the model.
- the cameras used to produce the video have pan/tilt/zoom (PTZ) features, this camera motion must be accommodated when rendering views of a scene.
- PTZ pan/tilt/zoom
- the system can read this information directly from the camera. Then, the system accesses a look-up table to find the pose of the camera within the geometry of the scene given the PTZ values. The pose is used to render a display.
- a calibration process To create the pose look-up table, a calibration process must be performed.
- the camera is pointed at a particular location in the scene and a user identifies (typically by pointing and clicking a mouse pointer) points in the image and corresponding points in the 3D model.
- the system then computes the rotation portion of the pose for that particular set of PTZ values. This procedure is repeated for several images having the camera pointed in various directions.
- the captured PTZ values and the computed pose for each direction are stored in the pose look-up table.
- An interpolation algorithm then computes PTZ and pose values between the measured values to fully populate the pose look-up table.
- a second technique aligns the video to a spherical image mosaic that itself has been aligned (possibly manually) to the 3D model.
- This is a robust technique because image-to-image alignment is performed rather than image-to-model alignment.
- Spherical image mosaics are a priori produced in a conventional manner for each camera having PTZ features. These mosaics are aligned to the 3D model and stored. Subsequent images from the cameras are aligned to the mosaics to provide accurate alignment of current images to the 3D model. To ensure alignment errors will not occur during changes in scene illumination, either multiple mosaics for each camera can be produced at various light levels or techniques disclosed in U.S. patent application Ser. No. 09/075,462, filed May 8, 1998 (Attorney Docket No. SAR 12426), incorporated herein by reference, can be used to align images over broad variations in illumination.
- FIG. 4 depicts a process 401 (performed at step 310 of FIG. 3 ) for identifying moving objects within the scene.
- the image sequence is input to the process.
- the image sequence is processed by both a two-dimensional (2D) module 418 and a three-dimensional (3D) module 420 .
- the 2D module 418 separates foreground objects from the static background scene.
- the 3D module 420 performs depth and shape recovery to enable the process 401 to identify the form of object that is moving in the scene.
- the static background information (a reference image) within the scene is extracted from the image sequence using a well known filtering technique that remove foreground motion from a video sequence.
- One such method is disclosed in European Patent Publication Number EP 1045591.
- the reference image is then subtracted from the original image sequence at step 404 to produce a two dimensional (2D) object silhouette for each moving object in the scene. All moving objects will be appear as a silhouette in step 406 .
- three dimensional information is necessary to identify and isolate moving objects versus objects that apparently move because of camera movement, shadows, and the like.
- Such three dimensional processing is performed in the 3D module comprising steps 408 , 410 , 412 and 414 .
- depth information is computed from the image sequence.
- background depth information is computed or determined and, at step 412 , the background depth information is subtracted from the depth information gleaned from the image sequence to produce foreground object depth information only.
- the foreground depth information is combined with the object silhouette information at step 414 to produce three dimensional object silhouettes at step 416 .
- the object silhouettes produced at step 416 accurately depict the foreground objects that are moving within a scene.
- each object silhouette is rendered into a three dimensional model then when the model is inserted as an icon into the rendered imagery of the scene that foreground object can be visualized from different viewpoints and appear geometrically correct within the scene.
- FIG. 5 depicts a flow diagram of a process 501 (performed at step 312 of FIG. 3 ) for generating icons that are three dimensional models of moving objects within a scene.
- the 2D and/or 3D object silhouettes from process 401 of FIG. 4 are input into the process 501 .
- the object silhouettes generally comprise both depth and/or shape information from the depth estimation module as well as textural information such as color and brightness. For example, significant textural discontinuities that are also close to the significant depth discontinuities can be classified to be part of the outline or silhouette of the object.
- the object silhouette is classified. The purpose of this classification step is to identify the model type that should be fit to the foreground object. Classification can be performed by analyzing attributes of the object.
- Examples of attributes include size and shape of the silhouette.
- An example of a method that can recover the attributes of an object is a moment analysis.
- the first and second order moments computed on the foreground object can be used to determine whether or not an object is slender.
- a slender object may be classified as a human, and non-slender object may be classified as another type of object such as a vehicle.
- different models for the object can be invoked. For example, at step 504 , a human may be modeled by a set of spheres and, at step 506 , a vehicle can be modeled as a box. Other object would be modeled as various types in steps 508 and 510 .
- These icons (object models) are inserted into the rendered imagery as described above.
- FIG. 7 depicts an illustrative display screen that may be viewed by a security guard.
- the view screen 700 depicts a “birds eye” view of the monitored scene in region 710 and depicts, in region 712 four of the live camera views from each of the four cameras 108 , 110 , 112 and 114 .
- region 710 is a rendering of the hallway structure 100 of FIG. 1 containing the moving objects that were identified by the moving object detection process 401 and rendered as icons by the moving object icon generator 501 .
- the icons are 702 , 704 and 706 are generally shown as different color “dots” depending on the camera that is capturing the movement of the object.
- icon 702 may be shown in red and the icon 716 for the camera (camera 110 ) that is capturing that movement would also be shown in red.
- camera icon 714 may be shown in blue and object 704 would also be in blue.
- the trailing shadow 708 may be used to show prior positions of the moving object as it moves through the scene.
- Object icon 706 contains shadow trail 708 to show movement of the object along hallway 104 .
- the security guard may receive additional information from erratic or abnormal movement of an object through a scene.
- the security guard may place the mouse pointer upon the object and click or double click to select that object.
- the surveillance system After selection, the surveillance system generates a view of that object from either a particular camera location or a synthetic camera location that is rendered from the multiple cameras viewing a scene.
- FIG. 8 depicts a synthetic view from a location in hallway 106 of object 702 .
- This synthetic view can be manipulated using a zoom control to zoom in/out on the object, or use a joy stick to move within the scene to get a better view of the object and its destination.
- the security guard can always select a live view of the scene as taken from a camera that is currently imaging the object.
- the rendered view 702 shows a sphere based model of a person walking along the hallway 106 . As the camera angle is panned or tilted for the synthetic view generated from a different location, the three dimensional spherical model will render a person walking down the hallway.
- the walls and floors of the rendered image are textured from the video that is produced by the cameras such that the synthetic view is as accurate as an actual camera view of the scene.
- the identification of the moving object and then rendering a specific image of a portion of the entire scene with that object within the scene is known as a “flashlight mode” of operation.
- the process used for rendering flashlight mode imagery is described in U.S. patent application Ser. No. 09/800,550, filed Mar. 7, 2001.
- the present system involves substantial flexibility in the view point and video rendering of a scene.
- the view selector may include specific go to points for the operator to check on a regular basis.
- the view may contain camera icons so that the security guard may know exactly what views are available from the live feeds.
- a top view of the motion as depicted in FIG. 7 is available.
- the security guard may fly through the image imagery to take a virtual walk through of the scene from a remote location and, at any time, full resolution video is available from the feeds of each of the cameras such that the security guard may elect a full resolution view of the imagery in the scene.
- imagery may be annotated when the mouse pointer is pointed to certain locations within a scene to show the location information regarding that scene or object identification. For example, if a person has entered through a secure check point that person's name and ID number may appear on the screen when that person's icon is identified within the scene. As such, the person could be tracked as they moved through a secure area. Alternatively, a person could be observed in a particular location, the user could request identification, and the full resolution video could be sampled by a face recognition system to identify the person. An annotation of the person's identification could then appear on the three dimensional contextual view of the scene. The user could then track the person as they moved through the facility. If the person could not be identified, security personnel could be dispatched to intercept the unidentified person.
- FIG. 9 Another embodiment of the present invention is depicted in FIG. 9 where an implicit 3D model is used to provide an intuitive map that interconnects image sequences.
- the system 900 comprises a plurality of video cameras, or other sources of imagery, 902 , 904 , 906 and 908 that produce a plurality of video sequences.
- the video sequences are coupled to an image processor 912 that contains an implicit 3D model 918 .
- the model 918 can be created using the model update source 914 .
- a view selector 910 is coupled to the image processor 912 .
- the view selector 910 is manipulated by a user such that views of the imagery taken by the cameras 902 , 904 , 906 and 908 are displayed on the image display 916 .
- the model update source 914 is used to create an implicit 3D model in an apriori manner by a user.
- the implicit 3D model creates a map that interconnects the views of the various cameras such that, as an object moves through a scene that is imaged by the cameras, a simple selection of a view using a mouse pointer on the screen will automatically display the best view of the selected image area.
- the map (the implicit model) identifies interconnections between video sequences.
- the map is a look-up table that comprises, for each video sequence, a transition region and a video sequence associated with the transition region.
- the transition region may be a single pixel or a region of pixels.
- Each video sequence is given a unique identification number.
- the unique identification numbers may be associated with one or more transition regions.
- each sequence has a transition region at 0, 90, 180 and 270 degrees with the coordinate system of an image. These regions are located at the top, bottom, right and left edges of an image. Other locations may be used. Using the four locations, a user can select a transition region into which an object moves such that a more appropriate view of the object is displayed.
- the implicit map only needs to be created once.
- the user needs to have knowledge of only the overlaps of the video produced by the cameras then the map can be created having the user identify which cameras overlap with each other camera or closely overlap each other. Note that there does not need to be an explicit overlap between the images.
- the user need only identify which camera view is desired to be shown next if a target happens to be moving in a particular direction. For each camera that overlaps or nearly overlaps, a user draws a rectangle or other shaped region of interest in the image and keys in which camera should be displayed if an object is moving in a particular direction within that region.
- FIG. 11D shows an example scene having three cameras 1104 , 1106 and 1108 .
- the coordinate system for each image is shown at scale 1150 .
- Each camera covers a particular region 1114 , 1112 and 1110 that is imaged by each of the cameras.
- Table 1 identifies the implicit three dimensional model (map) for the camera arrangement in FIG. 11D .
- camera 1 has only one available transition to camera 2 when an object moves in the region at 270 degrees.
- Camera 2 transitions to camera 1 at 90 degrees, camera 3 at 0 degrees and camera 3 also 180 degrees and, lastly, camera 3 transitions to camera 2 at 0 degrees and again at camera 2 at 180 degrees.
- FIG. 11A , 11 B and 11 C depict the three views from cameras 1104 , 1106 and 1108 as an object follows path 1102 shown in FIG. 11D .
- the object begins at position 1116 and transitions from right to left in FIG. 11A in the view of camera 1104 .
- the cursor 1120 may be placed on the object or in the region 1118 to select a new view.
- the transitions as defined in table 1 will identify camera 2 at the 270 degree region as the next camera to use to best view the object.
- FIG. 11B shows the object moving in the view of camera 2 from left to the 0 degree region 1128 .
- cursor 1120 may be placed upon the region and selected, the table is then used again to identify the next view of the scene to best image the moving object.
- the third camera 1108 is now selected as the object begins at position 1130 and moves to position 1132 .
- the object then moves from position 1130 to position 1132 .
- the object then transitions out of the scene.
- an implicit 3D model can easily be created to enable a user to quickly follow a moving object through the scene through any number of cameras that have been used to establish the implicit 3 dimensional model.
- FIG. 10 is a method of the alternative embodiment of the invention.
- the method 1000 begins at step 1002 with an input of a plurality of video sequences from the cameras.
- the video sequences are registered to an implicit relationship model as defined by the user selecting regions to identify cameras to which to transition.
- a view of the scene is selected using an input device such as a mouse, track pad, track ball and the like.
- a sequence is selected for display as identified in step 1010 , based on the placement of the cursor as discussed above.
- the selected video sequence is then displayed at step 1008 .
- This system provides and intuitive and simple manner for a user to follow an object through a scene. An operator can easily navigate around the scene by placing the cursor in a transition region within a particular video frame and selecting that region. If the operator wishes to see around a building corner, the operator can select the region of the corner and the best view around the corner would be displayed.
- the view selector was described as being manipulated by a user to select a view of the scene.
- the view selector may be automated. For example, when motion is detected in the scene (or a particular type of motion is detected), the view selector may automatically select a view that best displays the region of the scene containing the motion.
- the view selector may automatically select a view that best displays the region of the scene containing the motion.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Geometry (AREA)
- Processing Or Creating Images (AREA)
- Closed-Circuit Television Systems (AREA)
- Burglar Alarm Systems (AREA)
Abstract
A method and apparatus for providing immersive surveillance wherein a remote security guard may monitor a scene using a variety of imagery sources that are rendered upon a model to provide a three-dimensional conceptual view of the scene. Using a view selector, the security guard may dynamically select a camera view to be displayed on his conceptual model, perform a walk through of the scene, identify moving objects and select the best view of those moving objects and so on.
Description
- This application claims benefit of U.S. provisional patent application Ser. No. 60/339,726, filed Nov. 2, 2001 which is herein incorporated by reference.
- This invention was made with U.S. government support under contract number F30602-00-C-0143. The U.S. government has certain rights in this invention.
- 1. Field of the Invention
- The present invention generally relates to surveillance systems and, more particularly, relates to a method and apparatus for providing immersive surveillance.
- 2. Description of the Related Art
- The objective of a surveillance or visualization display is typically to allow a user to monitor or observe a scene with full awareness of the situation within the scene. Typical surveillance or visualization systems present video to a user from more than one camera on a single display. Such a display allows the user to observe different parts of the scene, or to observe the same part of the scene from different viewpoints. A typical surveillance display, for example, has 16 videos of a scene shown in a 4 by 4 grid on a monitor. Each video is usually labeled by a fixed textual annotation displayed under the video segment to identify the image. For example, the text “lobby” or “front entrance” may be shown. If an event deserving attention is observed in one particular video, then the label can be used to locate the activity in the scene.
- This approach for surveillance and visualization has been used widely for many years. However, there are some fundamental problems with this approach.
- First, if an event deserving attention occurs in one particular video, then the user does not know how the activity relates to other locations in the scene without referring to or remembering a map or 3D model of the scene. For example, if activity is observed near “
elevator 1” and the user knows that a guard is currently at “stairwell 5”, then without a map or 3D model, the user will not know if the guard is very close or very far from the activity in order to intervene. The process of referring to a map or 3D model either on paper or on a computer is typically time-consuming and error-prone since a human is involved in the association of the camera view to the map or model. The process of remembering a map or 3D model is also error-prone, and typically impossible when large numbers of cameras are used or if the site is large. - Second, if an event deserving attention occurs in a video and then the activity moves out of the field of view of the video in one particular direction, then there are only two ways that the user can predict the new location of the activity. First, the user can remember the orientation (pointing direction) of the camera with respect to a fixed coordinate system (for example, the compass directions). Second, the user can recognize landmarks in the video and can use the landmarks to determine the approximate orientation of the camera with respect to a fixed coordinate system by remembering or referring to a map or 3D model of the scene. These two methods of predicting the new location of activity are error-prone, since typically the views from cameras are shown with respect to many different arbitrary coordinate systems that vary widely from camera to camera depending on how each camera was mounted during installation. As more cameras are added to the system, the more difficult it is for the user to remember their orientations or to recognize the landmarks in the scene. In addition, some parts of the scenes may contain no distinguishing landmarks at all.
- Third, as more videos are displayed on a screen, then the resolution of each video has to be reduced in order to fit them into a display. This makes it difficult to observe the details of any event deserving attention in the video. The current solution to this problem is either to have an additional display that shows one selected video at high resolution, or to switch a single display between the view showing multiple reduced resolution videos and a view showing a single video at high resolution. However, the problem with this approach is that the user will miss any activity that may be occurring in other videos while they are focusing on the single high-resolution video.
- Therefore, there is a need in the art for a method and apparatus for providing an immersive surveillance system that provides a user with a three-dimensional contextual view of a scene.
- The present invention is a method and apparatus for providing immersive surveillance wherein a remote user may monitor a scene using a variety of imagery sources that are rendered upon a three-dimensional model to provide a three-dimensional contextual view of the scene. The surveillance system comprises a plurality of cameras supplying video and an image processor for applying the videos to a three dimensional (3D) model of the scene. The rendered model/video combination provides a 3D contextual view of the scene in which the user can be immersed. Using a view selector, the user may dynamically select a specific view to be displayed from the contextual model, perform a virtual walk through of the scene, identify moving objects and select the best view of those moving objects, and so on.
- So that the manner in which the above recited features of the present invention are attained and can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments thereof which are illustrated in the appended drawings.
- It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered limiting of its scope, for the invention may admit to other equally effective embodiments.
-
FIG. 1 depicts a high level block diagram of the present invention; -
FIG. 2 depicts a detailed block diagram of the surveillance system in accordance with the present invention; -
FIG. 3 depicts a flow chart of the operation of the present invention; -
FIG. 4 depicts a process for identifying moving objects in accordance with the present invention; -
FIG. 5 depicts a process for assigning icons to moving objects in accordance with the present invention; -
FIG. 6 depicts a “birds eye” view of an illustrative hallway structure within a scene that can be monitored with the present invention; -
FIG. 7 depicts examples of a display used for modeling moving objects within the hallway structure ofFIG. 6 ; -
FIG. 8 depicts a display of a synthetic view of a moving object identified by the present invention; -
FIG. 9 depicts a block diagram of an alternative embodiment of the invention; -
FIG. 10 depicts a flow diagram of a method of the embodiment ofFIG. 9 ; and -
FIG. 11A , 11B, 11C and 11D depicts an example of the operation of the embodiment ofFIG. 9 . -
FIG. 1 depicts a block diagram of asurveillance system 102 as applied to monitor activity in asimple hallway scene 100. Thehallway scene 100 comprises afirst hallway 104 and asecond hallway 106 that intersect and form a “T” shape. Thehallway structure 100 is monitored by fourcameras image processor 116. The image processor processes the imagery from thecameras view selector 120. Generally, a user, e.g., asecurity guard 122, may be located either at the facility containing thescene 100 or may be remotely located from thescene 100. As shall be described below, the scene is modeled as a three-dimensional computer model and the imagery from thecameras hallway scene 100 to thesecurity guard 122. The security guard, by manipulating the view selector, can take a virtual tour of the scene, can identify and isolate moving objects within the scene, can view the scene from either the camera locations or from locations between the cameras from a virtual viewpoint, can view the scene from a “bird's eye” view to identify moving objects or other locations to be viewed within the scene. -
FIG. 6 depicts a “bird's eye” view of thescene 100 ofFIG. 1 . The cameras are place such that the scene, and especially the hallway junction, is covered by multiple views of the cameras. Eachcamera structure 100 will be “draped” with the imagery collected from each of thecameras cameras -
FIG. 2 depicts a block diagram of thesurveillance system 102 of the present invention.System 102 comprises a camera assembly 212, animage processor 116, amodel update source 200, aview selector 120 and animage display 118. The camera assembly comprises a plurality ofcameras multiplexer 202. Any number of cameras may be used and coupled to a plurality of multiplexers such that the camera assembly 212 may cover entire buildings or regions that are to be surveilled. Themultiplexer 202 combines the video streams from the, for example, four cameras by splitting the screen into four quadrants and inserting one stream in each quadrant. The stream of video frames is coupled to theimage processor 116. Theimage processor 116 comprises aframe capture circuit 204, aframe splitter 206, animage rendering processor 208 and a3D model generator 210. One example of a computer system that can be used as the image processor in accordance with the invention is a dual processor, dual PCI bus, general purpose computer comprising two Pentium 4 processors, an INVIDIA GeForce3 GPU-based video card and four frame capture circuits. - The
frame capture circuit 204 captures, in a known manner, each frame of video and temporarily stores that information in a memory. Theframe splitter 206 is used to demux the video streams so that the video signal from each camera will be processed and stored independently. The3D model generator 210 and theimage rendering processor 208 work together to generate the contextual view of the scene. The 3D model ofscene 100 is apriori generated as a wire frame or planar computer model. Themodel update source 200 provides the 3D model. The view of the model that is to be rendered is identified by theview selector 120. Typically, the view selector comprises a joy stick, a mouse pointer, and a zoom control such that the security guard may move about the scene as well as zoom in or out on particular objects within the scene. and select various views of the scene, as needed. Once the view of the model is generated, the model is coupled to the image rendering processor where the various video images from the cameras are warped into alignment with the model and rendered upon or draped upon the model. The particular view of the model containing the view is displayed. - The coordinate system of the model is used for aligning the video imagery. The video images are closely aligned to the common coordinate system so that the user is easily able to determine how activity in one video relates to activity in other videos without referring to or remembering a map or 3D model of the scene. For instance, if an event deserving attention occurs in a video from one camera view and the activity then moves out of the field of view of that camera in a particular direction, the user can easily predict the new location of the activity within the view of another camera. The user is able to do this without having to remember the orientation of the camera since all video from the cameras is now aligned. For example, if activity moves out of one camera view to the right, then the user can expect to see the activity being recaptured from cameras with views that are displayed to the right of the first view. By using a common coordinate system from the 3D model, multiple, non overlapping portions of the video imagery from the cameras can be aligned to the model. One particular process for rendering imagery to a 3D model that can be used by the surveillance system of the present invention is described in U.S. patent application Ser. No. 09/800,550, filed Mar. 7, 2001 (Attorney docket SAR 13825) and incorporated herein by reference. Other processes for rendering images to a 3D model can be used.
-
FIG. 3 depicts a flow diagram 300 of aprocess 300 by which thesurveillance system 102 of the present invention operates. Atstep 302, input imagery from the cameras is coupled to the image processor. Atstep 304, the user selects a view of the scene and that view information is coupled to step 306 where the model is generated that depicts the model as viewed from the location selected in theview selection step 304. The overall model of the scene is apriori rendered using various well-known modeling techniques. Themodel generation step 306 is used to produce the model from the selected viewpoint. To produce a model, an outline of the location or building is encoded in a 3D digital format. The outline model comprises the perimeter of the location or building and also the outline of key areas such as corridors, streets, buildings, and so on. The outline model may also contain simple attributes of the location such as room numbers. The source for the outline model can be from simple measurements recorded manually, followed by encoding into one of the 3D formats known in the art such as Alias/Wavefront OBJ, Open Inventor, VRML and the like. - A technician marks the location of each camera on the outline model of the scene. The technician performs this process using information from the surrounding regions such as a room number, building shape or other distinguishing landmarks and by corresponding the camera locations manually to the outline model. The technician also defines the camera parameters such as height and orientation. The camera orientation comprise the pan, tilt and roll of the cameras with respect to a global coordinate system defined by the scene. There are many methods known in the art for measuring the pan, tilt and roll of a camera, any of which are useful in building the model of the scene. The result of the process for defining the camera parameters is a set of parameters that define location, height, pan, tilt and roll for each camera with respect to a global outline model of the scene.
- Subsequently, the planar surfaces of the outline model of the scene are then modeled using well known 3D shape modeling techniques. For example, one method for recovering polygons within a scene is for the installation technician to perform simple model building using captured imagery and knowledge of the 3D shape of the scene. The technician loads a single image from each camera view into a display. The technician then selects a set of points in the image that define the boundaries of a single planar surface in the scene, such as a wall. The surface need not be entirely planar, objects that are attached to the surface such as heaters may be defined as belonging to a single plane. The technician then records whether the plane is approximately vertical or horizontal, or any other predetermined orientation. The technician then repeats the process for other planar surfaces in the scene and for each camera view. In addition, the technician records the floor upon which each camera is located in a multi-floor building. The result of the process is a set of points in the coordinate system of the images, a set of flags defining the orientation of the surfaces in 3D and a set of numbers defining the floor upon which each camera is located.
- Other modeling techniques may be used to develop a full 3D model of the scene. Additionally texture may be mapped onto the 3D model such that the walls and floors and other objects within the scene that are not draped with video during the rendering process have apparent texture to the user.
- At
step 308, the model from the selected viewpoint and the input imagery are combined to render a view of the scene as directed by the security guard. In the example described herein, it is assumed that the camera locations are static, but from the following description it will be clear that the cameras may pan and tilt dynamically and the imagery updated dynamically to reflect the pan and tilt motion. The rendered view of the scene does not, at this point, contain moving objects. The rendering process is performed as described in U.S. patent application Ser. No. 09/800,550, filed Mar. 7, 2001 (Attorney Docket No. SAR 13825) or a similar rendering process. In summary, the video from each camera is aligned to the model and warped into position. The warped video from each camera is applied to the model and merged to form the contextual view of the scene. In this manner, the hallway structure ofscene 100 will contain walls represented with video imagery from the cameras. The user is presented with a “real” 3D view of thescene 100. - Moving objects within the scene are processed at
step 310. Where the input imagery is processed to identify moving objects and then produce icons that are inserted into the rendered view such that the security guard may identify movement within the scene. The process for identifying movement is described with respect toFIG. 4 and the process for generating icons to represent the motion is described with respect toFIG. 5 below. Atstep 314, the icons are inserted into the rendered imagery. Atstep 316, theprocess 300 queries whether the rendered imagery should be stored. If the query atstep 316 is answered affirmatively, the imagery is stored either on video tape or in digital memory atstep 318. Such storage allows the model and its constituent video to be “rewound” and “replayed” by the security guard, if desired. Atstep 320, a rendered image and icons are displayed for the security guard. Atstep 322, theprocess 300 queries whether a new view is selected by the security guard. If a new view is not selected, the process returns to step 302 and processes more of the video streams from the cameras. If a new view has been selected, then the process returns to bothsteps - If the cameras used to produce the video have pan/tilt/zoom (PTZ) features, this camera motion must be accommodated when rendering views of a scene. If the PTZ orientation of a camera is captured by encoders on the camera, the system can read this information directly from the camera. Then, the system accesses a look-up table to find the pose of the camera within the geometry of the scene given the PTZ values. The pose is used to render a display.
- To create the pose look-up table, a calibration process must be performed. The camera is pointed at a particular location in the scene and a user identifies (typically by pointing and clicking a mouse pointer) points in the image and corresponding points in the 3D model. The system then computes the rotation portion of the pose for that particular set of PTZ values. This procedure is repeated for several images having the camera pointed in various directions. The captured PTZ values and the computed pose for each direction are stored in the pose look-up table. An interpolation algorithm then computes PTZ and pose values between the measured values to fully populate the pose look-up table.
- If the foregoing encoder-based approach is not accurate enough to enable alignment of the video and the model, or encoders are not available to produce camera PTZ values, then image information can be used to match against the model and achieve alignment without PTZ values or with inaccurate PTZ values.
- One procedure aligns the video directly with the 3D model. This procedure is described in U.S. patent application Ser. No. 09/800,550, filed Mar. 7, 2001 (Attorney Docket No. SAR 13825). This alignment procedure can be augmented with the teachings of U.S. patent application Ser. No. 09/075,462, filed May 8, 1998 (Attorney Docket No. SAR 12426) to utilize texture maps and image filtering to improve image alignment when scene illumination varies.
- A second technique aligns the video to a spherical image mosaic that itself has been aligned (possibly manually) to the 3D model. This is a robust technique because image-to-image alignment is performed rather than image-to-model alignment. Spherical image mosaics are a priori produced in a conventional manner for each camera having PTZ features. These mosaics are aligned to the 3D model and stored. Subsequent images from the cameras are aligned to the mosaics to provide accurate alignment of current images to the 3D model. To ensure alignment errors will not occur during changes in scene illumination, either multiple mosaics for each camera can be produced at various light levels or techniques disclosed in U.S. patent application Ser. No. 09/075,462, filed May 8, 1998 (Attorney Docket No. SAR 12426), incorporated herein by reference, can be used to align images over broad variations in illumination.
-
FIG. 4 depicts a process 401 (performed atstep 310 ofFIG. 3 ) for identifying moving objects within the scene. Atstep 400, the image sequence is input to the process. The image sequence is processed by both a two-dimensional (2D)module 418 and a three-dimensional (3D)module 420. The2D module 418 separates foreground objects from the static background scene. The3D module 420 performs depth and shape recovery to enable theprocess 401 to identify the form of object that is moving in the scene. Atstep 402, the static background information (a reference image) within the scene is extracted from the image sequence using a well known filtering technique that remove foreground motion from a video sequence. One such method is disclosed in European Patent Publication Number EP 1045591. The reference image is then subtracted from the original image sequence atstep 404 to produce a two dimensional (2D) object silhouette for each moving object in the scene. All moving objects will be appear as a silhouette instep 406. - To accurately identify objects moving in a 3D scene, three dimensional information is necessary to identify and isolate moving objects versus objects that apparently move because of camera movement, shadows, and the like. Such three dimensional processing is performed in the 3D
module comprising steps step 408, depth information is computed from the image sequence. Atstep 410, background depth information is computed or determined and, atstep 412, the background depth information is subtracted from the depth information gleaned from the image sequence to produce foreground object depth information only. The foreground depth information is combined with the object silhouette information atstep 414 to produce three dimensional object silhouettes atstep 416. By combining the 2D and 3D object silhouette information, foreground objects that apparently moved due to camera movement or shadows are now identifiable as non-moving objects. As such, the object silhouettes produced atstep 416 accurately depict the foreground objects that are moving within a scene. - Once the foreground objects have been segmented and their depth and shapes have been recovered, then it is possible to model these objects in three dimensions. If each object silhouette is rendered into a three dimensional model then when the model is inserted as an icon into the rendered imagery of the scene that foreground object can be visualized from different viewpoints and appear geometrically correct within the scene.
-
FIG. 5 depicts a flow diagram of a process 501 (performed atstep 312 ofFIG. 3 ) for generating icons that are three dimensional models of moving objects within a scene. Atstep 500, the 2D and/or 3D object silhouettes fromprocess 401 ofFIG. 4 are input into theprocess 501. The object silhouettes generally comprise both depth and/or shape information from the depth estimation module as well as textural information such as color and brightness. For example, significant textural discontinuities that are also close to the significant depth discontinuities can be classified to be part of the outline or silhouette of the object. Atstep 502, the object silhouette is classified. The purpose of this classification step is to identify the model type that should be fit to the foreground object. Classification can be performed by analyzing attributes of the object. Examples of attributes include size and shape of the silhouette. An example of a method that can recover the attributes of an object is a moment analysis. The first and second order moments computed on the foreground object can be used to determine whether or not an object is slender. A slender object may be classified as a human, and non-slender object may be classified as another type of object such as a vehicle. Depending on the classification, different models for the object can be invoked. For example, atstep 504, a human may be modeled by a set of spheres and, atstep 506, a vehicle can be modeled as a box. Other object would be modeled as various types insteps -
FIG. 7 depicts an illustrative display screen that may be viewed by a security guard. Theview screen 700 depicts a “birds eye” view of the monitored scene inregion 710 and depicts, inregion 712 four of the live camera views from each of the fourcameras region 710 is a rendering of thehallway structure 100 ofFIG. 1 containing the moving objects that were identified by the movingobject detection process 401 and rendered as icons by the movingobject icon generator 501. The icons are 702, 704 and 706 are generally shown as different color “dots” depending on the camera that is capturing the movement of the object. For example,icon 702 may be shown in red and theicon 716 for the camera (camera 110) that is capturing that movement would also be shown in red. Similarly,camera icon 714 may be shown in blue and object 704 would also be in blue. To enhance the identity and movement of the object, the trailingshadow 708 may be used to show prior positions of the moving object as it moves through the scene.Object icon 706 containsshadow trail 708 to show movement of the object alonghallway 104. As such, the security guard may receive additional information from erratic or abnormal movement of an object through a scene. Upon identifying an object that the security guard desires to view more closely the security guard may place the mouse pointer upon the object and click or double click to select that object. After selection, the surveillance system generates a view of that object from either a particular camera location or a synthetic camera location that is rendered from the multiple cameras viewing a scene. -
FIG. 8 depicts a synthetic view from a location inhallway 106 ofobject 702. This synthetic view can be manipulated using a zoom control to zoom in/out on the object, or use a joy stick to move within the scene to get a better view of the object and its destination. Additionally, the security guard can always select a live view of the scene as taken from a camera that is currently imaging the object. The renderedview 702 shows a sphere based model of a person walking along thehallway 106. As the camera angle is panned or tilted for the synthetic view generated from a different location, the three dimensional spherical model will render a person walking down the hallway. The walls and floors of the rendered image are textured from the video that is produced by the cameras such that the synthetic view is as accurate as an actual camera view of the scene. The identification of the moving object and then rendering a specific image of a portion of the entire scene with that object within the scene is known as a “flashlight mode” of operation. The process used for rendering flashlight mode imagery is described in U.S. patent application Ser. No. 09/800,550, filed Mar. 7, 2001. - The present system involves substantial flexibility in the view point and video rendering of a scene. For example, the view selector may include specific go to points for the operator to check on a regular basis. The view may contain camera icons so that the security guard may know exactly what views are available from the live feeds. A top view of the motion as depicted in
FIG. 7 is available. The security guard may fly through the image imagery to take a virtual walk through of the scene from a remote location and, at any time, full resolution video is available from the feeds of each of the cameras such that the security guard may elect a full resolution view of the imagery in the scene. - Furthermore, the imagery may be annotated when the mouse pointer is pointed to certain locations within a scene to show the location information regarding that scene or object identification. For example, if a person has entered through a secure check point that person's name and ID number may appear on the screen when that person's icon is identified within the scene. As such, the person could be tracked as they moved through a secure area. Alternatively, a person could be observed in a particular location, the user could request identification, and the full resolution video could be sampled by a face recognition system to identify the person. An annotation of the person's identification could then appear on the three dimensional contextual view of the scene. The user could then track the person as they moved through the facility. If the person could not be identified, security personnel could be dispatched to intercept the unidentified person.
- Another embodiment of the present invention is depicted in
FIG. 9 where an implicit 3D model is used to provide an intuitive map that interconnects image sequences. Thesystem 900 comprises a plurality of video cameras, or other sources of imagery, 902, 904, 906 and 908 that produce a plurality of video sequences. The video sequences are coupled to animage processor 912 that contains animplicit 3D model 918. Themodel 918 can be created using themodel update source 914. Aview selector 910 is coupled to theimage processor 912. Theview selector 910 is manipulated by a user such that views of the imagery taken by thecameras image display 916. - The
model update source 914 is used to create an implicit 3D model in an apriori manner by a user. In essence, the implicit 3D model creates a map that interconnects the views of the various cameras such that, as an object moves through a scene that is imaged by the cameras, a simple selection of a view using a mouse pointer on the screen will automatically display the best view of the selected image area. - The map (the implicit model) identifies interconnections between video sequences. In one embodiment, the map is a look-up table that comprises, for each video sequence, a transition region and a video sequence associated with the transition region. The transition region may be a single pixel or a region of pixels. Each video sequence is given a unique identification number. The unique identification numbers may be associated with one or more transition regions. Once the relationship is made, the user may select a transition region in a displayed video sequence and the video sequence associated with the region will be displayed.
- In one example, each sequence has a transition region at 0, 90, 180 and 270 degrees with the coordinate system of an image. These regions are located at the top, bottom, right and left edges of an image. Other locations may be used. Using the four locations, a user can select a transition region into which an object moves such that a more appropriate view of the object is displayed.
- If the cameras are in fixed locations, the implicit map only needs to be created once. To produce the map, the user needs to have knowledge of only the overlaps of the video produced by the cameras then the map can be created having the user identify which cameras overlap with each other camera or closely overlap each other. Note that there does not need to be an explicit overlap between the images. The user need only identify which camera view is desired to be shown next if a target happens to be moving in a particular direction. For each camera that overlaps or nearly overlaps, a user draws a rectangle or other shaped region of interest in the image and keys in which camera should be displayed if an object is moving in a particular direction within that region.
-
FIG. 11D shows an example scene having threecameras scale 1150. Each camera covers aparticular region FIG. 11D . -
TABLE 1 Camera 1Camera 2Camera 32, 270° 1, 90° 2, 0° 3, 0° 2, 180° 3, 180° - In the first column,
camera 1 has only one available transition tocamera 2 when an object moves in the region at 270 degrees.Camera 2 transitions tocamera 1 at 90 degrees,camera 3 at 0 degrees andcamera 3 also 180 degrees and, lastly,camera 3 transitions tocamera 2 at 0 degrees and again atcamera 2 at 180 degrees. -
FIG. 11A , 11B and 11C depict the three views fromcameras path 1102 shown inFIG. 11D . The object begins atposition 1116 and transitions from right to left inFIG. 11A in the view ofcamera 1104. When the object reaches the left hand side intoregion 1118, thecursor 1120 may be placed on the object or in theregion 1118 to select a new view. At that point, the transitions as defined in table 1 will identifycamera 2 at the 270 degree region as the next camera to use to best view the object.FIG. 11B shows the object moving in the view ofcamera 2 from left to the 0degree region 1128. As the object moves intoregion 1128,cursor 1120 may be placed upon the region and selected, the table is then used again to identify the next view of the scene to best image the moving object. Thethird camera 1108 is now selected as the object begins atposition 1130 and moves toposition 1132. The object then moves fromposition 1130 toposition 1132. The object then transitions out of the scene. In this manner an implicit 3D model can easily be created to enable a user to quickly follow a moving object through the scene through any number of cameras that have been used to establish the implicit 3 dimensional model. -
FIG. 10 is a method of the alternative embodiment of the invention. Themethod 1000 begins atstep 1002 with an input of a plurality of video sequences from the cameras. Atstep 1004, the video sequences are registered to an implicit relationship model as defined by the user selecting regions to identify cameras to which to transition. Atstep 1010, a view of the scene is selected using an input device such as a mouse, track pad, track ball and the like. Atstep 1006, a sequence is selected for display as identified instep 1010, based on the placement of the cursor as discussed above. The selected video sequence is then displayed atstep 1008. This system provides and intuitive and simple manner for a user to follow an object through a scene. An operator can easily navigate around the scene by placing the cursor in a transition region within a particular video frame and selecting that region. If the operator wishes to see around a building corner, the operator can select the region of the corner and the best view around the corner would be displayed. - In the foregoing embodiments of the invention, the view selector was described as being manipulated by a user to select a view of the scene. However, the view selector may be automated. For example, when motion is detected in the scene (or a particular type of motion is detected), the view selector may automatically select a view that best displays the region of the scene containing the motion. Those skilled in the art will understand that many other criteria can be used to automate view selection.
- While foregoing is directed to the preferred embodiment of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.
Claims (23)
1. A surveillance system for monitoring a scene comprising:
a plurality of cameras producing video capturing the scene;
an image processor, coupled to said plurality of cameras, for applying each of the videos to a model of the scene;
a display, coupled to the image processor, for displaying a combination of the videos and model; and
a view controller, coupled to the image processor, for selecting views of the combination to be displayed.
2. The surveillance system of claim 1 wherein the image processor further comprises:
a three-dimensional model generator; and
an image rendering processor.
3. The surveillance system of claim 2 wherein said image processor further comprises:
means for identifying moving objects in each of the videos;
means for producing an icon representing each of the identified moving objects;
means for inserting the icon into the combination.
4. The surveillance system of claim 3 further comprising:
means for identifying a person as a moving object; and
means for annotating the display with a description of the person.
5. A display of a monitored scene comprising:
a three dimensional model of a scene having a plurality of video images rendered onto the three dimensional model.
6. The display of claim 5 wherein each of the video images in the plurality of video images is produced by a different camera viewing the scene from different locations.
7. The display of claim 5 further comprising icons representing moving objects identified within the plurality of video images.
8. The display of claim 5 further comprising a region displaying each of the video images as produced by a plurality of cameras.
9. The display of claim 5 wherein a viewpoint of the three dimensional model is selectable.
10. The display of claim 9 wherein the viewpoint is selected as a viewpoint of one of a plurality of cameras that produces the video images.
11. The display of claim 9 wherein the viewpoint is any location in three-dimensional space.
12. The display of claim 7 wherein the icon is annotated with text identifying the moving object.
13. (canceled)
14. (canceled)
15. (canceled)
16. (canceled)
17. A method of providing surveillance of a scene comprising:
producing a plurality of videos of a scene; producing a three dimensional model of the scene; selecting a viewpoint for the three dimensional model;
aligning the plurality of videos with the three dimensional;
rendering said plurality of videos onto the three dimensional model to form a combination view; and
displaying the combination view.
18. The method of claim 17 wherein the selected viewpoint is a bird's eye view.
19. The method of claim 17 further comprising:
selecting a location within the combination view; and
producing a view of the scene from the selected location.
20. The method of claim 17 further comprising:
identifying moving objects in the videos; producing an icon representing each moving object; and inserting the icon into the combination view.
21. The method of claim 17 further comprising: storing the combination view for replay.
22. The method of claim 20 wherein said identifying step further comprises:
identifying the object as a person; and annotating the combination view with text representing the identification of the person.
23. A method of providing surveillance of a scene comprising:
producing a plurality of videos of a scene;
producing an implicit 3D model of the scene;
selecting a region of a displayed video and using the 3D model to identify another video to be displayed to best produce an image of the selected region of the first video.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/404,261 US20090237508A1 (en) | 2000-03-07 | 2009-03-13 | Method and apparatus for providing immersive surveillance |
Applications Claiming Priority (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US18755700P | 2000-03-07 | 2000-03-07 | |
US09/800,550 US6985620B2 (en) | 2000-03-07 | 2001-03-07 | Method of pose estimation and model refinement for video representation of a three dimensional scene |
US33972601P | 2001-11-02 | 2001-11-02 | |
US10/202,546 US7522186B2 (en) | 2000-03-07 | 2002-07-24 | Method and apparatus for providing immersive surveillance |
US12/404,261 US20090237508A1 (en) | 2000-03-07 | 2009-03-13 | Method and apparatus for providing immersive surveillance |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/202,546 Continuation US7522186B2 (en) | 2000-03-07 | 2002-07-24 | Method and apparatus for providing immersive surveillance |
Publications (1)
Publication Number | Publication Date |
---|---|
US20090237508A1 true US20090237508A1 (en) | 2009-09-24 |
Family
ID=26897783
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/202,546 Expired - Fee Related US7522186B2 (en) | 2000-03-07 | 2002-07-24 | Method and apparatus for providing immersive surveillance |
US12/404,261 Abandoned US20090237508A1 (en) | 2000-03-07 | 2009-03-13 | Method and apparatus for providing immersive surveillance |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/202,546 Expired - Fee Related US7522186B2 (en) | 2000-03-07 | 2002-07-24 | Method and apparatus for providing immersive surveillance |
Country Status (7)
Country | Link |
---|---|
US (2) | US7522186B2 (en) |
EP (1) | EP1449180A4 (en) |
JP (1) | JP2005517253A (en) |
KR (1) | KR100940142B1 (en) |
CA (1) | CA2466085A1 (en) |
IL (1) | IL161400A0 (en) |
WO (1) | WO2003067537A2 (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080292140A1 (en) * | 2007-05-22 | 2008-11-27 | Stephen Jeffrey Morris | Tracking people and objects using multiple live and recorded surveillance camera video feeds |
US20090219300A1 (en) * | 2005-11-15 | 2009-09-03 | Yissum Research Deveopment Company Of The Hebrew University Of Jerusalem | Method and system for producing a video synopsis |
US20090310865A1 (en) * | 2008-06-13 | 2009-12-17 | Jenn Hwan Tarng | Video Surveillance System, Annotation And De-Annotation Modules Thereof |
US20110157368A1 (en) * | 2009-12-31 | 2011-06-30 | Samsung Techwin Co., Ltd. | Method of performing handoff between photographing apparatuses and surveillance apparatus using the same |
WO2011059193A3 (en) * | 2009-11-10 | 2011-10-20 | Lg Electronics Inc. | Method of recording and replaying video data, and display device using the same |
US20110317017A1 (en) * | 2009-08-20 | 2011-12-29 | Olympus Corporation | Predictive duty cycle adaptation scheme for event-driven wireless sensor networks |
US20120069191A1 (en) * | 2010-09-21 | 2012-03-22 | Hon Hai Precision Industry Co., Ltd. | Electronic device and switching method for the same |
US20120155778A1 (en) * | 2010-12-16 | 2012-06-21 | Microsoft Corporation | Spatial Image Index and Associated Updating Functionality |
US8482609B1 (en) * | 2006-11-22 | 2013-07-09 | Sightlogix, Inc. | Methods and apparatus related to surveillance system marketing, planning and/or integration |
US8949235B2 (en) | 2005-11-15 | 2015-02-03 | Yissum Research Development Company Of The Hebrew University Of Jerusalem Ltd. | Methods and systems for producing a video synopsis using clustering |
US8965047B1 (en) * | 2008-06-10 | 2015-02-24 | Mindmancer AB | Selective viewing of a scene |
US9071626B2 (en) | 2008-10-03 | 2015-06-30 | Vidsys, Inc. | Method and apparatus for surveillance system peering |
US9087386B2 (en) | 2012-11-30 | 2015-07-21 | Vidsys, Inc. | Tracking people and objects using multiple live and recorded surveillance camera video feeds |
US9129400B1 (en) * | 2011-09-23 | 2015-09-08 | Amazon Technologies, Inc. | Movement prediction for image capture |
US20170277967A1 (en) * | 2016-03-22 | 2017-09-28 | Tyco International Management Company | System and method for designating surveillance camera regions of interest |
US20170278367A1 (en) * | 2016-03-22 | 2017-09-28 | Tyco International Management Company | System and method for overlap detection in surveillance camera network |
US10084972B2 (en) | 2014-10-27 | 2018-09-25 | Axis Ab | Monitoring methods and devices |
US10089785B2 (en) * | 2014-07-25 | 2018-10-02 | mindHIVE Inc. | Real-time immersive mediated reality experiences |
US10347102B2 (en) | 2016-03-22 | 2019-07-09 | Sensormatic Electronics, LLC | Method and system for surveillance camera arbitration of uplink consumption |
US10475315B2 (en) | 2016-03-22 | 2019-11-12 | Sensormatic Electronics, LLC | System and method for configuring surveillance cameras using mobile computing devices |
US10665071B2 (en) | 2016-03-22 | 2020-05-26 | Sensormatic Electronics, LLC | System and method for deadzone detection in surveillance camera network |
US10733231B2 (en) | 2016-03-22 | 2020-08-04 | Sensormatic Electronics, LLC | Method and system for modeling image of interest to users |
US10764539B2 (en) | 2016-03-22 | 2020-09-01 | Sensormatic Electronics, LLC | System and method for using mobile device of zone and correlated motion detection |
US10977487B2 (en) | 2016-03-22 | 2021-04-13 | Sensormatic Electronics, LLC | Method and system for conveying data from monitored scene via surveillance cameras |
US11216847B2 (en) | 2016-03-22 | 2022-01-04 | Sensormatic Electronics, LLC | System and method for retail customer tracking in surveillance camera network |
US11557087B2 (en) | 2018-12-19 | 2023-01-17 | Sony Group Corporation | Image processing apparatus and image processing method for generating a strobe image using a three-dimensional model of an object |
US11601583B2 (en) | 2016-03-22 | 2023-03-07 | Johnson Controls Tyco IP Holdings LLP | System and method for controlling surveillance cameras |
Families Citing this family (160)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7522186B2 (en) * | 2000-03-07 | 2009-04-21 | L-3 Communications Corporation | Method and apparatus for providing immersive surveillance |
US9892606B2 (en) * | 2001-11-15 | 2018-02-13 | Avigilon Fortress Corporation | Video surveillance system employing video primitives |
US7868912B2 (en) * | 2000-10-24 | 2011-01-11 | Objectvideo, Inc. | Video surveillance system employing video primitives |
US8564661B2 (en) | 2000-10-24 | 2013-10-22 | Objectvideo, Inc. | Video analytic rule detection system and method |
US8711217B2 (en) | 2000-10-24 | 2014-04-29 | Objectvideo, Inc. | Video surveillance system employing video primitives |
US20050146605A1 (en) * | 2000-10-24 | 2005-07-07 | Lipton Alan J. | Video surveillance system employing video primitives |
JP2004072349A (en) * | 2002-08-05 | 2004-03-04 | Canon Inc | Image pickup device and its control method |
AU2003277240A1 (en) * | 2002-10-15 | 2004-06-07 | University Of Southern California | Augmented virtual environments |
US20040075741A1 (en) * | 2002-10-17 | 2004-04-22 | Berkey Thomas F. | Multiple camera image multiplexer |
JP3700707B2 (en) * | 2003-03-13 | 2005-09-28 | コニカミノルタホールディングス株式会社 | Measuring system |
US20040223054A1 (en) * | 2003-05-06 | 2004-11-11 | Rotholtz Ben Aaron | Multi-purpose video surveillance |
US7577636B2 (en) * | 2003-05-28 | 2009-08-18 | Fernandez Dennis S | Network-extensible reconfigurable media appliance |
US7633520B2 (en) * | 2003-06-19 | 2009-12-15 | L-3 Communications Corporation | Method and apparatus for providing a scalable multi-camera distributed video processing and visualization surveillance system |
US7259778B2 (en) * | 2003-07-01 | 2007-08-21 | L-3 Communications Corporation | Method and apparatus for placing sensors using 3D models |
AU2004306552A1 (en) * | 2003-10-09 | 2005-04-21 | De Beers Consolidated Mines Limited | Augmented video surveillance system |
US20070222894A1 (en) * | 2003-10-09 | 2007-09-27 | Gregory Cox | Enhanced Video Based Surveillance System |
GB2408879A (en) | 2003-12-03 | 2005-06-08 | Safehouse Internat Inc | Storing data recorded over a period of time |
US7428314B2 (en) * | 2003-12-03 | 2008-09-23 | Safehouse International Inc. | Monitoring an environment |
DE10358017A1 (en) * | 2003-12-11 | 2005-07-21 | Siemens Ag | 3D camera control |
JP4424031B2 (en) * | 2004-03-30 | 2010-03-03 | 株式会社日立製作所 | Image generating apparatus, system, or image composition method. |
US8055100B2 (en) * | 2004-04-02 | 2011-11-08 | The Boeing Company | Method and system for image registration quality confirmation and improvement |
US7773799B2 (en) * | 2004-04-02 | 2010-08-10 | The Boeing Company | Method for automatic stereo measurement of a point of interest in a scene |
US20070226616A1 (en) * | 2004-06-01 | 2007-09-27 | L-3 Communications Corporation | Method and System For Wide Area Security Monitoring, Sensor Management and Situational Awareness |
US8063936B2 (en) * | 2004-06-01 | 2011-11-22 | L-3 Communications Corporation | Modular immersive surveillance processing system and method |
US7813525B2 (en) * | 2004-06-01 | 2010-10-12 | Sarnoff Corporation | Method and apparatus for detecting suspicious activities |
AU2005251371A1 (en) * | 2004-06-01 | 2005-12-15 | L-3 Communications Corporation | Method and apparatus for video surveillance system |
US8289390B2 (en) * | 2004-07-28 | 2012-10-16 | Sri International | Method and apparatus for total situational awareness and monitoring |
US7639840B2 (en) * | 2004-07-28 | 2009-12-29 | Sarnoff Corporation | Method and apparatus for improved video surveillance through classification of detected objects |
JP4368767B2 (en) * | 2004-09-08 | 2009-11-18 | 独立行政法人産業技術総合研究所 | Abnormal operation detection device and abnormal operation detection method |
WO2006034135A2 (en) | 2004-09-17 | 2006-03-30 | Proximex | Adaptive multi-modal integrated biometric identification detection and surveillance system |
SE528330C2 (en) * | 2004-11-11 | 2006-10-24 | Totalfoersvarets Forskningsins | Method for monitoring a geographical area |
WO2006074161A2 (en) * | 2005-01-03 | 2006-07-13 | Vumii, Inc. | Systems and methods for night time surveillance |
EP1867167A4 (en) * | 2005-04-03 | 2009-05-06 | Nice Systems Ltd | Apparatus and methods for the semi-automatic tracking and examining of an object or an event in a monitored site |
US20080291278A1 (en) * | 2005-04-05 | 2008-11-27 | Objectvideo, Inc. | Wide-area site-based video surveillance system |
US7583815B2 (en) * | 2005-04-05 | 2009-09-01 | Objectvideo Inc. | Wide-area site-based video surveillance system |
US20060233461A1 (en) * | 2005-04-19 | 2006-10-19 | Honeywell International Inc. | Systems and methods for transforming 2d image domain data into a 3d dense range map |
US7945938B2 (en) * | 2005-05-11 | 2011-05-17 | Canon Kabushiki Kaisha | Network camera system and control method therefore |
US7720257B2 (en) * | 2005-06-16 | 2010-05-18 | Honeywell International Inc. | Object tracking system |
JP4909991B2 (en) * | 2005-09-12 | 2012-04-04 | タパング,カルロス | Frame-by-frame and pixel-by-pixel computer image camera frame matching model generation graphics image |
EP1941719A4 (en) * | 2005-10-04 | 2010-12-22 | Eugene J Alexander | System and method for calibrating a set of imaging devices and calculating 3d coordinates of detected features in a laboratory coordinate system |
EP1946567A4 (en) * | 2005-10-04 | 2009-02-18 | Eugene J Alexander | Device for generating three dimensional surface models of moving objects |
US7702131B2 (en) * | 2005-10-13 | 2010-04-20 | Fujifilm Corporation | Segmenting images and simulating motion blur using an image sequence |
US7697850B2 (en) * | 2005-10-31 | 2010-04-13 | Infoprint Solutions Company, Llc | Image-based printer system monitoring |
WO2007058900A2 (en) * | 2005-11-10 | 2007-05-24 | Alexander Eugene J | Calibrating an imaging device for generating three dimensional suface models of moving objects |
US7768527B2 (en) * | 2006-05-31 | 2010-08-03 | Beihang University | Hardware-in-the-loop simulation system and method for computer vision |
WO2008094172A2 (en) * | 2006-06-01 | 2008-08-07 | University Of Florida Research Foundation, Inc. | Radar microsensor for detection, tracking, and classification |
JP4603512B2 (en) * | 2006-06-16 | 2010-12-22 | 独立行政法人産業技術総合研究所 | Abnormal region detection apparatus and abnormal region detection method |
JP4215781B2 (en) * | 2006-06-16 | 2009-01-28 | 独立行政法人産業技術総合研究所 | Abnormal operation detection device and abnormal operation detection method |
JP5145664B2 (en) * | 2006-07-18 | 2013-02-20 | 富士ゼロックス株式会社 | Remote indication system |
US20080036864A1 (en) * | 2006-08-09 | 2008-02-14 | Mccubbrey David | System and method for capturing and transmitting image data streams |
JP4429298B2 (en) * | 2006-08-17 | 2010-03-10 | 独立行政法人産業技術総合研究所 | Object number detection device and object number detection method |
US8121356B2 (en) * | 2006-09-15 | 2012-02-21 | Identix Incorporated | Long distance multimodal biometric system and method |
US20080074494A1 (en) * | 2006-09-26 | 2008-03-27 | Harris Corporation | Video Surveillance System Providing Tracking of a Moving Object in a Geospatial Model and Related Methods |
US9544563B1 (en) | 2007-03-23 | 2017-01-10 | Proximex Corporation | Multi-video navigation system |
US7777783B1 (en) * | 2007-03-23 | 2010-08-17 | Proximex Corporation | Multi-video navigation |
US8929645B2 (en) | 2007-04-24 | 2015-01-06 | 21 Ct, Inc. | Method and system for fast dense stereoscopic ranging |
US8467628B2 (en) * | 2007-04-24 | 2013-06-18 | 21 Ct, Inc. | Method and system for fast dense stereoscopic ranging |
JP5538667B2 (en) * | 2007-04-26 | 2014-07-02 | キヤノン株式会社 | Position / orientation measuring apparatus and control method thereof |
ITMI20071016A1 (en) * | 2007-05-19 | 2008-11-20 | Videotec Spa | METHOD AND SYSTEM FOR SURPRISING AN ENVIRONMENT |
US7965865B2 (en) * | 2007-05-31 | 2011-06-21 | International Business Machines Corporation | Method, system, and program product for presenting electronic surveillance data |
US9305401B1 (en) * | 2007-06-06 | 2016-04-05 | Cognitech, Inc. | Real-time 3-D video-security |
US8009178B2 (en) * | 2007-06-29 | 2011-08-30 | Microsoft Corporation | Augmenting images for panoramic display |
US8542872B2 (en) * | 2007-07-03 | 2013-09-24 | Pivotal Vision, Llc | Motion-validating remote monitoring system |
JP5224142B2 (en) * | 2007-11-01 | 2013-07-03 | コニカミノルタホールディングス株式会社 | Imaging device |
RU2498408C2 (en) * | 2007-12-10 | 2013-11-10 | Абб Рисерч Лтд | Computer-implemented method and system for remote control of production process |
GB2457707A (en) * | 2008-02-22 | 2009-08-26 | Crockford Christopher Neil Joh | Integration of video information |
FR2932351B1 (en) * | 2008-06-06 | 2012-12-14 | Thales Sa | METHOD OF OBSERVING SCENES COVERED AT LEAST PARTIALLY BY A SET OF CAMERAS AND VISUALIZABLE ON A REDUCED NUMBER OF SCREENS |
US20100194861A1 (en) * | 2009-01-30 | 2010-08-05 | Reuben Hoppenstein | Advance in Transmission and Display of Multi-Dimensional Images for Digital Monitors and Television Receivers using a virtual lens |
JP2010206475A (en) * | 2009-03-03 | 2010-09-16 | Fujitsu Ltd | Monitoring support device, method thereof, and program |
US8862987B2 (en) * | 2009-03-31 | 2014-10-14 | Intel Corporation | Capture and display of digital images based on related metadata |
WO2010116364A1 (en) * | 2009-04-05 | 2010-10-14 | Tadsec Advanced Homeland Security Technologies Ltd | A security management system and method |
CN101527046B (en) * | 2009-04-28 | 2012-09-05 | 青岛海信数字多媒体技术国家重点实验室有限公司 | Motion detection method, device and system |
US8639046B2 (en) * | 2009-05-04 | 2014-01-28 | Mamigo Inc | Method and system for scalable multi-user interactive visualization |
US20120188333A1 (en) * | 2009-05-27 | 2012-07-26 | The Ohio State University | Spherical view point controller and method for navigating a network of sensors |
US10188295B2 (en) * | 2009-06-01 | 2019-01-29 | The Curators Of The University Of Missouri | Integrated sensor network methods and systems |
FR2946440B1 (en) * | 2009-06-05 | 2012-01-13 | Thales Sa | DEVICE FOR SIMULATION OF AN ENVIRONMENT OF A SYSTEM OF SUPERVISION OF AN INFRASTRUCTURE |
CN101635840B (en) * | 2009-08-26 | 2011-04-20 | 中兴通讯股份有限公司 | Video monitoring scene switching method and video monitoring system |
CN102055901B (en) * | 2009-11-05 | 2014-01-22 | 鸿富锦精密工业(深圳)有限公司 | Pan tile zoom (PTZ) camera and PTZ control method thereof |
US20110110557A1 (en) * | 2009-11-06 | 2011-05-12 | Nicholas Clark | Geo-locating an Object from Images or Videos |
EP2499827A4 (en) * | 2009-11-13 | 2018-01-03 | Pixel Velocity, Inc. | Method for tracking an object through an environment across multiple cameras |
MX2012011118A (en) * | 2010-03-26 | 2013-04-03 | Fortem Solutions Inc | Effortless navigation across cameras and cooperative control of cameras. |
DE102010003336A1 (en) * | 2010-03-26 | 2011-09-29 | Robert Bosch Gmbh | Method for the visualization of activity focuses in surveillance scenes |
CN102223473A (en) * | 2010-04-16 | 2011-10-19 | 鸿富锦精密工业(深圳)有限公司 | Camera device and method for dynamic tracking of specific object by using camera device |
US9569442B2 (en) * | 2010-04-27 | 2017-02-14 | The Radiant Group, Inc. | Geo-location video archive system and method |
US9635251B2 (en) * | 2010-05-21 | 2017-04-25 | Qualcomm Incorporated | Visual tracking using panoramas on mobile devices |
US8933986B2 (en) | 2010-05-28 | 2015-01-13 | Qualcomm Incorporated | North centered orientation tracking in uninformed environments |
US8531504B2 (en) | 2010-06-11 | 2013-09-10 | Intel Corporation | System and method for 3D video stabilization by fusing orientation sensor readings and image alignment estimates |
IL208910A0 (en) * | 2010-10-24 | 2011-02-28 | Rafael Advanced Defense Sys | Tracking and identification of a moving object from a moving sensor using a 3d model |
US20120105581A1 (en) * | 2010-10-29 | 2012-05-03 | Sony Corporation | 2d to 3d image and video conversion using gps and dsm |
US9185388B2 (en) * | 2010-11-03 | 2015-11-10 | 3Dmedia Corporation | Methods, systems, and computer program products for creating three-dimensional video sequences |
US8193909B1 (en) * | 2010-11-15 | 2012-06-05 | Intergraph Technologies Company | System and method for camera control in a surveillance system |
EP2641236A1 (en) * | 2010-11-17 | 2013-09-25 | Omron Scientific Technologies, Inc. | A method and apparatus for monitoring zones |
KR20120065817A (en) * | 2010-12-13 | 2012-06-21 | 한국전자통신연구원 | Method and system for providing intelligent access monitoring, intelligent access monitoring apparatus, recording medium for intelligent access monitoring |
MY171846A (en) * | 2010-12-27 | 2019-11-04 | Mimos Berhad | System and method for navigation and visualization |
US9746988B2 (en) * | 2011-05-23 | 2017-08-29 | The Boeing Company | Multi-sensor surveillance system with a common operating picture |
KR101302803B1 (en) * | 2011-05-26 | 2013-09-02 | 주식회사 엘지씨엔에스 | Intelligent image surveillance system using network camera and method therefor |
US20120300020A1 (en) * | 2011-05-27 | 2012-11-29 | Qualcomm Incorporated | Real-time self-localization from panoramic images |
FR2976107B1 (en) | 2011-05-30 | 2014-01-03 | Commissariat Energie Atomique | METHOD FOR LOCATING A CAMERA AND 3D RECONSTRUCTION IN A PARTIALLY KNOWN ENVIRONMENT |
US8368690B1 (en) | 2011-07-05 | 2013-02-05 | 3-D Virtual Lens Technologies, Inc. | Calibrator for autostereoscopic image display |
US8817067B1 (en) * | 2011-07-29 | 2014-08-26 | Google Inc. | Interface for applying a photogrammetry algorithm to panoramic photographic images |
EP2791909A4 (en) * | 2011-12-16 | 2015-06-24 | Thomson Licensing | Method and apparatus for generating 3d free viewpoint video |
US20130208123A1 (en) * | 2012-02-13 | 2013-08-15 | Honeywell International Inc. | Method and System for Collecting Evidence in a Security System |
US9195883B2 (en) | 2012-04-09 | 2015-11-24 | Avigilon Fortress Corporation | Object tracking and best shot detection system |
US9597016B2 (en) | 2012-04-27 | 2017-03-21 | The Curators Of The University Of Missouri | Activity analysis, fall detection and risk assessment systems and methods |
US9408561B2 (en) | 2012-04-27 | 2016-08-09 | The Curators Of The University Of Missouri | Activity analysis, fall detection and risk assessment systems and methods |
US9767598B2 (en) | 2012-05-31 | 2017-09-19 | Microsoft Technology Licensing, Llc | Smoothing and robust normal estimation for 3D point clouds |
US20130321564A1 (en) | 2012-05-31 | 2013-12-05 | Microsoft Corporation | Perspective-correct communication window with motion parallax |
US9846960B2 (en) | 2012-05-31 | 2017-12-19 | Microsoft Technology Licensing, Llc | Automated camera array calibration |
EP2860970A4 (en) * | 2012-06-08 | 2016-03-30 | Sony Corp | Information processing device, information processing method, program, and surveillance camera system |
US10084994B2 (en) * | 2012-12-12 | 2018-09-25 | Verint Systems Ltd. | Live streaming video over 3D |
US9648075B1 (en) * | 2012-12-18 | 2017-05-09 | Google Inc. | Systems and methods for providing an event map |
JP6171374B2 (en) * | 2013-02-06 | 2017-08-02 | ソニー株式会社 | Information processing apparatus, information processing method, program, and information processing system |
KR101383997B1 (en) * | 2013-03-08 | 2014-04-10 | 홍익대학교 산학협력단 | Real-time video merging method and system, visual surveillance system and virtual visual tour system using the real-time video merging |
KR101491324B1 (en) * | 2013-10-08 | 2015-02-06 | 현대자동차주식회사 | Apparatus for Taking of Image for Vehicle |
US9613448B1 (en) | 2014-03-14 | 2017-04-04 | Google Inc. | Augmented display of information in a device view of a display screen |
JP6357023B2 (en) * | 2014-06-06 | 2018-07-11 | 任天堂株式会社 | Information processing program, information processing apparatus, information processing apparatus control method, and information processing system |
US10412594B2 (en) | 2014-07-31 | 2019-09-10 | At&T Intellectual Property I, L.P. | Network planning tool support for 3D data |
SG10201407100PA (en) | 2014-10-30 | 2016-05-30 | Nec Asia Pacific Pte Ltd | System For Monitoring Event Related Data |
KR102282456B1 (en) * | 2014-12-05 | 2021-07-28 | 한화테크윈 주식회사 | Device and Method for displaying heatmap on the floor plan |
US10147210B1 (en) * | 2015-03-13 | 2018-12-04 | Amazon Technologies, Inc. | Data visualization system |
US10206630B2 (en) | 2015-08-28 | 2019-02-19 | Foresite Healthcare, Llc | Systems for automatic assessment of fall risk |
US11864926B2 (en) | 2015-08-28 | 2024-01-09 | Foresite Healthcare, Llc | Systems and methods for detecting attempted bed exit |
US9681111B1 (en) | 2015-10-22 | 2017-06-13 | Gopro, Inc. | Apparatus and methods for embedding metadata into video stream |
US10033928B1 (en) | 2015-10-29 | 2018-07-24 | Gopro, Inc. | Apparatus and methods for rolling shutter compensation for multi-camera systems |
US9792709B1 (en) | 2015-11-23 | 2017-10-17 | Gopro, Inc. | Apparatus and methods for image alignment |
US9973696B1 (en) | 2015-11-23 | 2018-05-15 | Gopro, Inc. | Apparatus and methods for image alignment |
US9848132B2 (en) | 2015-11-24 | 2017-12-19 | Gopro, Inc. | Multi-camera time synchronization |
US9667859B1 (en) | 2015-12-28 | 2017-05-30 | Gopro, Inc. | Systems and methods for determining preferences for capture settings of an image capturing device |
US9922387B1 (en) | 2016-01-19 | 2018-03-20 | Gopro, Inc. | Storage of metadata and images |
US9967457B1 (en) | 2016-01-22 | 2018-05-08 | Gopro, Inc. | Systems and methods for determining preferences for capture settings of an image capturing device |
US9665098B1 (en) | 2016-02-16 | 2017-05-30 | Gopro, Inc. | Systems and methods for determining preferences for flight control settings of an unmanned aerial vehicle |
US9973746B2 (en) | 2016-02-17 | 2018-05-15 | Gopro, Inc. | System and method for presenting and viewing a spherical video segment |
US9602795B1 (en) | 2016-02-22 | 2017-03-21 | Gopro, Inc. | System and method for presenting and viewing a spherical video segment |
US9743060B1 (en) | 2016-02-22 | 2017-08-22 | Gopro, Inc. | System and method for presenting and viewing a spherical video segment |
US10043058B2 (en) * | 2016-03-09 | 2018-08-07 | International Business Machines Corporation | Face detection, representation, and recognition |
EP3236440B1 (en) * | 2016-04-18 | 2021-03-03 | Hesotech GmbH automatisieren - visualisieren | Device, system and method for marking-free slope monitoring and/or building inspection |
CA3030850C (en) | 2016-06-28 | 2023-12-05 | Foresite Healthcare, Llc | Systems and methods for use in detecting falls utilizing thermal sensing |
US9934758B1 (en) | 2016-09-21 | 2018-04-03 | Gopro, Inc. | Systems and methods for simulating adaptation of eyes to changes in lighting conditions |
US10268896B1 (en) | 2016-10-05 | 2019-04-23 | Gopro, Inc. | Systems and methods for determining video highlight based on conveyance positions of video content capture |
US9973792B1 (en) | 2016-10-27 | 2018-05-15 | Gopro, Inc. | Systems and methods for presenting visual information during presentation of a video segment |
KR20180092163A (en) * | 2017-02-08 | 2018-08-17 | 삼성전자주식회사 | Electronic device and server for video playback |
US10194101B1 (en) | 2017-02-22 | 2019-01-29 | Gopro, Inc. | Systems and methods for rolling shutter compensation using iterative process |
US10187607B1 (en) | 2017-04-04 | 2019-01-22 | Gopro, Inc. | Systems and methods for using a variable capture frame rate for video capture |
JP6871801B2 (en) * | 2017-05-11 | 2021-05-12 | キヤノン株式会社 | Image processing equipment, image processing method, information processing equipment, imaging equipment and image processing system |
US11113887B2 (en) * | 2018-01-08 | 2021-09-07 | Verizon Patent And Licensing Inc | Generating three-dimensional content from two-dimensional images |
JP7119425B2 (en) * | 2018-03-01 | 2022-08-17 | ソニーグループ株式会社 | Image processing device, encoding device, decoding device, image processing method, program, encoding method and decoding method |
JP6828708B2 (en) * | 2018-03-29 | 2021-02-10 | 京セラドキュメントソリューションズ株式会社 | Control device, surveillance system, and surveillance camera control method |
US10902680B2 (en) * | 2018-04-03 | 2021-01-26 | Saeed Eslami | Augmented reality application system and method |
US10574975B1 (en) | 2018-08-08 | 2020-02-25 | At&T Intellectual Property I, L.P. | Method and apparatus for navigating through panoramic content |
US11196968B1 (en) * | 2018-08-08 | 2021-12-07 | Alarm.Com Incorporated | System for generating drone video feed overlays based on property monitoring system data |
JP2020086700A (en) * | 2018-11-20 | 2020-06-04 | ソニー株式会社 | Image processing device, image processing method, program, and display device |
US10902685B2 (en) * | 2018-12-13 | 2021-01-26 | John T. Daly | Augmented reality remote authoring and social media platform and system |
US11587420B2 (en) * | 2019-03-14 | 2023-02-21 | Johnson Controls Tyco IP Holdings LLP | Systems and methods of combining RFID and VMS for people tracking and intrusion detection |
WO2020213426A1 (en) * | 2019-04-18 | 2020-10-22 | ソニー株式会社 | Image processing device, image processing method, and program |
KR102152319B1 (en) * | 2019-08-09 | 2020-09-04 | 주식회사 벡터시스 | Method of calculating position and size of object in 3d space and video surveillance system using the same |
TWI726536B (en) | 2019-12-16 | 2021-05-01 | 財團法人工業技術研究院 | Image capturing method and image capturing apparatus |
CN111526328B (en) * | 2020-03-18 | 2022-01-04 | 深圳市华橙数字科技有限公司 | Video monitoring inspection method, device, terminal and storage medium |
DE102020213288A1 (en) * | 2020-10-21 | 2022-04-21 | Robert Bosch Gesellschaft mit beschränkter Haftung | Display device for a video surveillance system, video surveillance system and method |
CN112584060A (en) * | 2020-12-15 | 2021-03-30 | 北京京航计算通讯研究所 | Video fusion system |
CN112584120A (en) * | 2020-12-15 | 2021-03-30 | 北京京航计算通讯研究所 | Video fusion method |
Citations (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5164979A (en) * | 1989-11-21 | 1992-11-17 | Goldstar Co., Ltd. | Security system using telephone lines to transmit video images to remote supervisory location |
US5182641A (en) * | 1991-06-17 | 1993-01-26 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Composite video and graphics display for camera viewing systems in robotics and teleoperation |
US5276785A (en) * | 1990-08-02 | 1994-01-04 | Xerox Corporation | Moving viewpoint with respect to a target in a three-dimensional workspace |
US5289275A (en) * | 1991-07-12 | 1994-02-22 | Hochiki Kabushiki Kaisha | Surveillance monitor system using image processing for monitoring fires and thefts |
US5495576A (en) * | 1993-01-11 | 1996-02-27 | Ritchey; Kurtis J. | Panoramic image based virtual reality/telepresence audio-visual system and method |
US5696892A (en) * | 1992-07-10 | 1997-12-09 | The Walt Disney Company | Method and apparatus for providing animation in a three-dimensional computer generated virtual world using a succession of textures derived from temporally related source images |
US5708764A (en) * | 1995-03-24 | 1998-01-13 | International Business Machines Corporation | Hotlinks between an annotation window and graphics window for interactive 3D graphics |
US5714997A (en) * | 1995-01-06 | 1998-02-03 | Anderson; David P. | Virtual reality television system |
US5729471A (en) * | 1995-03-31 | 1998-03-17 | The Regents Of The University Of California | Machine dynamic selection of one video camera/image of a scene from multiple video cameras/images of the scene in accordance with a particular perspective on the scene, an object in the scene, or an event in the scene |
US5847755A (en) * | 1995-01-17 | 1998-12-08 | Sarnoff Corporation | Method and apparatus for detecting object movement within an image sequence |
US5850469A (en) * | 1996-07-09 | 1998-12-15 | General Electric Company | Real time tracking of camera pose |
US5850352A (en) * | 1995-03-31 | 1998-12-15 | The Regents Of The University Of California | Immersive video, including video hypermosaicing to generate from multiple video views of a scene a three-dimensional video mosaic from which diverse virtual video scene images are synthesized, including panoramic, scene interactive and stereoscopic images |
US5963664A (en) * | 1995-06-22 | 1999-10-05 | Sarnoff Corporation | Method and system for image combination using a parallax-based technique |
US6009190A (en) * | 1997-08-01 | 1999-12-28 | Microsoft Corporation | Texture map construction method and apparatus for displaying panoramic image mosaics |
US6018349A (en) * | 1997-08-01 | 2000-01-25 | Microsoft Corporation | Patch-based alignment method and apparatus for construction of image mosaics |
US6108437A (en) * | 1997-11-14 | 2000-08-22 | Seiko Epson Corporation | Face recognition apparatus, method, system and computer readable medium thereof |
US6144375A (en) * | 1998-08-14 | 2000-11-07 | Praja Inc. | Multi-perspective viewer for content-based interactivity |
US6144797A (en) * | 1996-10-31 | 2000-11-07 | Sensormatic Electronics Corporation | Intelligent video information management system performing multiple functions in parallel |
US6166763A (en) * | 1994-07-26 | 2000-12-26 | Ultrak, Inc. | Video security system |
US20010043738A1 (en) * | 2000-03-07 | 2001-11-22 | Sawhney Harpreet Singh | Method of pose estimation and model refinement for video representation of a three dimensional scene |
US20020089973A1 (en) * | 2000-11-17 | 2002-07-11 | Yehuda Manor | System and method for integrating voice, video, and data |
US20020094135A1 (en) * | 2000-05-11 | 2002-07-18 | Yeda Research And Development Co., Limited | Apparatus and method for spatio-temporal alignment of image sequences |
US6424370B1 (en) * | 1999-10-08 | 2002-07-23 | Texas Instruments Incorporated | Motion based event detection system and method |
US20020140698A1 (en) * | 2001-03-29 | 2002-10-03 | Robertson George G. | 3D navigation techniques |
US20030014224A1 (en) * | 2001-07-06 | 2003-01-16 | Yanlin Guo | Method and apparatus for automatically generating a site model |
US6512857B1 (en) * | 1997-05-09 | 2003-01-28 | Sarnoff Corporation | Method and apparatus for performing geo-spatial registration |
US6522787B1 (en) * | 1995-07-10 | 2003-02-18 | Sarnoff Corporation | Method and system for rendering and combining images to form a synthesized view of a scene containing image information from a second image |
US20030085992A1 (en) * | 2000-03-07 | 2003-05-08 | Sarnoff Corporation | Method and apparatus for providing immersive surveillance |
US6668082B1 (en) * | 1997-08-05 | 2003-12-23 | Canon Kabushiki Kaisha | Image processing apparatus |
US20040071367A1 (en) * | 2000-12-05 | 2004-04-15 | Michal Irani | Apparatus and method for alignmemt of spatial or temporal non-overlapping images sequences |
US20040240562A1 (en) * | 2003-05-28 | 2004-12-02 | Microsoft Corporation | Process and system for identifying a position in video using content-based video timelines |
US20040239763A1 (en) * | 2001-06-28 | 2004-12-02 | Amir Notea | Method and apparatus for control and processing video images |
US20050024206A1 (en) * | 2003-06-19 | 2005-02-03 | Supun Samarasekera | Method and apparatus for providing a scalable multi-camera distributed video processing and visualization surveillance system |
US20050057687A1 (en) * | 2001-12-26 | 2005-03-17 | Michael Irani | System and method for increasing space or time resolution in video |
US6989745B1 (en) * | 2001-09-06 | 2006-01-24 | Vistascape Security Systems Corp. | Sensor device for use in surveillance system |
US7124427B1 (en) * | 1999-04-30 | 2006-10-17 | Touch Technologies, Inc. | Method and apparatus for surveillance using an image server |
Family Cites Families (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US526785A (en) * | 1894-10-02 | Theodore g | ||
US529471A (en) * | 1894-11-20 | Filter | ||
US3018349A (en) * | 1960-04-08 | 1962-01-23 | Rt & E Corp | Fuse construction |
JPH0628132A (en) | 1992-07-09 | 1994-02-04 | Mitsubishi Heavy Ind Ltd | Monitor device |
JP3365182B2 (en) | 1995-12-27 | 2003-01-08 | 三菱電機株式会社 | Video surveillance equipment |
WO1997037494A1 (en) | 1996-03-29 | 1997-10-09 | Barry Katz | Surveillance system having graphic video integration controller and full motion video switcher |
JP3718579B2 (en) * | 1996-11-19 | 2005-11-24 | 住友電気工業株式会社 | Video surveillance system |
JPH10188183A (en) | 1996-12-26 | 1998-07-21 | Matsushita Electric Works Ltd | Display operation device for automatic fire alarm equipment |
JPH10210546A (en) | 1997-01-17 | 1998-08-07 | Sony Corp | Radio communication system, stationary station equipment and mobile station equipment |
JPH10240908A (en) * | 1997-02-27 | 1998-09-11 | Hitachi Ltd | Video composing method |
WO2000016243A1 (en) | 1998-09-10 | 2000-03-23 | Mate - Media Access Technologies Ltd. | Method of face indexing for efficient browsing and searching ofp eople in video |
JP2001202531A (en) * | 1999-10-15 | 2001-07-27 | Hitachi Kokusai Electric Inc | Method for editing moving image |
JP4564117B2 (en) | 1999-10-20 | 2010-10-20 | 綜合警備保障株式会社 | Security system |
AU2001280071A1 (en) | 2000-08-16 | 2002-02-25 | Sagarmatha Ltd. | Method and system for automatically producing optimized personalized offers |
US7599696B2 (en) * | 2004-06-25 | 2009-10-06 | Searete, Llc | Frequency reuse techniques in mote-appropriate networks |
US20060007308A1 (en) | 2004-07-12 | 2006-01-12 | Ide Curtis E | Environmentally aware, intelligent surveillance device |
-
2002
- 2002-07-24 US US10/202,546 patent/US7522186B2/en not_active Expired - Fee Related
- 2002-10-31 IL IL16140002A patent/IL161400A0/en unknown
- 2002-10-31 JP JP2003566812A patent/JP2005517253A/en active Pending
- 2002-10-31 KR KR1020047006666A patent/KR100940142B1/en not_active IP Right Cessation
- 2002-10-31 CA CA002466085A patent/CA2466085A1/en not_active Abandoned
- 2002-10-31 EP EP02806001A patent/EP1449180A4/en not_active Withdrawn
- 2002-10-31 WO PCT/US2002/034913 patent/WO2003067537A2/en active Application Filing
-
2009
- 2009-03-13 US US12/404,261 patent/US20090237508A1/en not_active Abandoned
Patent Citations (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5164979A (en) * | 1989-11-21 | 1992-11-17 | Goldstar Co., Ltd. | Security system using telephone lines to transmit video images to remote supervisory location |
US5276785A (en) * | 1990-08-02 | 1994-01-04 | Xerox Corporation | Moving viewpoint with respect to a target in a three-dimensional workspace |
US5182641A (en) * | 1991-06-17 | 1993-01-26 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Composite video and graphics display for camera viewing systems in robotics and teleoperation |
US5289275A (en) * | 1991-07-12 | 1994-02-22 | Hochiki Kabushiki Kaisha | Surveillance monitor system using image processing for monitoring fires and thefts |
US5696892A (en) * | 1992-07-10 | 1997-12-09 | The Walt Disney Company | Method and apparatus for providing animation in a three-dimensional computer generated virtual world using a succession of textures derived from temporally related source images |
US5495576A (en) * | 1993-01-11 | 1996-02-27 | Ritchey; Kurtis J. | Panoramic image based virtual reality/telepresence audio-visual system and method |
US6166763A (en) * | 1994-07-26 | 2000-12-26 | Ultrak, Inc. | Video security system |
US5714997A (en) * | 1995-01-06 | 1998-02-03 | Anderson; David P. | Virtual reality television system |
US5847755A (en) * | 1995-01-17 | 1998-12-08 | Sarnoff Corporation | Method and apparatus for detecting object movement within an image sequence |
US5708764A (en) * | 1995-03-24 | 1998-01-13 | International Business Machines Corporation | Hotlinks between an annotation window and graphics window for interactive 3D graphics |
US5729471A (en) * | 1995-03-31 | 1998-03-17 | The Regents Of The University Of California | Machine dynamic selection of one video camera/image of a scene from multiple video cameras/images of the scene in accordance with a particular perspective on the scene, an object in the scene, or an event in the scene |
US5850352A (en) * | 1995-03-31 | 1998-12-15 | The Regents Of The University Of California | Immersive video, including video hypermosaicing to generate from multiple video views of a scene a three-dimensional video mosaic from which diverse virtual video scene images are synthesized, including panoramic, scene interactive and stereoscopic images |
US5963664A (en) * | 1995-06-22 | 1999-10-05 | Sarnoff Corporation | Method and system for image combination using a parallax-based technique |
US6522787B1 (en) * | 1995-07-10 | 2003-02-18 | Sarnoff Corporation | Method and system for rendering and combining images to form a synthesized view of a scene containing image information from a second image |
US5850469A (en) * | 1996-07-09 | 1998-12-15 | General Electric Company | Real time tracking of camera pose |
US6144797A (en) * | 1996-10-31 | 2000-11-07 | Sensormatic Electronics Corporation | Intelligent video information management system performing multiple functions in parallel |
US6512857B1 (en) * | 1997-05-09 | 2003-01-28 | Sarnoff Corporation | Method and apparatus for performing geo-spatial registration |
US6009190A (en) * | 1997-08-01 | 1999-12-28 | Microsoft Corporation | Texture map construction method and apparatus for displaying panoramic image mosaics |
US6018349A (en) * | 1997-08-01 | 2000-01-25 | Microsoft Corporation | Patch-based alignment method and apparatus for construction of image mosaics |
US6668082B1 (en) * | 1997-08-05 | 2003-12-23 | Canon Kabushiki Kaisha | Image processing apparatus |
US6108437A (en) * | 1997-11-14 | 2000-08-22 | Seiko Epson Corporation | Face recognition apparatus, method, system and computer readable medium thereof |
US6144375A (en) * | 1998-08-14 | 2000-11-07 | Praja Inc. | Multi-perspective viewer for content-based interactivity |
US7124427B1 (en) * | 1999-04-30 | 2006-10-17 | Touch Technologies, Inc. | Method and apparatus for surveillance using an image server |
US6424370B1 (en) * | 1999-10-08 | 2002-07-23 | Texas Instruments Incorporated | Motion based event detection system and method |
US6985620B2 (en) * | 2000-03-07 | 2006-01-10 | Sarnoff Corporation | Method of pose estimation and model refinement for video representation of a three dimensional scene |
US7522186B2 (en) * | 2000-03-07 | 2009-04-21 | L-3 Communications Corporation | Method and apparatus for providing immersive surveillance |
US20010043738A1 (en) * | 2000-03-07 | 2001-11-22 | Sawhney Harpreet Singh | Method of pose estimation and model refinement for video representation of a three dimensional scene |
US20030085992A1 (en) * | 2000-03-07 | 2003-05-08 | Sarnoff Corporation | Method and apparatus for providing immersive surveillance |
US20020094135A1 (en) * | 2000-05-11 | 2002-07-18 | Yeda Research And Development Co., Limited | Apparatus and method for spatio-temporal alignment of image sequences |
US20020097798A1 (en) * | 2000-11-17 | 2002-07-25 | Yehuda Manor | System and method for coding and decoding |
US20020089973A1 (en) * | 2000-11-17 | 2002-07-11 | Yehuda Manor | System and method for integrating voice, video, and data |
US20040071367A1 (en) * | 2000-12-05 | 2004-04-15 | Michal Irani | Apparatus and method for alignmemt of spatial or temporal non-overlapping images sequences |
US20020140698A1 (en) * | 2001-03-29 | 2002-10-03 | Robertson George G. | 3D navigation techniques |
US20040239763A1 (en) * | 2001-06-28 | 2004-12-02 | Amir Notea | Method and apparatus for control and processing video images |
US20030014224A1 (en) * | 2001-07-06 | 2003-01-16 | Yanlin Guo | Method and apparatus for automatically generating a site model |
US6989745B1 (en) * | 2001-09-06 | 2006-01-24 | Vistascape Security Systems Corp. | Sensor device for use in surveillance system |
US20050057687A1 (en) * | 2001-12-26 | 2005-03-17 | Michael Irani | System and method for increasing space or time resolution in video |
US20040240562A1 (en) * | 2003-05-28 | 2004-12-02 | Microsoft Corporation | Process and system for identifying a position in video using content-based video timelines |
US20050024206A1 (en) * | 2003-06-19 | 2005-02-03 | Supun Samarasekera | Method and apparatus for providing a scalable multi-camera distributed video processing and visualization surveillance system |
Cited By (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8102406B2 (en) * | 2005-11-15 | 2012-01-24 | Yissum Research Development Company Of The Hebrew University Of Jerusalem | Method and system for producing a video synopsis |
US20090219300A1 (en) * | 2005-11-15 | 2009-09-03 | Yissum Research Deveopment Company Of The Hebrew University Of Jerusalem | Method and system for producing a video synopsis |
US8949235B2 (en) | 2005-11-15 | 2015-02-03 | Yissum Research Development Company Of The Hebrew University Of Jerusalem Ltd. | Methods and systems for producing a video synopsis using clustering |
US8514248B2 (en) | 2005-11-15 | 2013-08-20 | Yissum Research Development Company Of The Hebrew University Of Jerusalem Ltd. | Method and system for producing a video synopsis |
US8482609B1 (en) * | 2006-11-22 | 2013-07-09 | Sightlogix, Inc. | Methods and apparatus related to surveillance system marketing, planning and/or integration |
US8350908B2 (en) | 2007-05-22 | 2013-01-08 | Vidsys, Inc. | Tracking people and objects using multiple live and recorded surveillance camera video feeds |
US20080292140A1 (en) * | 2007-05-22 | 2008-11-27 | Stephen Jeffrey Morris | Tracking people and objects using multiple live and recorded surveillance camera video feeds |
US9172919B2 (en) | 2008-06-10 | 2015-10-27 | Mindmancer AB | Selective viewing of a scene |
US8965047B1 (en) * | 2008-06-10 | 2015-02-24 | Mindmancer AB | Selective viewing of a scene |
US20090310865A1 (en) * | 2008-06-13 | 2009-12-17 | Jenn Hwan Tarng | Video Surveillance System, Annotation And De-Annotation Modules Thereof |
US9071626B2 (en) | 2008-10-03 | 2015-06-30 | Vidsys, Inc. | Method and apparatus for surveillance system peering |
US20110317017A1 (en) * | 2009-08-20 | 2011-12-29 | Olympus Corporation | Predictive duty cycle adaptation scheme for event-driven wireless sensor networks |
US9344704B2 (en) | 2009-11-10 | 2016-05-17 | Lg Electronics Inc. | Method of recording and replaying video data, and display device using the same |
WO2011059193A3 (en) * | 2009-11-10 | 2011-10-20 | Lg Electronics Inc. | Method of recording and replaying video data, and display device using the same |
US20110157368A1 (en) * | 2009-12-31 | 2011-06-30 | Samsung Techwin Co., Ltd. | Method of performing handoff between photographing apparatuses and surveillance apparatus using the same |
US8934014B2 (en) * | 2010-09-21 | 2015-01-13 | ScienBiziP Consulting(Shenzhen)Co., Ltd. | Electronic device and switching method for the same |
US20120069191A1 (en) * | 2010-09-21 | 2012-03-22 | Hon Hai Precision Industry Co., Ltd. | Electronic device and switching method for the same |
US8971641B2 (en) * | 2010-12-16 | 2015-03-03 | Microsoft Technology Licensing, Llc | Spatial image index and associated updating functionality |
US20120155778A1 (en) * | 2010-12-16 | 2012-06-21 | Microsoft Corporation | Spatial Image Index and Associated Updating Functionality |
US9129400B1 (en) * | 2011-09-23 | 2015-09-08 | Amazon Technologies, Inc. | Movement prediction for image capture |
US9087386B2 (en) | 2012-11-30 | 2015-07-21 | Vidsys, Inc. | Tracking people and objects using multiple live and recorded surveillance camera video feeds |
US10089785B2 (en) * | 2014-07-25 | 2018-10-02 | mindHIVE Inc. | Real-time immersive mediated reality experiences |
US10084972B2 (en) | 2014-10-27 | 2018-09-25 | Axis Ab | Monitoring methods and devices |
US10475315B2 (en) | 2016-03-22 | 2019-11-12 | Sensormatic Electronics, LLC | System and method for configuring surveillance cameras using mobile computing devices |
US20170278367A1 (en) * | 2016-03-22 | 2017-09-28 | Tyco International Management Company | System and method for overlap detection in surveillance camera network |
US10192414B2 (en) * | 2016-03-22 | 2019-01-29 | Sensormatic Electronics, LLC | System and method for overlap detection in surveillance camera network |
US10318836B2 (en) * | 2016-03-22 | 2019-06-11 | Sensormatic Electronics, LLC | System and method for designating surveillance camera regions of interest |
US10347102B2 (en) | 2016-03-22 | 2019-07-09 | Sensormatic Electronics, LLC | Method and system for surveillance camera arbitration of uplink consumption |
US20170277967A1 (en) * | 2016-03-22 | 2017-09-28 | Tyco International Management Company | System and method for designating surveillance camera regions of interest |
US10665071B2 (en) | 2016-03-22 | 2020-05-26 | Sensormatic Electronics, LLC | System and method for deadzone detection in surveillance camera network |
US10733231B2 (en) | 2016-03-22 | 2020-08-04 | Sensormatic Electronics, LLC | Method and system for modeling image of interest to users |
US10764539B2 (en) | 2016-03-22 | 2020-09-01 | Sensormatic Electronics, LLC | System and method for using mobile device of zone and correlated motion detection |
US10977487B2 (en) | 2016-03-22 | 2021-04-13 | Sensormatic Electronics, LLC | Method and system for conveying data from monitored scene via surveillance cameras |
US11216847B2 (en) | 2016-03-22 | 2022-01-04 | Sensormatic Electronics, LLC | System and method for retail customer tracking in surveillance camera network |
US11601583B2 (en) | 2016-03-22 | 2023-03-07 | Johnson Controls Tyco IP Holdings LLP | System and method for controlling surveillance cameras |
US11557087B2 (en) | 2018-12-19 | 2023-01-17 | Sony Group Corporation | Image processing apparatus and image processing method for generating a strobe image using a three-dimensional model of an object |
Also Published As
Publication number | Publication date |
---|---|
EP1449180A2 (en) | 2004-08-25 |
IL161400A0 (en) | 2004-09-27 |
WO2003067537A3 (en) | 2003-11-20 |
KR100940142B1 (en) | 2010-02-03 |
KR20040053257A (en) | 2004-06-23 |
US7522186B2 (en) | 2009-04-21 |
WO2003067537A2 (en) | 2003-08-14 |
EP1449180A4 (en) | 2008-05-14 |
JP2005517253A (en) | 2005-06-09 |
CA2466085A1 (en) | 2003-08-14 |
US20030085992A1 (en) | 2003-05-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7522186B2 (en) | Method and apparatus for providing immersive surveillance | |
EP2913796B1 (en) | Method of generating panorama views on a mobile mapping system | |
US20030012410A1 (en) | Tracking and pose estimation for augmented reality using real features | |
JP5093053B2 (en) | Electronic camera | |
US11632602B2 (en) | Automated determination of image acquisition locations in building interiors using multiple data capture devices | |
JP2010504711A (en) | Video surveillance system and method for tracking moving objects in a geospatial model | |
CN105898107B (en) | A kind of target object grasp shoot method and system | |
US9756277B2 (en) | System for filming a video movie | |
Georgel et al. | An industrial augmented reality solution for discrepancy check | |
CN101542538A (en) | Method and system for modeling light | |
US20110187703A1 (en) | Method and system for object tracking using appearance model | |
CN102917171A (en) | Small target locating method based on pixel | |
Côté et al. | Live mobile panoramic high accuracy augmented reality for engineering and construction | |
WO2017017790A1 (en) | Image generation device, image generation system, and image generation method | |
KR101073432B1 (en) | Devices and methods for constructing city management system integrated 3 dimensional space information | |
WO2012081319A1 (en) | Video monitoring apparatus | |
JP2023546739A (en) | Methods, apparatus, and systems for generating three-dimensional models of scenes | |
Böhm | Multi-image fusion for occlusion-free façade texturing | |
US9305401B1 (en) | Real-time 3-D video-security | |
WO2021160476A1 (en) | A camera system with multiple cameras | |
JP2004030408A (en) | Three-dimensional image display apparatus and display method | |
JP2005004487A (en) | Apparatus and method for processing surround image photographed on capture path | |
KR101036107B1 (en) | Emergency notification system using rfid | |
KR101996907B1 (en) | Apparatus for tracking object | |
JP2005157635A (en) | Congestion level measuring device, facility control system and congestion level measuring method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |