MXPA06001363A - Method and system for performing video flashlight - Google Patents

Abstract

In an immersive surveillance system, videos or other data from a large number of cameras and other sensors is managed and displayed by a video processing system overlaying the data within a rendered 2D or 3D model of a scene. The system has a viewpoint selector configured to allow a user to selectively identify a viewpoint from which to view the site. A video control system receives data identifying the viewpoint and based on the viewpoint automatically selects a subset of the plurality of cameras that is generating video relevant to the view from the viewpoint, and causes video from the subset of cameras to be transmitted to the video processing system. As the viewpoint changes, the cameras communicating with the video processor are changed to hand off to cameras generating relevant video to the new position. Playback in the immersive environment is provided by synchronization of time stamped recordings of video. Navigation of the viewpoint on constrained paths in the model or map-based navigation is also provided.

Description

METHOD AND SYSTEM FOR MAKING INSTANT VIDEO TAKING DESCRIPTION OF THE INVENTION The present invention relates generally to image processing, and, more specifically, to systems and methods for providing immersive surveillance, in which videos of a number of cameras in A particular site or environment is handled by superimposing the video of these cameras on a 2D or 3D model of a scene. Immersed surveillance systems provide visualization of security camera systems at a site. The video output of the cameras in an immersed system is combined with a computerized interpreted model of the site. These systems allow the user to move through the virtual model and see the appropriate video automatically present in a virtual immersed environment that contains the video feeds in real time of the cameras. An example of such a system is the VIDEO FLASHLIGHT ™ system shown in the published North American patent application 2003/0085992 published on May 8, 2003, which is incorporated herein by reference. Systems of this type may encounter a problem of broadband communications. An immersive surveillance system can be formed of tens, hundreds or even thousands of cameras all generating video simultaneously.

When they propagate over the communication network of the system or are otherwise transmitted to a central display station, terminal or other display unit where the immersed system is viewed, this collectively constitutes a very large amount of propagation data. To accommodate this amount of data, either a large number of cables or other connection systems with a large amount of broadband must be provided to carry all the data, or the system may encounter problems with the limits of the transfer rate of data, meaning that part of the video that is potentially important to security personnel may simply not be available at the viewing station or terminal for viewing, lowering the effectiveness of surveillance. In addition, previous immersed systems did not provide immersive video playback of the system, but only for the user to view the current video of the cameras, or to reproduce the immersed immersion previously displayed without any freedom to change the location. Also, in such systems, the user navigates essentially without restrictions, usually by controlling his point of view or perspective with a mouse or joystick. Although this gives a greater freedom of investigation and movement to the user, it also allows a user to essentially lose himself in the scene he sees, and has difficulty moving the viewing point back to a useful position. Accordingly, it is an object of the invention to provide a system and method for an immersed video system that improves the system in these areas. In one embodiment, the present invention generally relates to a system and method for providing a system for handling large numbers of videos by superimposing them within a 2D or 3D model of a scene, especially in a system such as that shown in the application published North American patent 2003/0085992, which is incorporated herein by reference. According to one aspect of the invention, a surveillance system for a site has a plurality of cameras each producing a respective video of a respective portion of the site. A perspective selector is configured to allow a user to selectively identify a perspective on the site from which to view the site or a portion of it. A video processing system is coupled with the perspective selector to receive the data indicative of the perspective thereof, and coupled with the plurality of cameras to receive the videos thereof. The video processing system has access to a computerized model of the site. The video processing system interprets from the computer model real-time images that correspond to a view of the site from the perspective, in which at least a portion of at least one of the videos is superimposed on the computer model. The video processing system displays the images in real time to a viewer. A video control system receives the data identifying the perspective and based on the perspective automatically selects a subset of the plurality of cameras that are generating the appropriate video for the site view from the perspective interpreted by the video processing system, and causes the video of the subset of cameras to be transmitted to the video processing system. According to another aspect of the invention, a surveillance system for a site has a plurality of cameras each generating a respective data stream. Each data stream includes a series of video frames each corresponding to a real-time image of a part of the site, and each frame has a dater indicative of a time when the real-time image was made by the associated camera. A recording system receives and records the data streams of the cameras. A video processing system connects to the recorder and provides playback of the recorded data streams. The video processing system has an interpreter that during the reproduction of the recorded data streams interprets the images for a view from a reproduction perspective of a model of the site and applies to it the recorded data streams of at least two of the appropriate cameras for the sight. The video processing system includes a synchronizer that receives the recorded data streams from the recording system during playback. The synchronizer distributes the streams of recorded data to the interpreter in synchronized form so that each image is interpreted with video frames of which all were taken at the same time. In accordance with another aspect of the invention, an immersed surveillance system has a plurality of cameras each producing a respective video of a respective portion of a site. An image processor is connected to the plurality of cameras and receives the video thereof. The image processor produces an image interpreted for a perspective based on a model of the site and combined with a lurality of videos that are appropriate for the perspective. A display device couples with the image processor and displays the interpreted image. A vision controller coupled to the image processor provides the same the data defining the perspective that is displayed. The vision controller also engages with and receives input from an interactive navigation component that allows a user to selectively modify the perspective. According to a further aspect of the invention, a method comprises receiving data from an input device indicating a selection of a perspective and a field of view to view at least part of the video from a plurality of cameras in a surveillance system . A subgroup of one or more of the cameras that are in places such that those cameras can generate appropriate video for the field of view is identified. The video of the camera subgroup is transmitted to a video processor. A video display is generated with the video processor by interpreting the images of a computerized model of the site, where the images correspond to the field of view of the perspective of the site in which at least a portion of at least one of the videos are superimposed on the computer model. The images are displayed to a viewer, and the video of at least part of the cameras that are not in the subgroup is not allowed to be transmitted to the video interpretation system, thereby reducing the amount of data that is transmitted to the processor. video. According to another aspect of the invention, a method for a surveillance system comprises recording the data streams of system cameras in one or more recorders. The data streams are recorded together in synchronized format, with each frame having a datum indicative of a time when the real-time image was made - by the associated camera. There is communication with the recorders to cause the recorders to transmit the recorded data streams from the cameras to a video processor. The recorded data streams are received and the frames of them are synchronized based on the daters thereof. The data is received from an input device indicating a selection of a perspective and field of view to see at least part of the video of the cameras. A video display is generated with the video processor by interpreting the images of the computerized model of the site, where the images correspond to the field of view of the site perspective in which at least a portion of at least two of the videos is superimposed over the computer model. For each interpreted image, the video superimposed on it is of the frames that have all the timers that indicate the same period of time. The images are displayed to a viewer. According to yet another method of the invention, the recorded data streams of the cameras are transmitted to a video processor. The data is received from the data of an input device indicating a selection of a perspective and field of view to see at least part of the video of the cameras. A video display is generated with the video processor when interpreting the images of the computerized model of the site. The images correspond to the field of view of the perspective of the site in which at least a portion of at least two of the videos are superimposed on the computer model. The images are displayed to a viewer. The input indicating a change of perspective and / or field of vision is received. The entry is restricted so that an operator can only input changes to the view point or perspective for a new field of view that are the limited subset of all possible changes. The limited subset corresponds to a path through the site. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 shows a diagram illustrating how the traditional mode of operation in a video control room is transformed into a viewing environment for the global display of several cameras and effective violation management; Figure 2 illustrates a module that provides a comprehensive set of tools to evaluate a threat; Figure 3 illustrates the video overlay that is presented on a high resolution screen with control interfaces for the DVR and PTZ units; Figure 4 illustrates the information presented to the user as highlighted icons on a map display and as a textual list view, - Figure 5 illustrates the regions that are colored in color to indicate whether an alarm is active or not; Figure 6 illustrates a scalable system architecture for the Video Camera System Blanket of some cameras or a few hundred cameras quickly. Figure 7 illustrates a Vision Selection System of the present invention; Figure 8 is a diagram of capture, reproduction and display of synchronized data in a system of the invention; Figure 9 is a diagram of a data integrator and display in such a system; Figure 10 shows a map-based display used with an immersed video system; Figure 11 shows the software architecture of the system. To facilitate understanding, identical reference numbers have been used, whenever possible, to designate identical elements that are common to the figures.

The need for effective surveillance and military security installations or other secure locations is more urgent than ever. Effective day-to-day operations need to continue together with reliable security and effective response for perimeter violations and access control violations. Video-based operations and surveillance are increasingly being deployed at military bases and other sensitive sites. For example, in the Barracks of Campbell in Heidelberg, Germany there are 54 installed cameras and the military barracks of Villa Mark Twain a planned installation can have more than a hundred cameras. Current modes of video operations allow only traditional modes of viewing videos on TV monitors without being aware of a global environment 3D context. In addition, video-based violation detection is typically not existing and the video display is not directly connected to the violation detection systems. VIDEO FLASHLIGHT ™ (VFA), Alarm Evaluation (AA), and Vision-Based Alarm (VBA) technologies can be used to provide: (i) comprehensive visualization of, for example, the perimeter area to multiplex without video joins multiple in a 3D model of the environment, and (ii) detection of sudden movement and other intelligent alarms such as violation of perimeter, forgotten object and detection of vagrants in these locations. In the present application, reference is made to the immersive surveillance system named VIDEO FLASHLIGHT ™, which is exemplary of an environment in which the invention can be advantageously applied, although it should be understood that the invention can be used in different systems of the VIDEO FLASHLIGHT system. ™, with similar benefits. VIDEO FLASHLIGHT ™ is a system in which live video is mapped into and combined with a 2D or 3D computer model of a site, and the operator can move a perspective through the scene and view the combined interpreted imagery and the Live video appropriately applied from a variety of viewing points in the space of the scene. In a surveillance system of this type, cameras can provide comprehensive coverage of the area of interest. Videos are recorded continuously. The videos are interpreted seamless in the 3D model of the airport or other location to provide global contextual visualization. Automatic Video Based Alarms can detect security breaches, for example in doors and fences. The Video Camera System Blanket (BVC) will continually track the responsible individual and allow the security personnel to then navigate immersively in space and time to return at the time of the security breach and then move quickly in time to follow to the individual until the present moment. Figure 1 shows how the traditional mode of operation in a video control room is transformed into a viewing environment for global viewing of multiple cameras and effective violation handling. In summary, the BVC system provides the following capabilities. A single unified display shows the videos in real time interpreted without unions with respect to the 3D model of the environment. The user can freely navigate through the environment while viewing videos from multiple cameras with respect to the 3D model. The user can return quickly and intuitively in time and review events that have occurred in the past. The user can quickly get high-resolution video of an event by simply clicking on the model to direct one or more turn / tilt / telephoto cameras. The system allows an operator to detect a security breach, and allows the operator to follow the or to individuals through multi-camera tracking. The system also allows security personnel to view the current location and the alarm event through FA deployment or as archived video segments. VIDEO FLASHLIGHT ™ and Vision-Based Alarm Modules The FLASHLIGHT ™ VIDEO and the Vision-Based Alarm system comprise four different modules: Video Evaluation Module (VIDEO FLASHLIGHT ™ Interpretation). Vision Alert Alarm Module Alarm Evaluation Module System Operation Information Module The video evaluation module (VIDEO FLASHLIGHT ™) provides an integrated interface to watch a covered video in a 3D model. This allows a guard to navigate seamlessly through a large site and quickly assess any threats that occur within a large area. No other command and control system has this video overlay capability. The system superimposes the video of both fixed cameras and PTZ cameras, and uses the DVR (digital video recorder) modules to record and play back events. As best illustrated in Figure 2, this module provides a comprehensive set of tools to assess a threat. An alarm situation typically breaks down into 3 parts: Pre-evaluation: An alarm has occurred, and it is necessary to evaluate events that lead to the alarm. Competition technology uses DVR devices or a pre-alarm buffer to store information from an alarm. However, the pre-alarm buffers are often too short, and the DVR devices only display video from a particular camera using complex control interfaces. The Video Evaluation module on the other hand allows immersed synchronous viewing of all video streams at any time using an intuitive GUI. Live evaluation: An alarm is happening, and there is a need to quickly locate the live video that shows the alarm, assess the situation, and respond quickly. In addition, there is a need to monitor areas surrounding the alarms simultaneously to check additional activity. Most existing systems provide views of the scene using an uneven bank of monitors, and take time and familiarity with the scene to be able to switch between camera views to find the surrounding areas. Post-evaluation: An alarm situation has ended, and the point of interest has been changed from the field of view of the fixed cameras. There is a need to follow the point of interest through the scene. The FLASHLIGHT ™ VIDEO Module allows simple quick control of PTZ cameras using intuitive mouse click control in the 3D model. The video overlay is presented on a high-resolution screen with control interfaces for the DVR and PTZ units as shown in Figure 3.

Inputs and Outputs The VIDEO FLASHLIGHT ™ Video Evaluation module takes the image data and sensor data that has been put into the computer memory in a known format, takes the estimates that were calculated during the construction of the initial model, and covers them on the 3D model. In summary, the inputs and outputs for the Video Evaluation Module are: Inputs: Video of fixed cameras located in a known location and in a known format; Video and Position information from the location of the PTZ cameras; 3D postures of each camera with respect to the model. (These 3D postures are recovered using calibration methods during the establishment of the system); 3D model of the scene (This 3D model is retrieved using an existing 3D model, commercial 3D model building methods, or • any other computer model building method) A desired view given by an operator using a joystick or keyboard , or automatically controlled by an alarm, configured by the user. Outputs: An image in memory that shows the video snapshot of the desired view. PTZ command to control PTZ positions DVR controls to return and pre-view events in the past. The main features in the system Video evaluation are: Visualization of the 3D model of the site to provide a rich 3D context. (Navigation in space) Overlay of the video in real time on the 3D model to provide video based evaluation. Synchronous control of multiple DVR units to recover without joints and superimpose the video on the 3D model. (Time navigation) Control and overlay of the PTZ video by simple mouse click on the 3D model. No special knowledge of where the camera is needed by the guard to move the PTZ units. The system automatically decides which PTZ unit is best suited to see the area of interest. Automated video selection based on the selected perspective allows the system to integrate video matrix switchers to provide virtual access to a very large number of cameras. The level of detail interpretation engine provides seamless navigation through very large 3D sites. User Interface for Video Evaluation (VIDEO FLASHLIGHT ™) Visualization: there are two views that are presented to the user in the Video Evaluation module, (a) a view of the 3D interpreter and (b) a Map Insertion View. The 3D interpreter view displays the site model with the video or video plane overlays located in the 3D space. This provides detailed information of the site. The map insertion view is a top-down view of the site with the overlays of the occupied surface of the camera. This view provides a general context of the site. Navigation: Navigating through preferred perspectives: Navigation through the site is produced using a cycle of preferred perspectives. The left and right arrow keys allow you to fly between these main perspectives. There are multiple perspective cycles defined at different levels of detail (different zoom levels in the perspective). The up and down arrow keys are used to navigate through these zoom levels. Navigation with the mouse: The user can click the left side on any of the video overlays to center, that point within the preferred perspective. This allows the user to easily track a moving object that is moving through the fields of view of the overlapping cameras. The user can click the left side on the video planes to make the transition in a preferred superimposed perspective. Navigation with map insertion: The user clicks on the left side on the occupied surfaces of the map insertion to move to the preferred perspective for a particular camera. The user can also click on the left side and drag the mouse to identify a set of occupied surfaces to obtain an enlarged view in preferred focus of the site. PTZ Controls: Moving PTZ with the mouse: The user can change the left-hand click on the model or the map insertion view to move the PTZ units to a specific location. The system then automatically determines which PTZ units are suitable to see that point and moves those PTZs accordingly to see in that location. While pressing the left button, the user can rotate the mouse wheel to zoom in or out in focus of the nominal zoom that the system had previously selected. When the PTZ video is viewed, the system will automatically center the view in the primary PTZ perspective. Moving between PTZs: When multiple PTZ units see a particular point, the preferred view can be assigned to the PTZ unit closest to that point. The user can switch the preferred view to other PTZ units that see that point when using the left and right arrow keys. Controlling PTZ from a Bird View: In this mode, the user can control the PTZ while viewing all fixed camera views and a bird's eye view of the field. Using the up and down arrow keys the guard can move between the bird's eye view and zoom in on the views of the PTZ video. PTZ control is done by clicking on the site's displacement or the insertion map as described in the above. DVR Controls: Selecting the DVR Control Panel: The user can press ctrl-v to upload a panel to control the DVR units in the system. DVR playback controls: by default the DVR subsystem propagates the live video to the video evaluation station, ie the video station where the immersed display is displayed to the user. The user can select the pause button to stop the video at the current point in time. The user then switches to DVR mode. In the DVR mode the user is able to play forward or backward synchronously in time until the limits of the recorded video are reached. While the video is playing in DVR mode, the user is able to navigate through of the site as described in the previous Navigation section. DVR Search Controls: The user can search all videos controlled by DVR at a given point in time by specifying the time of interest where he wants to change. The system can move all the video to that point in time and then pause until the user selects another DVR command. Alarm Evaluation Module Map-based browser-Review The map-based browser is a visualization tool for large areas. Its main component is a scrollable and zoomed orthographic map that contains different components to represent sensors (fixed cameras), PTZ cameras, fence sensors) and symbolic information (text, system operation, limit lines, movement of an object over time). Accompanying this view is a descending example at scale of the map that is not displaceable nor can zoom in or zoom out whose purpose is to represent the field of vision port for the large view, display the state of the components not in the field of view of the large view, and provide another method to change the viewing port of the large view. The components in the map-based deployment are able to have different behaviors and functions based on the visualization application. For alarm evaluation, the components are capable of changing color and blinking based on the state of the sensor alarm that represents the visual component. When there is an unconfirmed alarm - on the sensor, it will be red and will flash on the map-based display. Once all the alarms for this sensor are confirmed, the component is red but will no longer blink. After all alarms for the sensors have been secured, the component will return to its normal green color. Sensors can also be disabled through the map-based component after they are yellow until they are trained again. Other modules are able to access the components in the map display when sending events through an API (application program interface). The alarm list is a module that adds alarms through many alarm stations and presents them as a textual list to the user for the alarm evaluation. Using this API, the alarm list is able to change the states of the map-based components whereupon such component change will change in color and flash. The alarm list is able to classify alarms by time, priority, name of the sensor, or type of alarm. It is also capable of controlling Video Snapshots to see the video that has occurred at the time of an alarm. For the video-based alarm, the alarm list is able to display the video that triggered the alarm in the video display window and save the video that caused the alarm to disk. Map-based Browser Interaction with Video Snapshots The components in the map-based browser have the ability to control the virtual view and the video feed for the deployment of snapshots of Video through the API exposed over a connection of TCP / IP. This offers the user another method to navigate a 3D scene in Video Snapshots. In addition to changing the virtual view, the components in the map-based deployment can also control the DVR and create a virtual trip where the camera changes its location after a specified amount of time has elapsed. This last function allows video snapshots to create personalized trips that follow a person through a 3D scene. Map-based browser deployment The alarm evaluation station integrates multiple alarms through multiple machines and presents them to the guard. The information is presented to the user as highlighted icons on a map display and as a textual list view (Figure 4). The map view allows the guard to identify the threat in its correct spatial context. It also acts as a hyperlink to control the Video Evaluation station to enslave the video immediately to fix it in the areas of interest.

The list view allows the user to evaluate the Alarm in terms of the type of alarm, the alarm time and also to see video fragments annotated for any alarms. Main Features and Specifications The main features of the AA station are as follows: It presents the user with alarms from Vision Alert stations, dry contact inputs, and other customary alarms that are integrated into the system. Symbolic information is superimposed on a 2D sitemap to provide the context in which an alarm is occurring. The textual information is displayed sorted by time or priority to get detailed information about any alarm. Enslaves the VIDEO FLASHLIGHT ™ Station to automatically navigate in the specific perspective of the Alarm guided by the user input. Preview the annotated video fragments of the current alarms. Save the video segments for later use. The user can manage the alarms when confirming the alarms, and once an alarm condition is resolved, play the alarm. The user can also disable specific alarms to allow pre-planned activity to occur without generating alarms. User Interface for Alarm Evaluation Module Display: The alarm list view integrates alarms for all Vision Alarm Stations and, external alarm sources or system faults in a single list. This list is updated in real time. The list can be classified by time or by alarm priorities. The map view shows on the maps where the alarms are occurring. The user can scroll around the map or selected areas when using the insertion map. The 'Map' view assigns alarms in symbolic regions marked to indicate where the alarm is happening. These regions are color coded to indicate whether an alarm is active or not, as illustrated in Figure 5. The preferred color coding for the alarm symbols is (a) Red: Unsecured alarm Active due to suspicious behavior, ( b) Gray: alarm due to malfunction in the system, (c) Yellow: Video source disabled, and (d) Green: All clear, no active alarm. Video preview: For video-based alarms a preview fragment of the activity is also available. These can be previewed in the video fragment window. Alarm confirmation: In the list view, the user is able to confirm alarms to indicate that he has observed. You can confirm alarms individually or you can ensure all alarms on a particular sensor from the map view by clicking the right side or to get a drop-down menu and select confirmation. If the alarm condition has been resolved, the user can indicate this by selecting the safe option in the list view. Once an alarm is secured, it will be removed from the list view. The user can ensure all alarms for a particular sensor by clicking on the right side in the region to get a drop-down menu and select the safe option. This will clear all alarms for that sensor in the list view as well. In addition, the user can disable the alarms of any sensor when using the drop-down menu and select the option to disable. Any new alarm will be automatically confirmed and secured for all disabled sources. Video Evaluation Station Control: The user can move the Evaluation Station Video to a preferred view of the map view by clicking the left side on the region marked for a particular sensor. The map view control will send a navigation command to the video evaluation station to move it. The user typically clicks on an active alarm area to evaluate the situation using the Video Evaluation module. Video of the Instantaneous System Installation Architecture and Hardware Implementation A scalable system architecture has been developed for the Video Camera System Blanket of some cameras or a few hundred cameras quicklymV.

(Figure 6). The invention is based on having modular filters that can be interconnected to propagate data therebetween. These filters can be sources (video capture devices, PTZ communicators, Data Base readers, etc.), transformations (Algorithm modules such as motion detectors, trackers) or collectors (such as rendering engines, writers of databases) . These are built with inherent chaining capability that allows multiple components to run in parallel. This allows the system to optimally use the resources available on multi-processor platforms. The architecture also provides sources and collectors that can send and receive propagation data through the network. This allows the system to be easily distributed across multiple PC workstations with simple configuration changes. Filtering modules are loaded dynamically at runtime based on simple XML-based configuration files. These define the connection capacity between the modules and define each of the specific behaviors of the filters. This allows an integrator to quickly configure the variety of different end-user applications and span across multiple machines without having to modify any code. The main characteristics of the system architecture are: System scalability: - Able to connect through multiple processors, multiple machines.

Modular capacity of the component: The modular architecture maintains clear separations between software modules, with a mechanism to propagate data between them. Each of the modules is defined as a filter with a common interface to propagate data between them. Component Update Capacity: it is easy to replace system components without affecting the rest of the system infrastructure. Data Propagation Architecture: Based on the propagation of data between the modules in the system. He has an inherent understanding of time through the system and is able to synchronize and merge data from multiple sources. Data Storage Architecture: Ability to simultaneously record and stream multiple meta-data streams through the processor. It provides search and revision capabilities in each node which can be driven by the deployment based on Maps / Models and other clients. It is powered by the main SQL database engine. The system of the invention provides efficient communication with the sensors of the system, which are generally cameras but can be other types of sensors, such as smoke or fire detectors, motion detectors, open door detectors, or any of a variety of security sensors. Similarly, sensor data is generally video, but may also be other kinds of data such as alarm indications of detected motion or intrusion, fire, or any other sensor data. A main requirement of a surveillance system is to be able to select the data that is observed at any given time. Video cameras can spread dozens, hundreds or thousands of video sequences. The view selection system herein is a means for viewing, handling, storing, reproducing, and analyzing this video data as well as data from other sensors. Vista Selection System Figure 7 illustrates the selection criteria for video. Instead of entering the individual sensor camera numbers (eg, camera 1, camera 2, camera 3, etc.), the surveillance data display is based on a perspective 3 selector that provides a camera position selected virtual or perspective, means a set of data that define a point and field of view from that point, to the system to indicate the appropriate real-time view of the surveillance data to be displayed. The position of the virtual camera can be derived from the operator input, such as electronic data received from, for example, an interactive station with an input device such as a joystick, or the output of an alarm sensor, such as an automated response to an event without operator control. Once the perspective is selected, the system then automatically calculates which sensors are suitable for the field of view for that particular perspective. In the preferred embodiment, the system calculates which subset of the system sensors appears in the field of view of the video overlay area of interest with a priority program / video selector 5, which is coupled with the perspective selector 3 and receives from it the data that defines the perspective of the virtual camera. The system by means of the priority program / video selector 5 then dynamically switches to the chosen sensors, ie the subset of appropriate sensors, and avoids switching to the other sensors of the system by controlling a video switch 7. The video switch 7 is coupled to the inputs of all the sensors (including the cameras) in the system, which generate a large number of video or data feeds 9. Based on the control of the selector 5, the switch 7 switches on the communication link to carry the data feeds from the subset of appropriate sensors, and to prevent transmission of the data feeds from the other sensors, to transmit only one set reduced from 11 data feeds that are appropriate for, the perspective of the virtual camera selected for the video overlay station 13. According to a preferred embodiment, the switch 7 is an analog matrix switch controlled by the video priority / selector program 5 to switch to a smaller number of video feeds 11 from an original larger set 9 to the station 13 of video overlay. This system is used especially when the feeds are an analog video that is transmitted to the video evaluation station for viewing on a limited set of wired lines. In such a system, the flow of analog signals from the video cameras that are not appropriate for the present field of vision is turned off so as not to input the wires to the video evaluation station, and the video feeds of the cameras that are appropriate lights are physically turned on to pass through those connection wires. Alternatively, video cameras can produce digital video, and this can be transmitted to digital video servers connected to a local area network that links them to the video evaluation station, so that digital video can be propagated to the video evaluation station on the network. In such a system, the video switch is part of the video evaluation station, and communicates with the individual digital video server over the network. If the server has a camera that is appropriate, the switch directs it to propagate that video to the video evaluation station. If the video is not appropriate, the switch sends a command to the video server to not send your video. The result is a reduction in traffic on the network, and greater efficiency in transmitting the appropriate video to the video station for viewing. The video is shown interpreted on the top of a 2D or 3D model of the scene, that is, in an immersed video system, as described in the published North American patent application 2003/0085992. The video overlay station 13 produces the video constituting the display of the surveillance system immersed in real time by combining the appropriate data feeds 11, especially video imagery, with images interpreted in real time from views created by an interpretation system. that uses a 2-D model, or preferably 3-D, of the system site, which may also generally be referred to as geospatial information, and preferably stored in a data storage device 15 accessible to the interpretation component of the video overlay station 13. The appropriate geospatial information that is displayed interpreted in each screen image is determined by the perspective selector 3.

The video overlay station 13 prepares each image of the display video by applying, for example, as a texture, the video imagery appropriate to the image interpreted in appropriate portions of the field of view. In addition, the geospatial information is selected in the same way. The perspective selector determines what geospatial information is displayed. Once the video for the display is interpreted and combined with the appropriate sensor data streams, it is sent to a display device to be displayed to the operator. These four blocks, video selector 3, priority program / video selector 5, video switch 7, and video overlay station 13, provide the management of the display of potentially thousands of camera views. Someone with experience in the. The technician will easily understand that these functions can be supported in a single computerized system with their functions carried out largely by software, or they can be discretely distributed computational components that perform their respective tasks. Where the system relies on a network to transmit video to the video station, then it is preferred that the perspective selector 3, the video selector, the video switch 7 and the video overlay and interpretation station are all expressed in the Same video station computer using software modules for each one. If the system is more reliant on wired video feeds and off-line or analog communications, it is better if the components are discrete circuits, with the video switch being linked by wires to a current physical switch near the video source to turn it off and save broadband when the video is inappropriate for the selected field of view. Capture, Reproduction and Display of Synchronized Data With the ability to visualize live data from thousands of sensors, there is a need to store the data in a certain way that allows them to reproduce as if the data were live. Most digital video systems store data from each camera separately. However, according to the present embodiment, the system is configured to synchronously record video data, re-read them synchronously, and deploy them in the immersed surveillance deployment (preferably VIDEO FLASHLIGHT ™). Figure 2 shows a block diagram of the capture, playback and display of synchronized data in VIDEO FLASHLIGHT ™. A recorder controller 17 synchronizes the recording of all data, in which each stored data frame includes data, a dater, identifying the time when it was created. In the preferred embodiment, this synchronized recording is performed by Ethernet control of the DVR devices 19, 21. The recorder controller 17 also controls the playback of the DVR devices, and ensures that the recording and playback times start at exactly the same time. In the reproduction, the recorder controller 17 causes the DVR devices to reproduce the appropriate video in a selected virtual camera perspective starting from a point in the time selected by the operator. The data is propagated over the local network to a data synchronizer 23 that buffered the reproduced data to handle any real-time glide of the data reading, reads information such as the timers to correctly synchronize the multiple data streams of data. so that all the frames of the various recorded data streams are of the same time period, and then distribute the synchronized data to the immersed monitoring display system, for example, VIDEO FLASHLIGHT ™, and to any other components in the system, for example , interpretation components, processing components, and data fusion components, generally indicated in 27. In an analogous modality, the analogue video of the cameras is taken to a circuit frame, where it is divided. A part of the video goes to the Map Viewer station, as discussed in the above. The other part goes with the video of the other three cameras through a cable box to the recorder, which stores all four video feeds in a synchronized mode. The video is recorded and also, if appropriate for the current viewing point, it is transmitted by wiring to the video station for interpretation on the display immersed by VIDEO FLASHLIGHT ™. In a more digital environment, there are a number of digital video servers each attached to approximately four to twelve of the cameras. The cameras are connected to a digital video server connected to the surveillance system's network. The digital video server has connected to it, usually in the same physical location, a digital video recorder (DVR) that stores the video of the cameras. The server propagates the video to the video station for application to the interpreted images for immersed deployment, if appropriate, and does not transmit the video if the video switch, discussed in the above, does not direct it. In the same way that the live video data is applied to the immersed surveillance display as discussed above, the recorded synchronized data is incorporated into a real-time immersion watch display displayed to the operator. The operator is able to move through the model of the scene and see the scene interpreted from his selected perspective, and use the video or other data of the time period of interest. The recorder controller and the data synchronizer are preferably separate dedicated computer systems, but can be supported on one or more computer systems or electronic components, and the functions thereof can be achieved by hardware and / or software in those systems, such as those With experience in the art they will easily understand. Integrator and Data Visualization In addition to video sensors, ie cameras, there may also be hundreds of thousands of non-video based sensors in a system. The visualization and management of these sensors is also very important. As best shown in Figure 3, a Symbolic Data Integrator 27 collects data from different metadata sources (such as video alarms, access control alarms, object traces) in real time. The rule machine 29 combines multiple pieces of information to generate complex situation decisions, and makes several determinations as a matter of automated response, dependent on the different sets of metadata entries and the predetermined response rules provided thereto. The rules can be based on the geo-location of the sensors for example, and can also be based on dynamic operator input. A Symbolic Information Display 31 determines how to present the determinations of the rule machine 29 to the user (e.g., color / icon). The results of the rules machine determinations then, when appropriate, are used to control the perspective of a Video Evaluation Station through a View Controller Interface. For example, a certain type of alarm can automatically alert the operator and cause the operator display device to immediately display a surveillance view immersed from a virtual camera perspective that sees the location of the sensor that transmits the metadata that identify the alarm condition. The components of this system can be separate electronic hardware, but can also be achieved by using appropriate software components in a computer system on or shared with the operator's display terminal.

Restricted Navigation An immersive surveillance visualization system provides an unlimited means to navigate in space and time. In daily use, however, only certain locations in space and time are appropriate for manual application. The present system therefore applies restricted space and time navigation in the VIDEO FLASHLIGHT ™ system. An analogy can be derived between a car and a train; a train can only move along certain trajectories in space, while a car can move in an arbitrary number of trajectories. An example of such an implementation is to limit the easy viewing of locations where there is no sensor coverage. This is implemented by analyzing the desired perspective provided by the operator using an input device such as a joystick or a mouse click on a computer screen. The system calculates the desired perspective by calculating the change in the 3D display position that the point clicked on the screen can center. The system then makes a determination if the perspective contains any sensors that can or are potentially visible, and, sensitive to a determination that such a sensor exists, changes the perspective, while, sensitive to a determination that there is no such sensor, the system It will not change the perspective. Hierarchies of restricted movements have also been developed, as described below. Navigation based on Maps or Events Like the navigation within the same immersed video display, such as by means of mouse clicks on the points on the display or a joystick, etc., the system allows an operator to navigate using events externally directed. For example, as seen in the screen shot of Figure 4, a VIDEO FLASHLIGHT ™ display has a map display 37 in addition to the display 39 of immersed video interpreted. The map display shows a list of alarms 41 as well as a map of the area. By simply clicking on any of a listed alarm or map, the perspective is immediately changed to a new perspective corresponding to that location, and the VIDEO FLASHLIGHT ™ display is interpreted for the new perspective. The map display 37 is altered in color or an icon appears to indicate a sensor event, as in Figure 4, a violation of the wall is detected. The operator can then click on that indicator in the map display 37 and the perspective for the immersed display 39 will immediately switch to a pre-programmed perspective for that sensor event, which will then be displayed.

PTZ control The image processing system known as the world coordinates (x, y, z) of each pixel in each camera sensor as well as in the 3D model. When the user 5 clicks a mouse on a point in the 2D or 3D immersed video model display, the system identifies the optimal camera to see the field of view centered at that point. In some cases, the best-located camera for viewing the location is a turn-tilt-telephoto camera (PTZ), which can be pointed in a different direction from that needed to see the desired location. In this case, the system calculates the position parameters (for example, the pan, tilt angle, zoom angle of a panoramic sensor, steered tilt), directs the PTZ to that location by transmitting the appropriate electrical control signals to the camera over the network, and receives the PTZ video, which is inserted into the immersed surveillance display. The details of this process are discussed further in the following. PTZ Transfer As described in the above, the system knows the world coordinates (x, y, z) of each pixel in each camera sensor as well as in the 3D model. Because it knows the position of the camera sensor, the system can choose which sensor to use based on the desired visualization requirements. For example, in the preferred embodiment, when a scene contains more than 1 PTZ camera, the system automatically selects one or more PTZs based entirely or in part on the 2D or 3D coordinates projected on the ground (eg, latitude-longitude) of the PTZ locations and the point of interest. In the preferred mode, the system calculates the distance to the target of each PTZ based on its 2D or 3D coordinates, and chooses to use the PTZ that is closest to the target to see the target. Additional rules include explaining occlusions of the 3D objects that are modeled in the scene, as well as areas with no output for the values of spin, tilt, telescope, and these rules are applied in a determination of which camera is optimal to see a selected point. particular on the site. PTZ Calibration PTZ requires calibration for the 3D scene. This calibration is done by selecting the 3D points (x, y, z) in the VIDEO FLASHLIGHT ™ model that are visible from the PTZ. The PTZ is pointed at that location and the mechanical values of rotation, tilt, telephoto are read and stored. This is repeated at several different points in the model, distributed around the location of the PTZ camera. A linear adjustment is then performed at the points separately in the turning, tilting and telephoto gaps respectively. The zoom space is sometimes not linear and can be done before adjusting a query from the manufacturers or empirical. The linear adjustment is performed dynamically each time it is required to move the PTZ. When a PTZ is requested to point to a 3D location, the rotation and tilt angles in the model space (fi le) are calculated for the desired location with respect to the PTZ location. Fi and tit are then calculated for all calibration points with respect to the location of PTZ. The linear adjustments are then made separately in the mechanical values of rotation, inclination and telephoto stored from the moment of the calibration using weighted least squares that weigh more strongly these fi and tit of calibration that are closer to the fi and theta corresponding to the location desired. The least-squares adjustment uses the calibration keys as x-coordinate inputs and uses the PTZ's measured slew, tilt and telephoto values as coordinate values y. The least squares adjustment then retrieves the parameters that gave an output value and 'for a given input value'. The fi ttata corresponding to the desired point are then fed into a computer program that expresses the parametric equation (the value? X ') which then returns the mechanical pivot point (tilt, telephoto) to the PTZ camera. These determined values are then used to determine the appropriate electrical control signals to transmit to the PTZ unit to control its position, orientation and zoom. Immersed surveillance display index One benefit of integrating video and other information into the VIDEO FLASHLIGHT ™ system is that data can be indexed in ways that were previously not possible. For example, if the VIDEO FLASHLIGHT ™ system is connected to a license reading system that is installed at multiple checkpoints, then a simple query of the VIDEO FLASHLIGHT ™ system (using the rule-based system described previously) can show instantly the imagery of all the cases of that vehicle. Typically this is a very laborious task. VIDEO FLASHLIGHT ™ is the "operating system" of the sensors. The spatial and algorithmic fusion of the sensors greatly improves the probability of detection and probability of correct identification of a target in surveillance-type applications. These sensors can be of any passive or active type, including video, acoustic, seismic, magnetic, IR, etc. Figure 5 shows the software architecture of the system. Essentially all sensor information is fed to the system through sensor controllers and these are shown at the bottom of the graph. Auxiliary sensors 45 are any active / passive sensors, such as those listed above, for effective surveillance in a site. The appropriate information of all these sensors together with the live video of the fixed cameras 47 and 49 and PTZ are fed to a Meta-data Manager 51 that fuses all this information. There is a rule-based processing at this level 51 that defines the basic artificial intelligence of the system. The rules have the ability to control any device 45, 47 or 49 under the meta-data manager 51, and may be rules such as "record video only when any door is opened in Runner A", "track any target with a PTZ camera automatically in Zone B ", or" Make VIDEO FLASHLIGHT ™ fly and zoom in on a person that matches a profile or diaphragm criteria ". These rules have direct consequences on the view that is interpreted by the 3D Interpretation Machine 53 (at the top of the Meta-Data Manager, and receives data from it for viewing), since it is usually the visual information that is verifies at the end, and typically the users / guards wish to fly over the objects of interest, zoom in, and evaluate the situation additionally with the visual feedback provided by the system. All the capabilities mentioned in the above can be used remotely with the available TCP / IP Services. This module 55 exposes the API to remote sites that may not physically have the equipment, but wish to use the services. Remote users have the ability to see the output of the application as the local user does, since the interpreted image is sent to the remote site in real time. This is also a means of compressing all the information (video sensors, auxiliary sensors and spatial information) in a portable format, that is, the interpreted real-time program output, since a user can evaluate all this information remotely as You can do it at the same time without having any equipment except a screen and some kind of input device like a keyboard. An example can be accessing all this information with a laptop. The system has a display terminal in which the various display components of the system are displayed to the user, as shown in Figure 6. The display device includes a graphical user interface (GUI) that displays, among other things , interpreted video surveillance and data for the perspective selected by the operator and accepts the mouse inputs, joystick or others to change the perspective or otherwise monitor the system. Navigation Control dß Perspective In previous designs of immersed surveillance systems, the user navigated freely in a 3D environment without any restriction on perspective. In the present design, there are restrictions on the user's potential viewing points, thereby increasing the visual quality and decreasing the complexity of the user's interaction. One of the disadvantages of a completely free navigation is that if the user is not familiar with the 3D controls (which is not an easy task since there are more than 7 parameters for the control that include the position (x, y, z) , rotation (tilt, azimuth, roll), and the field of view, it is easy to get lost or create unsatisfactory viewing points). This is why the system helps the user to create perfect viewing points, since the video projections are in discrete parts of a continuous environment and these parts should be viewed in the best possible way. Assistance can be in the form of providing, through the operator console, perspective hierarchies, rotation by pulsation and zoom, and map-based navigation, etc. Perspective Hierarchy Perspective hierarchical navigation takes advantage of the discrete nature of the video projections and essentially decreases the complexity of the user's interaction of the 7+ dimensions to approximately 4 or less depending on the application. This is done by creating a perspective hierarchy in the environment. A possible way to create this hierarchy is as follows; the lowest level of the hierarchy represents the display points exactly equivalent to the positions and orientations of the camera in the scene with a possibly larger field of view to achieve a larger context. Higher level display points show more and more camera clusters and the highest node in the hierarchy represents a perspective that sees all the camera projections in the scene. Once this hierarchy is established, instead of controlling absolute parameters such as position and orientation, the user makes the simple decision of where to see in the scene and the system decides and creates the best view for the user to use the hierarchy. The user can also explicitly raise or lower the hierarchy or move to even nodes; that is, viewing points laterally separated in the hierarchy at the same level.

Since all the nodes are perfect viewing points that are carefully selected in advance depending on the needs of the client, and depending on the camera configuration of the site, the user can navigate the scene when moving from one view to another with a simple option of low order complexity, and the visual quality is above a certain threshold controlled all the time. Click Rotation and Zoom This navigation scheme makes the joystick unnecessary as a user interface device for the system, and a mouse is the preferred input device. When the user is investigating a displayed scene as a view of a perspective, he can further control the perspective by clicking on the object of interest in the 3D scene. This entry will cause a change in the parameters of the perspective so that the view is rotated, and the pulsed object is in the center of the view. Once the object is centered, it can be zoomed in using additional input using the mouse. This centric object navigation makes navigation drastically more intuitive. View and Navigation based on map Sometimes, when the user looks at a small part of the world, there is a need to see the "big picture", have a larger context, that is, see the site map. This is particularly useful when the user quickly wishes to switch to another part of the 3D scene, in response to an alarm event. In the VIDEO FLASHLIGHT ™ system a user can access a spell map view of the scene. In this view, all the resources in the scene, including the various sensors, are represented with their current status. Video sensors are also among those, and a user can create the optimal view they want in the 3D scene by selecting one or multiple video sensors in this map view when selecting their occupied occupied surfaces, and the system will respond accordingly to automatically navigate to the perspective that shows all these sensors. PTZ Navigation Control The Telephoto Tilt (PTZ) Tilt cameras are typically fixed in one position and have the ability to rotate and zoom. PTZ cameras can be calibrated to a 3D environment, as explained in a previous section. Derivation of the Rotation and Zoom Parameters Once the calibration is done, an image can be generated for any point in the 3D environment since that point and the position of the PTZ creates a line that constitutes a unique combination of turn / tilt / teleobj etivo. Here, the zoom can be adjusted to "track" a specific size (human (~ 2m), automobile (~ 5m), truck (~ 15m), etc.) and therefore depending on the distance of the point from the PTZ , adjust the zoom accordingly. The zoom can be adjusted additionally afterwards, depending on the situation. Controlling User Interaction and PTZ In the VIDEO FLASHLIGHT ™ system, in order to investigate an area with a PTZ, the user clicks on that point in the interpreted image of the 3D environment. This position is used by the software to generate the rotation angles and the initial zoom. These parameters are sent to the PTZ controller unit. The PTZ rotates and zooms to the point. Meanwhile, the PTZ unit is sending back its immediate parameters of rotation, tilt, telephoto and video feed. These parameters are again converted into the VIDEO FLASHLIGHT ™ coordinate system to project the video over the correct point and the outgoing video is used as the projected image. Therefore, the general effect is the visualization of a PTZ that rotates from one point to another with the real-time image projected on the 3D model. An alternative is to control PTZ spin / tilt / telephoto with keyboard strokes or any other input device without using the 3D model. This proves that it is useful for spin / tilt type derivative movements while tracking a person where instead of continuously clicking on the person, the user clicks on pre-assigned keys. (for example, the left / right / up / down / up-shift / down-shift keys can be mapped to left-turn / right-turn / up-tilt / down-tilt / telephoto-inward / telephoto-out) ... Viewing the scene while controlling the PTZ The PTZ control when clicking on the 3D model and the viewing of the oscillating PTZ camera is described in the previous section. But the perspective from which this effect is visualized can be important. An ideal way is to have a perspective that is "fixed" to the PTZ where the perspective from which the user sees the scene has the same position as the PTZ camera and rotates when the PTZ is spinning. The field of view is usually larger than the current camera to give the context to the user. Another useful PTZ visualization is to select a perspective at a higher level in the perspective hierarchy (see Perspective Hierarchy). In this way, multiple fixed and PTZ cameras can be viewed from one perspective.

Multiple PTZ When there are multiple PTZs in the scene, rules can be imposed on the system as to which PTZ to use where, and in what situation. These rules can be in the form of margin maps, diagrams of Turning / lnclination / Teleobj etivo, etc. If a view is desired for a particular point in the scene, the PTZ set that passes all of these tests for that point is used for consequent processes such as displaying them in VIDEO FLASHLIGHT ™ or sending them to a video matrix visualizer. 3D-2D Plane The VIDEO FLASHLIGHT ™ Interpretation Machine typically projects video over a 3D Scene for viewing. But especially when the field of view of the camera is too small and the point of observation is too different from the camera, there is too much distortion when the video is projected onto the 3D environment. To still show the video and maintain the spatial context, the plan is introduced as a way to show the video feed in the scene. The plane is displayed in close proximity to the original camera location. The coverage area of the camera is also shown and linked to the map. The distortion can be detected by multiple measurements, including the morphology of the shape between the original and projected image, the differences in image size, etc. Each plane is displayed essentially as a screen that hangs in immersed imagery perpendicular to the line of sight of the viewer, with the video displayed on it from the camera that can otherwise be displayed as distorted in the immersed environment. Since the planes are 3D objects, the farther the perspective camera is, the lower the plane, since the spatial context is preserved very well. In an application where there are hundreds of cameras, the plane can still prove that it is really effective. On 'a 1600x1200 screen, as much as +250 planes on an average size of 100x75 can be visible in one shot. Of course, in this magnitude, the planes will act as live textures for the whole scene. Although the foregoing is directed to the embodiments of the present invention, other and additional embodiments of the invention may be viewed without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.

Claims (28)

1. CLAIMS 1. A surveillance system for a site, the system is characterized in that it comprises: a plurality of cameras each producing a respective video of a respective portion of the site; a perspective selector configured to allow a user to selectively identify a perspective on the site from which he sees the site or a portion of it; a video processor coupled with the plurality of cameras to receive videos thereof; the video processor has access to a computerized model of the site and interprets the real-time images of the computer model corresponding to a field of view of the site from the perspective and in which at least a portion of at least one of the videos are superimposed over the computer model, the video processor displays the images to be seen in real time for a user; and a perspective-based video control system that automatically selects a subset of the plurality of cameras that is generating video appropriate for the field of view of the site from the perspective interpreted by the video processor, and which causes the video of the subset of cameras is transmitted to the video processor.
2. 2. The immersed surveillance system according to claim 1, characterized in that the video control system includes a video switch that allows the transmission to the video processor of the video of the subset of selected cameras as appropriate for the view and avoids the transmission to the video video processor of at least some of the cameras of the plurality of cameras that are not in the camera subset.
3. The immersed surveillance system according to claim 2, characterized in that the cameras propagate the video thereof over a network through one or more servers to the video processor, and the video switch communicates with the servers for prevent the propagation on the network of at least part of the video of the cameras that are not in the subset of the cameras.
4. The immersed surveillance system according to claim 2, characterized in that the cameras transmit the video thereof to the video processor by means of communication lines and the video switch is an analogous matrix switching device that turns off the flow to along the lines of communications of at least some of the videos of the cameras that are not in the subset of cameras.
5. The immersed surveillance system according to claim 1, characterized in that the video control system determines a distance between the perspective and each of the plurality of cameras, and selects the subset of the cameras to include the camera that has the shortest distance to perspective.
6. 6. The immersed surveillance system according to claim 1, characterized in that the perspective selector is an interactive display in a computer station through which the user can identify the perspective in the computerized model while viewing the images in a display device.
7. The immersed surveillance system according to claim 1, characterized in that the computer model is a 3-D model of the site.
8. The immersed surveillance system according to claim 1, characterized in that the perspective selector receives an input from the operator or automatic signal in response to an event and changes the perspective to a second perspective in response thereto; and the video control system based on the second perspective automatically selects a second subset of the plurality of cameras that is generating the appropriate video for the site view of the second perspective interpreted by the video processor, and causes the video of A different subset of cameras is transmitted to the video processor.
9. 9. The immersed surveillance system according to claim 8, characterized in that the perspective selector receives the input from the operator to change the perspective, and the change is a continuous movement from the perspective to the second perspective, and the continuous movement is restricted to a viewing path allowed by the perspective selector of so that movement outside the viewing path is inhibited despite any operator input that directs the movement.
10. The immersed surveillance system according to claim 1, characterized in that at least one of the cameras is a PTZ camera having parameters that can be controlled in direction or zoom, and the video control system transmits a control signal to the PTZ camera to cause the camera to adjust the direction or zoom parameters of the PTZ camera so that the PTZ camera provides data appropriate for the field of view.
11. 11. A surveillance system for a site, the system is characterized in that it comprises: a plurality of cameras that each generates, a respective data stream, each data stream includes a series of video frames corresponding each to an image In real time of a part of the site, each frame has a dater indicative of a time when the real-time image was made by the associated camera; a recorder that receives and records the data streams of the cameras; a video processing system connected to the recorder and which provides for the reproduction of the data streams recorded on it, the video processing system has an interpreter which plays the images for the reproduction of the recorded data streams a view of a model rendering perspective of the site and applying to it the recorded data streams from at least two of the cameras appropriate for the view; The video processing system includes a synchronizer that receives the recorded data streams from the recording system during playback, the synchronizer distributes the recorded data streams to the interpreter in synchronized form so that each image is interpreted with the video frames of the which all were taken at the same time.
12. The immersed surveillance system according to claim 11, characterized in that the synchronizer synchronizes the data streams based on the video frame timers thereof.
13. 13. The immersed surveillance system according to claim 12, characterized in that the recorder is coupled to a controller that causes the recorder to store the plurality of data streams in a synchronized format, and to read the date stamps of the plurality of data streams. to allow synchronization.
14. 14. The immersed surveillance system according to claim 11, characterized in that the model is a 3D model.
15. 15. An immersive surveillance system characterized in that it comprises: a plurality of cameras each producing a respective video of a respective portion of a site; an image processor connected to the plurality of cameras and receiving the video thereof, the image processor produces an interpreted image for a perspective based on the model of the site and combined with a plurality of videos that are appropriate for the perspective; a display device coupled to the image processor and displaying the interpreted image; and a vision controller coupled to the image processor and providing the data defining the perspective that is displayed, the vision controller is coupled to and receives the input of an interactive navigation component that allows a user to selectively modify the perspective , the navigation component restricts the modification of the perspective to a preselected set of view points.
16. 16. The immersed surveillance system according to claim 15, characterized in that the vision controller calculates a change in the position of the point display.
17. 17. The immersed surveillance system according to claim 15, characterized in that, when the user modifies the perspective to a second perspective, the vision controller determines whether any video besides the appropriate video for the first perspective is appropriate for the second perspective. perspective, and a second image is interpreted for the second video using any additional video identified as appropriate for the second perspective by the vision controller.
18. 18. A method for an immersive surveillance system having a plurality of cameras each producing the respective video of a respective part of a site, and a display station with a display device that displays images for viewing by a user, the method is characterized in that it comprises: receiving from an input device data indicating a selection of a perspective and the field of view to see at least part of the video from the cameras; identify a subgroup of one or more of the cameras that are in locations so that those cameras can generate the appropriate video for the field of view; transmit the video from the camera subgroup to a video processor; generate with the video processor a display of video when interpreting images of a computerized model of the site, where the images correspond to the field of vision of the perspective of the site in which at least a portion of at least one of the videos it is superimposed on the computer model, - displaying the images to a viewer; and causing the video of at least part of the cameras that are not in the subgroup to not be transmitted to the video interpretation system and consequently reduce the amount of data that is transmitted to the video processor.
19. 19. The method according to the claim 18, characterized in that the video of the subgroup of cameras is transmitted to the video processor through servers associated with the cameras on a network, and where causing the video not to be transmitted is achieved by communicating through the network at least to a server associated with at least one of the cameras that are not in the subgroup of the cameras so that the server does not transmit the video of at least one camera.
20. The method according to claim 18, and further characterized in that it comprises: receiving an input indicative of a change of perspective and / or field of vision so that a new field of vision and / or a new perspective is defined; and determining a second subgroup of cameras that can generate appropriate video for the new field of view or the new perspective; cause the video of the second subgroup of the cameras to be transmitted to the video processor; the video processor uses the computer model and the received video to interpret new images for the new field of vision or the new perspective; and where the video of at least part of the cameras that are not in the second group is not allowed to be transmitted to the video processor.
21. The method according to claim 20, characterized in that the first and second groups have at least one of the chambers in common and each subgroup has at least one chamber thereof that is not in the other subgroup.
22. 22. The method according to claim 20, characterized in that the subgroups each have only a respective one of the cameras therein.
23. The method according to claim 18, characterized in that one of the cameras in the subgroup is a camera having a controllable direction or zoom, and the method further comprises transmitting to the camera a control signal such as to cause the camera adjust the direction or zoom of it.
24. 24. A method for a surveillance system for a site having a plurality of cameras each generating a respective data stream from a series of video frames each corresponding to a real-time image of a part of the site , the method is characterized in that it comprises: recording the data streams of the cameras in one or more recorders, the data streams are recorded together in synchronized format, and with each frame having a datum indicative of a time when the image in real time it was done by the associated camera; communicate with the recorders to cause the recorders to transmit the recorded data streams from the cameras to a video processor; receive the streams of recorded data and synchronize the frames thereof based on the timers thereof; receiving from an input device data indicating a selection of a perspective and field of vision to see at least part of the video of the cameras; generate with the video processor a video display when interpreting images of a computerized model of the site, where the images correspond to the field of view of the perspective of the site in which at least a portion of at least two of the videos it is superimposed on the computer model; where, for each interpreted image, the video superimposed on it is of frames that have date stamps of which all indicate the same period of time; and display the images to a visualizer.
25. 25. The method of compliance with the claim 24, characterized in that, sensitive to the received input, the video is selectively reproduced forward and backward.
26. 26. The method of compliance with the claim 25, characterized in that the reproduction is controlled from the location of the video processor by transmitting command signals to the recorders.
27. 27. The method according to claim 24, further characterized in that it comprises receiving the input that directs a change of field of view and / or perspective to a new field of view, the video processor generates images from the computer model and the video for the new perspective and / or field of vision.
28. 28. A method for a surveillance system for a site having a plurality of cameras each generating a respective data stream from a series of video frames each corresponding to a real-time image of a part of the site, the method is characterized in that it comprises: transmitting the recorded data streams from the cameras to a video processor; receiving from an input device data indicating a selection of a perspective and field of vision to see at least part of the video of the cameras; generate with the video processor a video display when interpreting images of a computerized model of the site, where the images correspond to the field of view of the perspective of the site in which at least a portion of at least two of the videos it is superimposed on the computer model; and display the images to a viewer; receive the input indicative of a change of perspective and / or field of view, the entry is restricted so that an operator can only enter changes of perspective or perspective for a new field of vision that are the limited subset of all the possible changes, the limited subset corresponds to a path through the site.