Patent Application
20100321500
One of the drawbacks with using video surveillance to monitor a location is that it can be difficult to determine where there are coverage gaps in the surveillance. This difficulty is exacerbated when reconciling surveillance coverage from multiple viewpoints (i.e., when several video cameras are used to cover an area from multiple locations).
The video cameras in a typical security system are usually placed such that all of the scenes which are viewed by the cameras overlap to some extent. However, there are often areas where one or more obstacles block a portion of the field of view of one camera and the remaining cameras are unable to provide adequate surveillance of the blocked area. These gaps in the video surveillance may not be readily apparent when camera data is viewed by security personnel.
One method that is used to minimize the size and number of blocked video coverage areas is to place surveillance cameras at optimal locations such that the effect of obstacles is minimized. The placement of cameras in these desired positions can often be problematic because there may be no infrastructure or supporting structures that exist at these locations making it difficult and/or expensive to adequately mount the video cameras. In addition, even if special arrangements are made to place cameras at these locations, there are typically unforeseen areas of blocked coverage.
Another of the current methods that is used to minimize the size and number of blocked video coverage areas is to place multiple cameras in an area and use rotating field of views for each of the cameras. One of the shortcomings associated with using rotating field of views for each of the cameras is that events in the field of view of the camera can transpire when the camera is not pointing where the events occur. Security personal monitoring multiple screens, and particularly screens with rotating fields of view, frequently fail to detect activity on those screens. In addition, even when rotating field of views are used for each of the cameras, there are typically unforeseen areas of blocked coverage.
In the following description, reference is made to the accompanying drawings that form a part hereof, and in which is shown by way of illustration specific embodiments which may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention, and it is to be understood that other embodiments may be utilized and that structural, logical and electrical changes may be made without departing from the scope of the present invention. The following description of example embodiments is, therefore, not to be taken in a limited sense, and the scope of the present invention is defined by the appended claims.
The functions or algorithms described herein may be implemented in software or a combination of software, hardware and human implemented procedures in one embodiment. The software may consist of computer executable instructions stored on computer readable media such as memory or other type of storage devices. Further, such functions correspond to modules, which are software, hardware, firmware or any combination thereof. Multiple functions may be performed in one or more modules as desired, and the embodiments described are merely examples. The software may be executed on a digital signal processor, ASIC, microprocessor, or other type of processor operating on a computer system, such as a personal computer, server or other computer system.
A system and method are provided for addressing video surveillance fields of view limitations. In some embodiments, the system and method perform video surveillance of a given area and then geo-locate any obstacles within the area, including measuring their overall size and shape. The system and method further map the size, location and shape of the objects into a database and then identify where there are video surveillance coverage gaps.
The system and method are able create a synthetic video image of the area from multiple vantage points. The objects which have been mapped into a database are used to create the synthetic image. The synthetic image that is created can be from a vantage point that is located anywhere between at least two video surveillance vantage points.
In some example embodiments, activity 150 which includes loading a global position of the first vantage point and the second vantage point into the database may further include determining the global position of the first vantage point and determining the global position of the second vantage point. As an example, determining the global position of the first vantage point may be done simultaneously with determining the global position of the second vantage point by using a global positioning system that includes components which are located at the first vantage point and the second vantage point.
In addition, activity 160 which includes loading a global position of the objects in the area into the database based on information in the database may further include determining the global position of the objects in the area based on information in the database. As an example, the determination may be based on knowing the global positions of the first vantage point and the second vantage point as well as the locations of the objects in the area relative to the first vantage point and the second vantage point.
In some example embodiments, activity 110 which includes loading a first video image of an area from a first vantage point into a database may further include obtaining the first video image from a first camera, and activity 120 which includes loading a second video image of the area from a second vantage point into the database may further include obtaining the second video image from a second camera. As an example, obtaining the first video image from the first camera may be done simultaneously with obtaining the second video image from the second camera.
In some example embodiments, activity 130 which includes loading a first set of data relating to the size and distance of objects in the area from the first vantage point into the database may further include obtaining the data from a first lidar (i.e., Light Detection and Ranging or Laser Imaging Detection and Ranging (system), or Laser Identification Detection and Ranging or Laser Induced Differential Absorption Radar), and activity 140 which includes loading a second set data relating to the size and distance of the objects in the area from the second vantage point into the database may further include obtaining the data from a second lidar. As an example, obtaining the data from the first lidar may be done simultaneously with obtaining the data from the second lidar.
The measurements from the first and second lidar (as well as the global positioning system) may be loaded into the database such that the database contains the geo-location, size and shape of the objects which are within the area. In addition, the location of each surveillance camera and the field of view of each camera may be added to the database such that any areas that are blocked from video surveillance by objects in each camera's field of view may determined by the processor. In preferred embodiments, the fields of view of the lidars are at least equal to the fields of view of the cameras.
The geo-located objects and composite video images of the surveillance zone (which are obtained by the cameras) are used by the processor to generate synthetic video images. Using the information in the database, the processor creates a new vantage point. The objects in the database are tiled with scene data for realistic presentations.
Due to limitations on what is actually in the database, the location of any new vantage points will be limited to a location that is somewhere between any of at least two cameras/lidars. This limitation on the synthetic video image vantage point which may be determined (and subsequently displayed) by the processor is because it is only possible to create a new vantage point for those objects that are tiled with scene data. As an example, a new vantage point could not be created which is on an opposite side of video surveyed objects because there is nothing from that opposite side vantage point that would be visible to the surveillance cameras from the original vantage point(s).
In some example embodiments, obtaining the first video image from a first camera and obtaining the second video image from a second camera may be done simultaneously with obtaining the data from a first lidar and obtaining the data from a second lidar which may also be done simultaneously with receiving a global position of the first vantage point from the global positioning system and receiving the global position of the second vantage point from the global positioning system.
The video surveillance system 10 further includes a global positioning system 20 that is used to determine the global position of the first video camera 16, the second video camera 18, the first lidar 12 and the second lidar 14. The video surveillance system 10 further includes a processor 30 that receives data from the first camera 16, the second camera 18, the first lidar 12, the second lidar 14 and the global positioning system 20. The processor 30 creates a synthetic video image from any vantage point (e.g. vantage point Z) that is located between the first vantage point X and the second vantage point Y using the data from the first and second video cameras 16, 18, the first and second lidars 12, 14 and the global positioning system 20.
The global positioning system 20 and the first and second lidars 12, 14 are used to globally locate objects O1, O2, O3, O4, O5 within an area A. The location of the objects O1, O2, O3, O4, O5 within the area A is correlated with video images that are taken from the first and second video cameras 12, 14.
When the first and second lidars 12, 14 are mounted on the first and second cameras 16, 18 (or vice versa), the surveillance system 10 is able to continuously update the data to reflect those areas that are blocked from video surveillance by the first and second cameras 16, 18. One example of where this may be useful is for areas such as shipping ports where stacks of shipping containers are constantly moving in and out of a port (i.e., a surveillance area). As the containers stack up or are moved, there will be changing gaps in the video surveillance.
In some example embodiments, the first video camera 16 and the second video camera 18 simultaneously send data to the processor 30 and/or the first lidar 12 and the second lidar 14 simultaneously send data to the processor 30. In addition, the global positioning system 20 may simultaneously send data to the processor 30 along with the first and second lidar 12, 14 and/or the first and second video cameras 16, 18.
Although not explicitly shown in the FIGS., the first and second lidars 12, 14 and the first and second cameras 16, 18 are able to monitor when a portion of any of the objects may be moved within or removed from area A. As an example, the system 10 is able to monitor when one or more containers in a stack of containers is removed from (or added to) the rest of the stack of containers.
It should be noted that embodiments are contemplated where only a single lidar and/or camera are used to supply data to the processor 30 relating to the size and distance of objects in an area A from the first vantage point X and then subsequently supply data relating to the size and distance of objects in the area from the second vantage point Y. In addition, a single component in the global positioning system 20 may be used to supply the global position of the first and second vantage points X, Y to the processor 30.
Embodiments are also contemplated where multiple lidars and/or cameras are used to supply data to the processor 30 relating to the size and distance of objects in an area from multiple vantage points. In addition, multiple components in the global positioning system 20 may be used to supply the global positions of the multiple vantage points to the processor 30.
In some embodiments, a computer system may form part of the system 10. A block diagram of an example computer system that executes programming for performing some of the methods described above is shown in
Computer storage includes random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM) & electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD ROM), Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium capable of storing computer-readable instructions, as well as data, including video frames.
Computer 710 may include or have access to a computing environment that includes input 716, output 718, and a communication connection 720. In some example embodiments, the input 716 may allow a user to select the vantage point (e.g., vantage point Z) of the synthetic video image. In addition, the output 718 may include a display that illustrates the synthetic video image generated by the processor 30.
The computer may operate in a networked environment using a communication connection to connect to one or more remote computers. The remote computer may include a personal computer (PC), server, router, network PC, a peer device or other common network node, or the like. The communication connection may include a Local Area Network (LAN), a Wide Area Network (WAN) or other networks.
Computer-readable instructions stored on a computer-readable medium, such as storage devices, are executable by the processing unit 702 of the computer 710. A hard drive, CD-ROM, and RAM are some examples of articles including a computer-readable medium.
The Abstract of the Disclosure is provided to comply with 37 C.F.R. §1.72(b) with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. The above description and figures illustrate embodiments of the invention to enable those skilled in the art to practice the embodiments of the invention. Thus the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separate embodiment.
