|
|
|
Presentation Topic - Luncheon - 21 February 2008 |
| Video Analytics is a new terms that start to replace standard terms of video surveillance and CCTV. Video Analytics is the emerging technology where computer vision is used to filter and manage real time CCTV video for security and intelligent traffic monitoring. With the ambitious and ambiguity of what is a Video Analytics for surveillance applications. Several systems have been thought of, acquired and deployed. There is also a hesitation of what Video Analytics should be used for and using this technology that analyze video for specific data collection, behaviour analysis, objects identification or attitude recognition. With this in mind it has a wide range of applications including safety and security. It can be implemented as a software algorithms that run on processors inside a computer or on an embedded computer platform or in video cameras, recording devices, or specialized video processing units. Video analytics algorithms together are integrated with video and called Intelligent Video Software systems that run on embedded computers. The technology can evaluate the contents of video to determine specified information about the content of that video. Examples of video analytics applications include: counting the number of pedestrians entering a door or geographic region, determining the location, speed and direction of travel, identifying suspicious movement of people or assets, license plate identification or evaluating how long a package has been left in an area. This presentation will cover the basic concepts of Video analytics and its uses in security/safety applications. It will present several examples of where Video Analytics fits and more examples of where it does not fit. It will also demonstrate several approaches for deployment with the current systems and building upon new infrastructure. It will also present results of different field deployments/pilots. The talk will stimulate the
audience to provide different views and potential applications for
cameras with brain that can identify and report targeted incidents
or objects. |