Video analytics: Content analysis in security and surveillance applications

For this reason, there is a push to develop new methods that will significantly increase the effectiveness of monitoring security and surveillance video. Video content analysis (VCA), also known as video analytics, electronically recognizes the significant features within a series of frames and allows systems to issue alerts when specific types of events occur, speeding real-time security response. In addition, VCA automatically searches the captured video for specific content, relieving personnel from tedious hours of reviewing. This also decreases the number of personnel needed to screen camera video on an ongoing basis, reducing costs. At present, VCA is an emerging technology with techniques that are continuingly being developed to help make widespread implementation feasible in the years ahead.

One certainty is that VCA will require a great deal of processing in order to identify objects of interest in the vast stream of video pixel data. In addition, VCA systems must be programmable in order to meet variations in application, recognize different types of content and adapt to evolving algorithms. Newly available video processors provide an exceptionally high level of performance and programming flexibility for compression, VCA and other requirements of digital video systems. Software platforms and tools that complement the processors help simplify development for security and surveillance products. As VCA techniques develop, they can be readily implemented as the enabling technology currently exists.

VCA flow
To date there is no governing international standard for VCA, but the generic flow can be described as follows:

1. A longer sequence is separated into individual scenes or shots that are to be analyzed. Since different scenes have different histograms, or color frequency distributions, a frame where the histogram changes radically from that of the previous frame can be treated as a scene change.
2. Changing foreground objects within the scene are detected as separate from the static background.
3. Individual foreground objects are extracted or segmented, then tracked from frame to frame. Tracking involves detecting the position and speed of the object, which may be variable or temporarily stationary.
4. If recognition is necessary, the features of the object are extracted so that the object can be classified.
5. If the event is something of interest, an alert is issued to the management software and/or personnel.

Next: Foreground / background detection