Content-based software demultiplexing of surveillance video

Time-multiplexed video recordings must be demultiplexed for effective analysis by investigators - a task often made difficult by the proprietary nature of the recording equipment. In addition to a lack of standards, some systems may record scenes from different cameras with a time-varying sequence. To address this issue, a content-based image analysis technique for extracting a specified camera view from a multiplexed video sequence is presented. A single frame from the specified view is used as a reference to which subsequent frames are compared. Frames matching the reference within a specified similarity threshold are passed on to the demultiplexed output. An optional region of interest may be used to select an area of the scene that is unique to that camera view but relatively consistent over time. The software implementation of this technique allows multiple camera views to be demultiplexed simultaneously from a digitized stream of multiplexed video. Similarity metrics and adaptive techniques are discussed.