View handling in video surveillance systems

A method of video processing, the method comprising:

• receiving a single video feed provided by a source, wherein the source is one of a video buffer, a camera, or a multiplexer coupled to a plurality of cameras;
• determining a known view model set comprising at least one known view model representing a scene of the single video feed and comprising a video frame from the single video feed and a background model of the scene;
• creating video analytics functionally relevant to the scene represented by at least one known view model of the known view model set;
• receiving a current frame from the single video feed;
• determining which known view model from the known view model set represents the scene depicted in the current frame, wherein the determined known view model is designated as a current known view model;
• performing video analytics for the current known view model on the current frame;
• receiving a next frame from the single video feed;
• and
• determining whether the next frame is directed to the current known view model by using video processing;
• if the video processing determines that the next frame is directed to the current known view model, performing video analytics for the current known view model on the next frame;
• and
• if the video processing determines that the next frame is not directed to the current known view model, determining whether the next frame is directed to any other known view model of the known view model set by using video processing;
• if the video processing determines that the next frame is directed to a different known view model of the known view model set, performing video analytics for the different known view model on the next frame;
• and
• if the video processing determines that the next frame is not directed to any other known view model of the known view model set, discarding the next frame.