A video coder using 3-D model based background for video surveillance applications

We present a model based video coder for remote video surveillance applications at very low bit rates. Unlike the known model based video codecs, we use the model based approach for background modeling and not for "head-and-shoulders" modeling. Since in video surveillance the remote site that is being monitored is usually a previously known physically closed space, we build a 3-D model of the site and use it to synthesize the background of the scene for each of the video cameras used. The codec has two layers, one layer for the background using a 3-D model and a second layer for the part of the scene not represented by the background. The second layer may use conventional hybrid DPCM-DCT coding schemes, like H.263, or object-based coding techniques, like those used in MPEG-4 video VM. The proposed codec can be a good framework for a multiview codec.