ComMode: an algorithm for video background modeling and object segmentation

This paper describes an algorithm called ComMode (competitive mode estimation) for building a statistical background model of a complete video shot in the presence of independent camera motion, and independently moving foreground objects. Furthermore, as a by-product of the algorithm, the foreground is automatically segmented as a first step towards detection and tracking of video objects. The algorithm works by treating the intensity value at each pixel location as a time series, and segmenting it into statistically coherent modes. Initially, the most likely background mode is selected by a heuristic. Then, pixels competitively propagate their background mode to neighbouring pixels. The result is that each pixel location ends up with the most likely estimate for its background statistical model.