Motion-based Object Segmentation using Sprites and Anisotropic Diffusion

Many algorithms have been developed to recognize regions, edges, color, and objects in images and videos. For applications like surveillance or object-based video coding, it is important to segment the foreground objects from the background. The task is very challenging in the case of a moving camera. We present a foreground segmentation approach that is designed for sprite coding as well as other applications, e.g. video surveillance. Accurate frame-to- frame image registration and sprite generation build the pre-processing step. The segmentation algorithm operates on error images, which are produced by the image registration and subtraction from reconstructed background frames. It is processed in several steps including low-pass filtering using anisotropic diffusion. Experiments show excellent results with single- and multi-view test sequences.