Commentary Paper on "Foreground Object Detection Using Two Successive Images"

This paper describes a simple and novel algorithm for detecting foreground objects in video sequences using just two consecutive frames. The method isdivided in three layers: the perceptual layer detects regions of interest by looking for pixels whose values change significantly between the two frames. The memory layer allows for the detection of objects that may become stationary (these objects are added to the background after a period of time). The perceptual layer builds on information from the perceptual layer and from the previous iteration´s memory layer to extract the actual foreground objects. Background edges are detected and removed first, followed by a level-set method that shrinks the boundary of the region of interest to the boundary of the object. The method is tested on a variety of sequences taken with different cameras in different environments, and obtains very good results.