M. Bichsel, SEGMENTING SIMPLY CONNECTED MOVING-OBJECTS IN A STATIC SCENE, IEEE transactions on pattern analysis and machine intelligence, 16(11), 1994, pp. 1138-1142
A new segmentation algorithm is derived, based on an object-background
probability estimate exploiting the experimental fact that the statis
tics of local image derivatives show a Laplacian distribution. The obj
ects' simply connectedness is included directly into the probability e
stimate and leads to an iterative optimization approach that can be im
plemented efficiently. This new approach avoids early thresholding, ex
plicit edge detection, motion analysis, and grouping.