Spatially adaptive HOS-based motion detection for video sequence segmentation

In this paper an adaptive procedure, based on a coarse-to-fine scheme, for the segmentation of a video sequence into background and moving objects, aimed at supporting content-based functionalities, is presented. The coarse stage provides a pixel-based motion detection based on non Gaussian signal extraction using Higher Order Statistics (HOS). The fine motion detection phase refines the coarse classification by introducing some topological constraints on the segmentation map essentially by means of simple morphological operators at low computational cost. The background model takes explicitly into account the apparent motion, induced by background fluctuations typically appearing in outdoor sequences. Spatial adaptation of the algorithm is obtained by varying the threshold of the HOS based motion detector on the basis of the local spectral characteristics of each frame, measured by a parameter representing the local spatial bandwidth. Simulation results show that, the introduction of local bandwidth to control the segmentation algorithm rejects the large apparent motion observed in outdoor sequences, without degrading the detection performance in indoor sequences.