An approach to segmenting motion objects and suppressing shadows without background learning has been developed. Since\nwavelet transformation indicates the position of sharper variation, it is adopted to extract the information contents with the most\nmeaningful features based on two successive video frames only. According to the fact that the saturation component is lower in\nthe region of shadow and is independent of the brightness, HSV color space is selected to extract foreground motion region and\nsuppress shadow instead of other colormodels. A local adaptive thresholding approach is proposed to extract initial binary motion\nmasks based on the results of the wavelet transformation. A foreground reclassification is developed to get an optimal segmentation\nby fusion of mode filtering, connectivity analysis, and spatial-temporal correlation. Comparative studies with some investigated\nmethods have indicated the superior performance of the proposal in extracting motion objects and suppressing shadows from\ncluttered contents with dynamic scene variation and crowded environments.
Loading....