Spatio-temporal detection of video moving object

A new method to detect moving objects from video sequences with global motion is proposed based on spatio-temporal joint detection. In order to overcome the drawback of subjective fixed threshold of traditional temporal segmentation, the characteristic parameters of background noise in difference image are adaptively evaluated and the automatic threshold is obtained. Then the temporal segmentation mask is amended by morphological operations; Considering the lack of traditional spatial segmentation algorithm of watershed, an improved watershed algorithm in accord with the human vision characteristics is proposed, which includes the noise reduction by morphological reconstruction, gradient transformation and gray level non-linear transformation based on Web perception principle. The improved watershed can restrain over-segmentation effectively; the temporal and spatial information fusion is fulfilled by ratio operation, and the video moving object is obtained. The emulation experiments show that the proposed algorithm can detect the moving object quickly and effectively.