A hardware-accelerated segmentation algorithm for moving object generation

It presents an efficient moving object segmentation algorithm suitable for images on the programmable graphics hardware. The basic idea is to use simultaneously a novel spatial segmentation algorithm and an effective temporal algorithm based on human visual system. It defines two features needed in segmentation, the spatial and the temporal. Two segmentation algorithms are used simultaneously to produce the edges and the region of a moving object, respectively. Then, it takes use of the edges with the region of the moving object to obtain the object. It reduced number of the time-consuming motion estimation computation dramatically. So, the whole processing speed is significantly accelerated to meet the hardware implementation requirement. Finally, a post-processing step is applied on the object to smooth the object boundary. Good performance of this algorithm is demonstrated by the experimental results.