Abstract:
Motion detection is an important computer vision problem that has been used in different applications including surveillance. Most of the applications require fast processing due to their real time nature. The GPU (Graphic Processing Unit) is used as a cost-efficient tool that provides great opportunities for parallel processing. This paper studies the performance of the GPU in implementing a realistic motion detection application and compares the performance of multiple GPUs and CPU for this class of applications. The experimental results have shown that the GPU based system demonstrated high speedup and it is therefore a good low cost solution for real-time scenarios such as in video surveillance systems.

Paper available at IEEE.