Research on a hibrid moving object detection algorithm in video surveillance system

Moving Object detection and tracking are receiving a growing attention with the development of powerful embedded system, which prodding the pervasive use of surveillance systems. The proposed hybrid algorithm combined simple frame difference(FD) algorithm, simple adaptive background subtraction (BS) algorithm, and accurate Gaussian modeling so as to benefit from the high detection accuracy of Mixture of Gaussian solution (MoG) in outdoor scenes while reducing the computations. The proposed system is capable of adapting to dynamic scene, removing shadow, and distinguishing left/removed objects both in indoor and outdoor. It is proved to be suitable for real time surveillance applications.