A real-time motion detection algorithm for traffic monitoring systems based on consecutive temporal difference

Moving objects detection is a basic task in video analysis and applications. Many algorithms have been proposed to detect moving objects under different situations in the past decades. In this paper, we propose a new method to detect moving objects in a non-stationary, complex background for an automatic traffic monitoring system. As a pre-treatment, the square neighborhood algorithm is adopted to compensate the disturbance caused by shaking of camera. Then, an improved temporal difference method is applied to obtain the moving areas. Some post-treatments are used to optimize the detection by eliminating noise from the moving areas. The proposed method is excellent in real-time performance because it requires only a little memory and computation. Experiment results show that this method can detect the moving objects efficiently and accurately form the video recorded by a shaking camera with changing background and noises.