Dual background modeling of traffic image based on LBP and Gaussian

The detection of moving objects is a key step in the traffic video monitoring system. The most common way to detect moving objects is background subtraction and the critical technique is the background modeling. In this paper, we propose a method combining LBP with Gauss for the detection of the moving objects. We adopt the method of parallel processing in order to improve the processing speed in the implementation of the algorithm. And the video sequences are used to test the proposed method. Experiments show that our methods have high real-time in background updating.