A Background Reconstruction Algorithm based on Pixel Intensity Classification in Remote Video Surveillance System

1 The work is supported by National Key Fundamental Research (973) Program in China, the project number is: 2001CB309403. AbstractA background reconstruction algorithm based on pixel intensity classification is presented in this paper. Assumption that background pixel intensity appears in image sequence with the maximum probability is adopted. The pixel intensity values are classified based on the calculated pixel intensity difference between inter-frame, finally, the intensity value with the maximum frequency is selected as the background pixel intensity value. In proposed algorithm, the pre-training of no-moving object in background and the models of background and target aren’t needed, and only one parameter is adjusted. Simulation results to real video surveillance sequences show that background can be reconstructed correctly, so target can be extracted perfectly and tracked successfully.