Indoor video moving objects detection based on the independent component analysis with reference

Moving objects and static background are independent in video scene. But due to the same environment and video cameras, moving objects and static background in video frames are relevant. So based on the correlation between the moving objects and static background, a reference image of moving objects is constructed. And this reference image is used in the algorithm of video moving objects detection based on the independent component analysis to improve the performance. Experimental results show that the proposed algorithm has good quantitative detection performance and high efficiency of training and detection in indoor scene of dramatic changes of illumination.