Moving Object Detection based on Clausius Entropy

A real-time detection and tracking of moving objects in video sequences is very important for smart surveillance systems. However, due to dynamic changes in natural scenes such as sudden illumination and weather changes, repetitive motions that cause clutter, motion detection has been considered a difficult problem to process reliably. Hence, its robustness needs to be improved for applications in complex environments. In this paper, we propose a novel approach for the detection of moving objects that is based on the Claudius entropy method. First, the increment of entropy generally means the increment of complexity, and objects in unstable conditions cause higher entropy variations. Hence, if we apply these properties to the motion segmentation, pixels with large changes in entropy in moments have a higher chance in belonging to moving objects. Therefore, we apply the Clausius Entropy theory to convert the pixel value in an image domain into the amount of energy change in an entropy domain. Second, we use an adaptive background subtraction method to detect moving objects. This models entropy variations from backgrounds as a mixture of Gaussian. Experiment results demonstrate that the proposed method can detect moving objects effectively and reliably.