A New Detection Algorithm of Moving Objects Based on Human Morphology

This paper begins with a discussion of the deficiency of current algorithms which use the number of the changing points of frame-difference as the threshold to determine a moving object. Based on human morphology, the feature of the human body in video surveillance is analyzed. Secondly, "the head and shoulder projection curve"," the proportion of head hair "and "height-width ratio "are extracted as three key parameters by mathematical methods. Finally, the two key parameters are used to detect the moving target, replacing the existing threshold. DSP-based experimental results show that this method can effectively distinguish a moving human object from the moving interferential object caused by environmental change, thus to avoid the false alarms by the improvement of movement tracking stability.