An Efficient Moving Object Detection Algorithm Using Multi-mask

Motion object detection is the basis of video surveillance, and background subtraction is commonly used to detect motion object, but how to build and maintain background model is very critical, and what´smore, one background model can´t solve all complex background problems. This paper present the Mask Motion Object Detection (MMOD) algorithm, which synthesize the thoughts of background subtraction and frame difference, frame difference mask and background difference mask are generated and utilized to detect motion object. Morphological post processing method is introduced to reduce noise and improve detection precision. It is proved by testing with standard sequence provided by MPEG organization and outdoor/indoor sequence captured by us that MMOD algorithm achieves good detection result.