Moving object detection is an important process in intelligent video surveillance systemsOn the basis of analyzing existing detection approaches，this paper proposes a detection algorithm based on a gradient directionsFor a video image sequence，edge gradient images of each frame are achieved firstly by means of directionSecondly，the traditional frame difference is improved and it car extract the rough edges of moving objects by processing two temporal correlative frames using uint8 formatFinally，after connective areas of moving objects are obtained，the complete moving object contours are effectively detected using the gradient directionExperimental results show that，the proposed algorithm overcomes the shortcoming of not correctly 〖JP〗detecting moving objects with traditional frame difference and can effectively and accurately extract moving object contour among indoor and outdoor environments with complex backgrounds