Abstract: A moving object extraction based on background subtraction capable of stably extracting the moving object under various environments. Temporal changes of image feature parameter values for sub-regions subdividing a frame of each input image are stored, and the background image is reconstructed by statistically processing a temporal change of the image feature parameter values for each sub-region within a prescribed target region of the frame over a prescribed period of time to obtain the statistical quantity characterizing that temporal change, judging whether that temporal change is due to an illumination change or not according to the obtained statistical quantity and a prescribed illumination change judging condition, and updating a background image value for each sub-region by a new background image value according to the image feature parameter values for each sub-region during the prescribed period of time.

Abstract: A scheme for directional counting of moving objects capable of counting moving objects stably while determining passing directions of the moving objects accurately. In this scheme, a counting line is set in an image field of the sequential images, and a dynamic image formed by pixels forming the counting line is obtained for each frame and while a succesively updated background image is obtained. Then, a subtraction and binarization processing are applied to the dynamic image and the background image to extract a moving object region, and a moving object image is formed by sequentially labeling the moving object region in time order.