Abstract: The invention, at the first frame, records the background, as the threshold of detection-constant image with the predeterming minimum threshold, and with each subsequent frame, corrects the background and threshold with formulas while producing the adaptation of a renewal-constant in each pixel depending on the presence of the detected object, defines the difference between the current frame and background, compares it with the threshold, combines elements exceeding a threshold into detection zones, performs rejection of the detection zones, divides the zones in order to separate shadows, forms a tracking zone, searches already-detected segment of objects, forming clusters of the tracking zones. The coordinates of the obtained rectangles are assumed as the coordinates of the objects located in the frame.

Abstract: Binarization is performed using a threshold image obtained by multiplying a variation in each pixel value of an input image with a coefficient. Although the variation is time-averaged based on an update coefficient for each pixel, the update coefficient is switched depending on whether or not a relevant pixel belongs to the object. Subsequently, from the binary image, an initial detection zone is formed and a spatial filtering process is performed thereto. The spatial filtering process includes at least one of skeleton analysis processing, object mask processing, morphology processing, and section analysis processing. For a tracking zone, the temporal positional change thereof is tracked, and the noise is reduced. Some of the tracking zones are removed, and the remaining zones are integrated into a cluster, and furthermore the cluster selection is performed based on the dimensions in real space.

Abstract: Binarization is performed using a threshold image obtained by multiplying a variation in each pixel value of an input image with a coefficient. Although the variation is time-averaged based on an update coefficient for each pixel, the update coefficient is switched depending on whether or not a relevant pixel belongs to the object. Subsequently, from the binary image, an initial detection zone is formed and a spatial filtering process is performed thereto. The spatial filtering process includes at least one of skeleton analysis processing, object mask processing, morphology processing, and section analysis processing. For a tracking zone, the temporal positional change thereof is tracked, and the noise is reduced. Some of the tracking zones are removed, and the remaining zones are integrated into a cluster, and furthermore the cluster selection is performed based on the dimensions in real space.

Abstract: The invention, at the first frame, records the background, as the threshold of detection—constant image with the predetermining minimum threshold, and with each subsequent frame, corrects the background and threshold with formulas while producing the adaptation of a renewal—constant in each pixel depending on the presence of the detected object, defines the difference between the current frame and background, compares it with the threshold, combines elements exceeding a threshold into detection zones, performs rejection of the detection zones, divides the zones in order to separate shadows, forms a tracking zone, searches already-detected segment of objects, forming clusters of the tracking zones. The coordinates of the obtained rectangles are assumed as the coordinates of the objects located in the frame.