Color optical flow estimation based on gradient fields with extended constraints

Traditional optical flow estimations are poor in real applications because premises of the brightness constancy model are not accurate in real environment. An Optical flow estimation technique for color image sequences based on gradient fields with extended constraints model is proposed. This presented technique establishes optical flow equations at gradient fields of color images to weaken optical estimation errors caused by illumination variations. Three groups of experiments show that the proposed algorithm is more accurate and robust than traditional algorithms.