Robust motion estimation methods using gradient orientation information

Changing lighting conditions cause temporal variations of image intensities and make most existing motion estimation techniques ineffective. As a solution to this problem, we use gradient orientation information, which depends very little on changes of image intensities, in place of commonly used image features such as intensities and gradients. By employing gradient orientation, two conventional motion estimation techniques (the spatio-temporal gradient method and the gradient structure tensor method) can be transformed into methods that are far more robust to changing image intensities. Simulation results on both synthetic and real image sequences show that the proposed methods perform motion estimation remarkably well irrespective of time-varying image intensities. In addition, the proposed methods also cope better with the aperture problem in which only unidirectional gradients are available and large erroneous motion estimates are produced.