Authors : Z.E. Baarir and F. Charif
Abstract: Optical flow estimation is important in the area of computer vision. This study presents a fast modified Horn and Schunck study for robust boundary preserving estimation of optical flow. Variational approaches have addressed this topic and proposed methods that account for velocity boundaries at the cost of significant computational complexity, which makes them inadequate for current real-time applications. The proposed method is derived from the benchmark algorithm of Horn and Schunck and Simoncelli�s matched-pair 5 tap filters, such that it produces robust, fast and exact detection of motion boundaries and it is very simple to implement. Experimental results using synthetic and real optical flow image sequences are presented to demonstrate the effectiveness of our method in comparison to selected methods.
Z.E. Baarir and F. Charif , 2006. Fast Global Motion Estimation for Image Sequences. Asian Journal of Information Technology, 5: 968-975.