A Comparative Study on Gradient-Based Approaches for Optical Flow Estimation

The most readily available motion parameter from sequential image is optical flow. Among various optical flow estimation techniques, gradient-based approach is a common technique. This approach is based on the assumption that the brightness of a point in the image remains constant during a short time interval, while the location of that point in the image may change due to motion. This assumption leads to a single local constraint on the optical flow at a certain point in the image. It is, however, ill-posed as the constraint constitutes only one equation of two unknowns, that is, xcomponent and y-component of the flow vector. In order to solve this problem, various methods have been proposed. There are, however, only a few comparative studies from the viewpoint of the application to the specific and practical motion analysis. This paper reviews the gradient-based approaches theoretically and compares their performance empirically from the point of view of application to vehicle motion analysis. The basic methods of gradient-based approach are reviewed as follows: (1) Increase in the number of observation equations: (a) spatial local optimization method, (b) temporal local optimization method, (c) multispectral constraints method, (d) second order derivative method and by their combination; (2) Imposition of a condition: (a) spatial global optimization method, (b) temporal global optimization method and their combination. The result of empirical comparison shows the difficulty of estimation of precise and dense optical flow by ordinary gradient-based approaches, when sequential images are taken at an interval about 1/30 seconds. Hence, it is difficult to analyze vehicle motion by the gradient-based approaches in this case.

[1]  Robert J. Woodham Multiple light source optical flow , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[2]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[3]  William H. Press,et al.  Numerical recipes in C , 2002 .

[4]  Steven S. Beauchemin,et al.  The computation of optical flow , 1995, CSUR.

[5]  Joseph K. Kearney,et al.  Optical Flow Estimation: An Error Analysis of Gradient-Based Methods with Local Optimization , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Richard G. Lane,et al.  Determining optical flow using a differential method , 1997, Image Vis. Comput..

[7]  Giulio Sandini,et al.  Estimation of depth from motion using an anthropomorphic visual sensor , 1990, Image Vis. Comput..

[8]  Hans-Hellmut Nagel,et al.  Displacement vectors derived from second-order intensity variations in image sequences , 1983, Comput. Vis. Graph. Image Process..

[9]  Makoto Sato,et al.  Hierarchical Estimation of Displacement Vectors in Image Sequences , 1988, Systems and Computers in Japan.

[10]  Larry S. Davis,et al.  Contour-based motion estimation , 1982, Comput. Vis. Graph. Image Process..

[11]  Hideyoshi Tominaga,et al.  A Motion Detection Method on Video Image by Using Hierarchical Pixels , 1990, Systems and Computers in Japan.

[12]  Yuan-Fang Wang,et al.  Experiments in computing optical flow with the gradient-based, multiconstraint method , 1987, Pattern Recognit..

[13]  Vishal Markandey,et al.  Multispectral constraints for optical flow computation , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[14]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[15]  Hidetoshi Miike,et al.  Field theory approach for determining optical flow , 1991, Pattern Recognit. Lett..