Parallel Optical Flow Using Local Voting

We describe a parallel algorithm for computing optical flow from short-range motion. Regularizing optical flow computation leads to a forruulation which minimizes matching error and, at the same time, maximises smoothness of the optical flow. We develop an approximation to the full regularization computation in which corresponding points are found by comparing local patches of the images. Selection aniong competing matches is performed using a winner-take-all scheme. The algorithm accommodates many different image transformations uniformly, with siniilar results, from brightness to edges. The optical flow computed froni different image transformations, such as edge detection and direct brightness computation, can be simply combined. The algorithm is easily implemented using local operations on a finegrained computer, and has been implemented on a Connection Machine. Experiments with natural images show that the scheme is effective and robust against noise. The algorithm leads to dense optical flow fields; in addition, inforniation from matching facilitates segmentation.

[1]  Claude L. Fennema,et al.  Velocity determination in scenes containing several moving objects , 1979 .

[2]  D Marr,et al.  Directional selectivity and its use in early visual processing , 1981, Proceedings of the Royal Society of London. Series B. Biological Sciences.

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

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

[5]  H. K. Nishihara,et al.  Practical Real-Time Imaging Stereo Matcher , 1984 .

[6]  Gilad Adiv,et al.  Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  V. Ramachandran,et al.  Spatial phase and frequency in motion capture of random-dot patterns. , 1985, Spatial vision.

[8]  E H Land,et al.  An alternative technique for the computation of the designator in the retinex theory of color vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Tomaso A. Poggio,et al.  On parallel stereo , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[10]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  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.

[12]  Hh Bülthoff,et al.  Parallel Computation of Optical Flow , 1987 .

[13]  H. Bülthoff,et al.  INTERACTION OF DIFFERENT MODULES IN DEPTH PERCEPTION. , 1987, ICCV 1987.

[14]  Heinrich H. Bülthoff,et al.  Parallel Motion Algorithm explains Barber Pole and Motion Capture Illusion without "Tricks'' , 1987 .

[15]  Anselm Spoerri,et al.  The early detection of motion boundaries , 1990, ICCV 1987.

[16]  Alessandro Verri,et al.  Against Quantitative Optical Flow , 1987 .

[17]  M. Bertero,et al.  Ill-posed problems in early vision , 1988, Proc. IEEE.

[18]  W. Reichardt,et al.  Movement Detectors of the Correlation Type Provide Sufficient Information for Local Computation of the 2-D Velocity Field , 1988 .

[19]  Norberto M. Grzywacz,et al.  A computational theory for the perception of coherent visual motion , 1988, Nature.

[20]  Daphna Weinshall,et al.  The MIT vision machine , 1988 .

[21]  T Poggio,et al.  Parallel integration of vision modules. , 1988, Science.

[22]  Jin Luo,et al.  Computing motion using analog and binary resistive networks , 1988, Computer.

[23]  James J. Little,et al.  Algorithmic Techniques for Computer Vision on a Fine-Grained Parallel Machine , 1989, IEEE Trans. Pattern Anal. Mach. Intell..