This Article 
 Bibliographic References 
 Add to: 
On the Detection of Motion and the Computation of Optical Flow
March 1992 (vol. 14 no. 3)
pp. 346-352

A method for the detection of motion in image sequences is presented. In this method, the intensity history at each pixel is convolved with the second derivative in time of a temporal Gaussian smoothing function. The zero crossings in a single frame of the resulting function indicate the positions of moving edges. Intensity changes in time due to illumination effects do not produce zero crossings; thus, they are not interpreted as motion by the present method. It is also shown that the spatial and temporal derivatives of this function can be used to compute the component of the optical flow that is normal to the zero-crossing contours. This computation is also insensitive to nonconvective temporal and spatial variations in the image intensity that are caused by illumination effects.

[1] B. F. Buxton and H. Buxton, "Monocular depth perception from optical flow by space time signal processing," inProc. Royal Soc. London, vol. B218, pp. 27-47, 1983.
[2] B. F. Buxton and H. Buxton, "Computation of optical flow from the motion of edge features in image sequences,"Image Vision Comput., vol. 2, pp. 59-75, 1984.
[3] J. H. Duncan and T. C. Chou, "Temporal edges: The detection of motion and the computation of optical flow," inProc. Second Int. Conf. Comput. Vision(Tampa, FL), 1988, pp. 374-382; CAR-TR-362, Univ. of Maryland, Cent. Automat. Res. May 1988.
[4] A. S. Haynes and R. Jain, "Time-varying edge detection,"CVGIP, vol. 21, pp. 345-367, 1983.
[5] B. K. P. Horn and B. G. Schunck, "Determining optical flow,"Artificial Intell., vol. 17, pp. 185-203, 1981.
[6] R. Jain, W. N. Martin, and J. K. Aggarwal, "Segmentation through the detection of changes due to motion,"Comput. Vision Graphics Image Processing, vol. 11, pp. 13-34, 1979.
[7] A. R. Jain and H. -H. Nagel, "On the analysis of accumulative difference pictures from image sequences of real world scenes,"IEEE Trans. Patt. Anal. Machine Intell., vol. 1, pp. 206-214, 1979.
[8] A. D. Marr and A. S. Ullman, "Directional selectivity and its use in early visual processing," inProc. Royal Soc. London, vol. B211, pp. 151-180, 1981.
[9] E. W. Ng and M. Geller, "A table of integrals of the error functions,"J. Res. Nat. Bureau Standards-B. Math. Sc., vol. 73B, pp. 1-20, 1969.
[10] A. M. Waxman and F. Bergholm, "Convected activation profiles and image flow extraction," LSR-TR-4, Lab. Sensory Robotics, College of Eng., Boston Univ., Boston, MA, Aug. 1987.

Index Terms:
temporal variations; pattern recognition; optical flow; image sequences; temporal Gaussian smoothing function; zero crossings; moving edges; illumination effects; spatial variations; image intensity; lighting; optical information processing; pattern recognition; picture processing
J.H. Duncan, T.C. Chou, "On the Detection of Motion and the Computation of Optical Flow," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 3, pp. 346-352, March 1992, doi:10.1109/34.120329
Usage of this product signifies your acceptance of the Terms of Use.