| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Optical Flow with an Intensity-Weighted Smoothing
May 1989 (vol. 11 no. 5)
pp. 512-522
Matching algorithms which use image structure such as edges and junctions cannot perform well on unstructured images. For such images, global gradient-based methods may be more appropriate. Some of the assumptions involved in applying discretized conservation equations such as the optical flow equation are discussed and an intensity-weighted method of estimating dense displacement fields is presented, which attempts to avoid some of the problems of the standard methods. The only derivative required is the intensity gradient, and the method includes procedures for automatic parameter evaluation. The algorithm is expected to perform better than conventional algorithms on images without strong texture, as is demonstrated on the test set of images.
[1] H.-H. Nagel, "Displacement vectors derived from second-order intensity variations in image sequences,"Comput. Vision, Graphics, Image Processing, vol. 21, no. 1, pp. 85-117, 1983.
[2] W. E. L. Grimson, "Computational experiments with a feature based stereo algorithm, "IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-7, pp. 17-34, Jan. 1985.
[3] W. Hoff and N. Ahuja, "Surfaces from stereo," inProc. Int. Conf. Pattern Recognition, 1986, pp. 516-519.
[4] B. K. P. Horn and B. G. Schunck, "Determining optical flow,"Artificial Intell., vol. 17, pp. 185-203, 1981.
[5] H.-H. Nagel, "Constraints for the estimation of displacement vector fields from image sequences," inProc. Int. Joint Conf. Artificial Intell., Karlsruhe Germany, 1983, pp. 945-951.
[6] H.-H. Nagel and W. Enkelmann, "An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, no. 5, pp. 565-593, Sept. 1986.
[7] R. C. Bolles, H. H. Baker, and D. H. Marimont, "Epipolar-plane image analysis: An approach to determining structure from motion,"Int. J. Comput. Vision, vol. 1, no. 1, pp. 7-56, 1987.
[8] O. Faugeras, F. Lustman, and G. Toscani, "Motion and structure from motion from point and line matches," inProc. 1st. Int. Conf. Comput. Vision, 1987, pp. 25-34.
[9] T. Tsukiyama and T. S. Huang, "Motion stereo for navigation of autonomous vehicles in man-made environments," inProc. Int. Conf. Pattern Recognition, 1986, pp. 165-168.
[10] M. Herman and T. Kanade, "Incremental reconstruction of 3D scenes from multiple, complex images,"Artificial Intell., vol. 30, pp. 289-341, 1986.
[11] L. Demling, R. Ottenjann, and K. Elster,Endoscopy and Biopsy of the Esophagus and Stomach. A Color Atlas. Philadelphia, PA: Saunders, 1972.
[12] D. J. Nolan,The Double-Contrast Barium Meal-A Radiological Atlas. Buckinghampshire: HM and M, 1980.
[13] H. T. Verstappen,Remote Sensing in Geomorphology. Amsterdam: Elsevier, 1977.
[14] B. G. Schunck, "Image flow continuity equations for motion and density," inProc. Workshop Motion, 1986.
[15] S. T. Barnard and W. B. Thompson, "Disparity analysis of images,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-2, pp. 333- 340, July 1980.
[16] K. Price, "Relaxation matching techniques--A comparison,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-7, pp. 617-623, Sept. 1985.
[17] C. Fennema and W. Thompson, "Velocity determination in scenes containing several moving objects,"Comput. Graphics Image Processing, vol. 9, pp. 301-315, 1979.
[18] J. M. Fitzpatrick, "A method for calculating velocity in time dependent images based on the continuity equation," inProc. IEEE Conf. Comput. Vision Pattern Recognition, 1985, pp. 78-81.
[19] B. G. Schunck, "The image flow contraint equation,"Comput. Vision Graphics Image Proc., vol. 35, pp. 20-46, 1986.
[20] E. Hildreth,The Measurement of Visual Motion, Cambridge, MA: MIT Press, 1983.
[21] P. Anandan, "Computing dense displacement fields with confidence measures in scenes containing occlusion,"SPIE Int. Robots Comput. Vision, vol. 521, 1984, pp. 184-194.
[22] J.K. Kearny, W.B. Thompson, and D.L. Boley, "Optical flow estimation: An error analysis of gradient-based methods with local optimization,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, pp. 229-244, Mar. 1987.
[23] P. Beaudet, "Rotationally invariant image operators," inProc. IEEE Conf. Pattern Recognition, 1978, pp. 579-583.
[24] P. E. Gill, W. Murray, and M. H. Wright,Practical Optimization. London: Academic, 1981.
[25] K. Prazdny, "Detection of binocular disparities,"Biol. Cybern., vol. 52, pp. 93-99, 1985.
[26] A. Verri and T. Poggio, "Against quantitative optical flow," inProc. 1st Int. Conf. Comput. Vision, 1987, pp. 171-180.
Index Terms:
picture processing; pattern recognition; intensity-weighted smoothing; global gradient-based methods; discretized conservation equations; optical flow equation; dense displacement fields; intensity gradient; automatic parameter evaluation; pattern recognition; picture processing
Citation:
J. Aisbett, "Optical Flow with an Intensity-Weighted Smoothing," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 5, pp. 512-522, May 1989, doi:10.1109/34.24783
