Abstract | ||
---|---|---|
This paper presents an algorithm that provides good estimates of the optical flow at motion discontinuities and occlusion regions based on the least-median-squares robust estimator. The use of a multiresolution scheme enables optical flow to be computed for objects with large motions. A movable overlapping neighbourhood strategy eliminates block-effects and also deals with cases of the local neighbourhood straddling regions of two or three motions. Results for both synthetic and real image sequences are presented. A quantitive comparison with the matching technique of Anandan (1989) and the differential technique of Odobez and Bouthemy (see Proceedings of 7th European Conference on Signal Processing, 1994) shows that the proposed algorithm gives much lower angular and absolute errors. |
Year | DOI | Venue |
---|---|---|
1996 | 10.1109/ICASSP.1996.544831 | Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference |
Keywords | Field | DocType |
image resolution,image segmentation,image sequences,least mean squares methods,absolute errors,algorithm,angular errors,block effects elimination,differential technique,large motions,least median squares robust estimator,local neighbourhood,matching technique,motion discontinuities,movable overlapping neighbourhood,occlusion regions,optical flow,real image sequences,robust multiresolution computation,synthetic image sequences | Computer vision,Mathematical optimization,Computer science,Image processing,Robust statistics,Robustness (computer science),Artificial intelligence,Real image,Motion estimation,Optical flow,Optical computing,Computation | Conference |
Volume | ISSN | ISBN |
4 | 1520-6149 | 0-7803-3192-3 |
Citations | PageRank | References |
6 | 0.73 | 5 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
eeping ong | 1 | 144 | 9.18 |
M. Spann | 2 | 411 | 104.62 |