Eduard Sojka
ABSTRACT
In this paper, we describe a new method for determining optical flow in image sequences. We present the explanation of the theoretical background, the description of the corresponding algorithm, and experimental results. The algorithm we propose is simple, relatively accurate and fast at the same time. Therefore, it may be used in applications in which the computational speed is critical. Due to its simplicity and due to the nature of instructions it mostly performs, it also has a good chance to be implemented on a special hardware and used in real time applications.
- Alvarez, L., Weickert, J., and Sanchez, J. 2000. Reliable Estimation of Dense Optical Flow Fields with Large Displacements. International Journal of Computer Vision 39, 41--56. Google Scholar
Digital Library
- Anandan, P. 1989. A Computational Framework and an Algorithm for the Measurement of Visual Motion. International Journal of Computer Vision 2, 3, 283--310.Google ScholarCross Ref
- Barron, J. L., Fleet, D. J., and Beauchemin, S. S. 1994. Performance of Optical Flow Techniques. International Journal of Computer Vision 12, 1, 43--77. Google ScholarDigital Library
- Beauchemin, T. S., and Barron, J. L. 1995. The Computation of Optical Flow. ACM Computing Surveys 27, 3, 433--467. Google ScholarDigital Library
- Black, M. J., and Fleet, D. J. 2000. Probabilistic Detection and Tracking of Motion Boundaries. International Journal of Computer Vision 38, 3, 231--245. Google ScholarDigital Library
- Brox, T., Bruhn, A., Papengerg, N., and Weickert, J. 2004. High accuracy optical flow estimation based on a theory of warping. In Proceedings of ECCV 2004, Springer-Verlag LNCS 3024, 25--36.Google Scholar
- Dubois, D., and Prade, H. 1988. Possibility Theory: An Approach to Computerized Processing of Uncertainty. Plenum Press, New York.Google ScholarCross Ref
- Dubois, D., Prade, H., and Smets, P. 1996. Representing Partial Ignorance. IEEE System Machine and Cybernetic 26, 361--377. Google ScholarDigital Library
- Dubois, D., Prade, H., and Sandri, S. 1993. On Possibility/Probability Transformations. In Fuzzy Logic: State of the Art, Kluwer Academic Publishers, Dordrecht, 103--112.Google Scholar
- Horn, B. K. P., and Schunck, B. G. 1981. Determining Optical Flow, Artificial Intelligence 17, 185--203.Google ScholarDigital Library
- Kim, Y. H., Martinez, A. M., and Kak, A. C. 2005. Robust Motion Estimation under Varying Illumination. Image and Vision Computing 23, 365--375. Google ScholarDigital Library
- Liu, H., Hong, T. H., Herman, M., Camus, T., and Chellappa, R. 1998. Accuracy vs Efficiency Trade-offs in Optical Flow Algorithms. Computer Vision and Image Understanding, 72, 3, 271--286. Google ScholarDigital Library
- Lucas, B., and Kanade, T. 1981. An iterative image registration technique with an application to stereo vision. In Proceedings of the International Joint Conference on Artificial Intelligence, 674--679. Google ScholarDigital Library
- Negahdaripour, S. 1998. Revised Definition of Optical Flow: Integration of Radiometric and Geometric Cues for Dynamic Analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20, 9, 961--979. Google ScholarDigital Library
- Singh, A. 1991. Optic Flow Computation: A Unified Perspective. IEEE Computer Society Press.Google Scholar
- Sun, C. 2002. Fast Optical Flow Using 3D Shortest Path Techniques. Image and Vision Computing 20, 981--991.Google ScholarCross Ref
- Teng, C. H., Lai, S. H., Chen Y. S., and Hsu W. H. 2005. Accurate Optical Flow Computation under Non-Uniform Brightness Variations. Computer Vision and Image Understanding 97, 315--346. Google ScholarDigital Library
- Yager, R. R. 1982. Level Sets for membership evaluation of fuzzy subsets. In Procceedings of Fuzzy Sets and Possibility Theory: Recent Developments, R. R. Yager, Ed., Pergamon Press, Oxford, 90--97.Google Scholar
- Zadeh, L. 1978. Fuzzy Sets as a Basis for a Theory of Possibility. Fuzzy Sets and Systems 1, 3--28.Google ScholarCross Ref
Index Terms
- An efficient algorithm for computing optical flow
Recommendations
Motion Field and Optical Flow: Qualitative Properties
It is shown that the motion field the 2-D vector field which is the perspective projection on the image plane of the 3-D velocity field of a moving scene, and the optical flow, defined as the estimate of the motion field which can be derived from the ...
On Benchmarking Optical Flow
Special issue on empirical evaluation of computer vision algorithmsEvaluating the performance of optical flow algorithms has been difficult because of the lack of ground truth data sets for complex scenes. We present a new method for generating motion fields from real sequences containing polyhedral objects and present ...
Highly accurate optical flow estimation on superpixel tree
Formulated as a pixel-labeling problem, optical flow estimation using efficient edge-aware filtering has shown great success recently. However, the typical challenge that restricts the range of applicability of this method is the computational ...
Comments