ICIAP 1997: Image Analysis and Processing pp 462-469 | Cite as
Integral based approach for determining motion vector fields
Poster Session B: Active Vision, Motion, Shape, Stereo
First Online:
Abstract
This paper describes a method determining a motion vector field from an image sequence. In this method, a couple of a basic constraint equations in integral form and an additional constraint equation of spatio-temporal local constancy of a motion vector field is solved by the over-deterministic approach such as the least squares method. The method is applied to artificially synthesized image sequences and a real image one. As the results, robustness of the proposed method to noisy image sequences is confirmed. In addition, it is confirmed that the method requires less calculation cost than a conventional spatio-temporal optimization method.
Download
to read the full conference paper text
References
- 1.S. Maybank: Theory of reconstruction from image motion. Springer-Verlag (1993)Google Scholar
- 2.P. Anandan: Computing optical flow from two frames of an image sequence. COINS Technical Report 86-16 (1986)Google Scholar
- 3.B. K. P. Horn and B. G. Schunck: Determining optical flow. Artificial Intelligence 17 (1981) 185–203Google Scholar
- 4.J. K. Kearney, W. B. Thompson and D. L. Boley: Optical flow estimation: an error analysis of gradient-based methods with local optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-9 (1987) 229–244Google Scholar
- 5.A. Nomura, H. Miike and K. Koga: Field theory approach for determining optical flow. Pattern Recognition Letters 12 (1991) 183–190Google Scholar
- 6.J. Aisbett: Optical flow with an intensity-weighted smoothing. IEEE Transactions on Pattern Analysis and Machine Intelligence 11 (1989) 512–522Google Scholar
- 7.A. D. Bimbo, P. Nesi and J. L. C. Sanz: Analysis of optical flow constraints. IEEE Transactions on Image Processing 4 (1995) 460–469Google Scholar
- 8.N. Mukawa: Estimation of shape, reflection coefficients and illuminant direction from image sequences. Proceedings of the 3rd International Conference on Computer Vision (Osaka, Japan, 1990) 507–512Google Scholar
- 9.A. Nomura, H. Miike and K. Koga: Determining motion fields under non-uniform illumination. Pattern Recognition Letters 16 (1995) 285–296Google Scholar
- 10.K. Nakajima, A. Osa, T. Maekawa and H. Miike: Evaluation of body motion by optical flow analysis. Japanese Journal of Applied Physics 36 (1997) 2929–2937Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 1997