Abstract
Undeniably, the numerical evaluation of Computer Vision algorithms is of utmost importance. However, often neglected is the role of theoretical knowledge to interpret the numerical performance of those algorithms. In addition, the lack of theoretical research in Computer Vision has long been recognized. In this contribution, we demonstrate that extended theoretical knowledge of a phenomenon enables one to design algorithms that are better suited for the task at hand and to evaluate the theoretical assumptions of other, similar algorithms. For instance, the problem posed by multiple image motions was poorly understood in the frequency domain yet frequency-based multiple motions algorithms were developed. We present algorithms for computing multiple image motions arising from occlusion and translucency which are capable of extracting the information-content of occlusion boundaries and distinguish between those and additive translucency phenomena. These algorithms are based on recent theoretical results on occlusion in the frequency domain and demonstrate that a complete theoretical understanding of a phenomenon is required in order to design adequate algorithms. We conclude by proposing an evaluation protocol which includes theoretical considerations and their influence on the numerical evaluation of algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Beauchemin, S.S. and Barron, J.L. (1995) The computation of optical flow, ACM Computing Surveys, 27 (3): 433–467.
Beauchemin, S.S. and Barron, J.L. (1997a) A theoretical framework for discontinuous optical flow, submitted.
Beauchemin, S.S. and Barron, J.L. (1997b) The local frequency structure of 1D occluding image signals, submitted.
Beauchemin, S.S., Chalifour, A. and Barron, J.L. (1997) Discontinuous optical flow: Recent theoretical results, Vision Interface, Kelowna, Canada, 57–64.
Black, M.J. (1991) A robust gradient-method for determining optical flow, Technical Report YALEU/DCS/RR-891, Yale University, New-Haven, CT.
Black, M.J. and Jepson, A. (1994) Estimating optical flow in segmented images using variable-order parametric models with local deformations, Technical Report SPL-94053, Xerox Systems and Practices Laboratory, Palo Alto, California.
Jahne, B. (1990) Motion determination in space-time images, Proceedings of ECCV, Antibes, France, 161–173.
Jain, R.C. and Binford, T.O. (1991) Ignorance, myopia and naivete in computer vision systems, CVGIP: I U, 53: 112–117.
Jenkin, M.R.M., Jepson, A.D. and Tsotsos, J.K. (1991) Techniques for disparity measurement, CVGIP, 53 (1): 14–30.
Jepson, A.D. and Black, M. (1993) Mixture models for optical flow computation, IEEE. Proceedings of CVPR, New York, 760–761.
Longuet-Higgins, H.C. (1981) A computer algorithm for reconstructing a scene from two projections, Nature, 223: 133–135.
Murray, D.W. and Buxton, B.F. (1987) Scene segmentation from visual motion using global optimization, IEEE PAMI, 9 (2): 220–228.
Musmann, H.G., Pirsch, P. and Grallert, H.J. (1985) Advances in picture coding, Proc of IEEE, 73 (4): 523–548.
Nagel H.-H. (1987) On the estimation of optical flow: Relations between different approaches and some new results, Artificial Intelligence, 33: 299–324.
Negandaripour, S. and Lee, S. (1992) Motion recovery from image sequences using only first order optical flow information, IJCV, 9 (3): 163–184.
Overington, I. (1987) Gradient-based flow segmentation and location of the focus of expansion, Alvey Vision Conference, University of Cambridge, England, 860–870
Prince, J.L. and McVeigh, E.R. (1992) Motion estimation from tagged MR image sequences, IEEE Trans. on Medical Images, 11 (2): 238–249.
Schunck, B.G. (1989) Image flow segmentation and estimation by constraint line clustering, IEEE PAMI, 11 (10): 1010–1027.
Shizawa, M. and Mase, K. (1991) Principle of superposition: A common computational framework for analysis of multiple motion, IEEE Proceedings of Workshop on Visual Motion, Princeton, New Jersey, 164–172.
Wang, J.Y.A. and Adelson, E.H. (1993) Layered representation for motion analysis, Proceedings of CVPR’93, 361–366.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Beauchemin, S.S., Bajcsy, R. (2000). The Role of Theory in the Evaluation of Image Motion Algorithms. In: Klette, R., Stiehl, H.S., Viergever, M.A., Vincken, K.L. (eds) Performance Characterization in Computer Vision. Computational Imaging and Vision, vol 17. Springer, Dordrecht. https://doi.org/10.1007/978-94-015-9538-4_5
Download citation
DOI: https://doi.org/10.1007/978-94-015-9538-4_5
Publisher Name: Springer, Dordrecht
Print ISBN: 978-90-481-5487-6
Online ISBN: 978-94-015-9538-4
eBook Packages: Springer Book Archive