Abstract
If stereopsis is to be used in a dynamic environment, it makes little sense to re-compute the entire representation of disparity space from scratch at each time step. One simple approach would be to use the results from the current solution to “prime” the algorithm for the next solution. If three dimensional trajectory information was available, this information could be used to first update the previous solution, and then this updated solution could be used to “prime” the algorithm for the following stereo pair. Recent work[4, 5] has demonstrated that it is possible to measure such trajectory information very quickly without complex token or feature extraction. This paper demonstrates how raw disparity measurement made by this earlier technique can be integrated into a single trajectory measurement at each image point. A mechanism is then proposed that updates a stereopsis algorithm operating in a dynamic environment using this trajectory information.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
E. H. Adelson and J. R. Bergen. Spatiotemporal energy models for the perception of motion. J. Optical Society of America A, 2(2):284–299, 1985.
K.I. Beverley and D. Regan. Evidence for the existance of neural mechanisms selectively sensitive to direction of movement. J. Physiology, 193:17–29, 1973.
M. R. M. Jenkin. Tracking three-dimensional moving light displays. In 1983 ACM SIGARTSIGGRAPH Workshop on Motion, pages 66–70, Toronto, 1983.
M. R. M. Jenkin and A. Jepson. Measuring trajectory. In IEEE Workshop on Visual Motion, pages 31–37, Irvine, California, 1989.
M. R. M. Jenkin and A. Jepson. Response profiles of trajectory detectors. IEEE Transactions on Systems, Man and Cybernetics, 19(6):1617–1622, 1989.
M. R. M. Jenkin, A. D. Jepson, and J. K. Tsotsos. Techniques of disparity measurement. Technical Report RBCV-TR-87-16, Researches in Biological and Computational Vision, Department of Computer Science, University of Toronto, 1987.
M. R. M. Jenkin and J. K. Tsotsos. Applying temporal constraints to the dynamic stereo problem. Computer Vision, Graphics, and Image Processing, 33:16–32, 1986.
A. Jepson and M. R. M. Jenkin. The fast computation of disparity from phase differences. In CVPR 89, pages 398–403, San Diego, California, 1989.
T. J. Olson and R. D. Potter. Real-time vergence control. In CVPR 89, pages 404–409, San Diego, California, 1989.
T. Poggio and W. H. Talbot. Mechanisms of static and dynamic stereopsis in foveal cortex of rhesus monkey. J. Physiology, 315:469–492, 1981.
T. D. Sanger. Stereo disparity computation using gabor filters. Biol. Cybern., 59:405–418, 1988.
A. M. Waxman and J. H. Duncan. Binocular image flows: steps towards stereo-motion fusion. Technical Report CAR-TR-119, Centre for Automation Research, University of Maryland, May 1985.
A. M. Waxman and S. S. Sinha. Dynamic stereo: Passive ranging to moving objects from relative image flows. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(4):406–412, 1986.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jenkin, M.R.M. (1990). On the use of trajectory information to assist stereopsis in a dynamic environment. In: Faugeras, O. (eds) Computer Vision — ECCV 90. ECCV 1990. Lecture Notes in Computer Science, vol 427. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0014882
Download citation
DOI: https://doi.org/10.1007/BFb0014882
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-52522-6
Online ISBN: 978-3-540-47011-3
eBook Packages: Springer Book Archive