A Probabilistic Framework for Correspondence and Egomotion
This paper is an argument for two assertions: First, that by representing correspondence probabilistically, drastically more correspondence information can be extracted from images. Second, that by increasing the amount of correspondence information used, more accurate egomotion estimation is possible. We present a novel approach illustrating these principles.
We first present a framework for using Gabor filters to generate such correspondence probability distributions. Essentially, different filters ’vote’ on the correct correspondence in a way giving their relative likelihoods. Next, we use the epipolar constraint to generate a probability distribution over the possible motions. As the amount of correspondence information is increased, the set of motions yielding significant probabilities is shown to ’shrink’ to the correct motion.
KeywordsFeature Point Probabilistic Framework Rotational Error Epipolar Line Independent Motion
Unable to display preview. Download preview PDF.
- 1.Clocksin, W.F.: A new method for computing optical flow. In: BMVC (2000)Google Scholar
- 2.Harris, C.G., Stephens, M.: A combined corner and edge detector. In: AVC88, pp. 147–151 (1988)Google Scholar
- 4.Marr, D.: Vision: a computational investigation into the human representation and processing of visual information. W. H. Freeman, San Francisco (1982)Google Scholar
- 6.Fleet, D.: Disparity from local weighted phase-correlation. In: IEEE International Conference on SMC, pp. 46–48. IEEE Computer Society Press, Los Alamitos (1994)Google Scholar
- 11.Makadia, A., Geyer, C., Daniilidis, K.: Radon-based structure from motion without correspondences. In: CVPR (2005)Google Scholar