Abstract
In this paper we explore a multiple hypothesis approach to estimating rigid motion from a moving stereo rig. More precisely, we introduce the use of Gaussian mixtures to model correspondence uncertainties for disparity and image velocity estimation. We show some properties of the disparity space and show how rigid transformations can be represented. An algorithm derived from standard random sampling-based robust estimators, that efficiently estimates rigid transformations from multi-hypothesis disparity maps and velocity fields is given.
Similar content being viewed by others
References
Bergen, J., Anadan, P., Hanna, K., and Hingorami, R. 1992. Hierarchical model-based motion estimation. In European Conference on Computer Vision, pp. 237–252.
Bregler, C. 1997. Learning and recognizing human dynamics in video sequences. In Proc. Computer Vision and Pattern Recognition, pp. 568–574.
Demirdjian, D. and Darrell, T. 2001. Motion estimation from disparity images. In International Conference on Computer Vision, vol. I, pp. 213–218.
Demirdjian, D. and Horaud, R. 2000. Motion-egomotion discrimination and motion segmentation from image-pair streams. Computer Vision and Image Understanding, 78(1):53–68.
Devernay, F. and Faugeras, O. 1996. From projective to Euclidean reconstruction. In Proc. Computer Vision and Pattern Recognition Conference, San Francisco, CA, June 1996, pp. 264–269.
Fischler, M.A. and Bolles, R.C. 1981. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Graphics and Image Processing, 24(6):381–395.
Harris, C. and Stephens, M. 1988. A combined corner and edge detector. In Alvey Vision Conference, 1988, pp. 147–151.
Harville, M., Rahimi, A., Darrell, T., Gordon, G., and Woodfill, J. 1999. 3D Pose tracking with linear depth and brightness constraints. In Proc. International Conference on Computer Vision, Bombay, pp. 206–213.
Horn, B.K.P., Hilden, H.M., and Negahdaripour, S. 1988. Closed-form solution of absolute orientation using orthonormal matrices. Journal of the Optical Society of America, 5(7):1127–1135.
Irani, M., Rousso, B., and Peleg, S. 1994. Computing occluding and transparent motions. In International Journal on Computer Vision, pp. 5–16.
Koenderink, J. and van Doorn, A. 1991. Affine structure from motion. Journal of the Optical Society of America A, 8(2):377–385.
Lhuillier, M. and Quan, L. 2000. Robust dense matching using local and global geometric constraints. In Proc. of the 16th International Conference on Pattern Recognition, Barcelona, Spain, vol. 1, pp. 968–972.
O'Neill, M. and Denos, M. 1996. Automated system for coarse-to-fine pyramidal area correlation stereo matching. Image and Vision Computing, 14(3):225–236.
Shi, J. and Tomasi, C. 1994. Good features to track. In Proc. Computer Vision and Pattern Recognition, IEEE Computer Society, Seattle, Washington, June 1994, pp. 593–600.
Stein, G.P. and Shashua, A. 1998. Direct estimation of motion and extended scene structure from a moving stereo rig. In Proc. Computer Vision and Pattern Recognition.
Zhang, Z., Deriche, R., Faugeras, O., and Luong, Q. 1995. A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry. Artificial Intelligence, 78:87–119.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Demirdjian, D., Darrell, T. Using Multiple-Hypothesis Disparity Maps and Image Velocity for 3-D Motion Estimation. International Journal of Computer Vision 47, 219–228 (2002). https://doi.org/10.1023/A:1014502126337
Issue Date:
DOI: https://doi.org/10.1023/A:1014502126337