Abstract
We examine the problem of computing shape descriptions from stereo, where by shape descriptions we mean 3-D volumetric descriptions of objects rather than a 2 /12-D depth map of the scene. We argue that intermediate 2 /12-D depth measurements may not be always directly available from stereo, especially when there are curved surfaces in the scene, and that 3-D volumetric descriptions of objects may have to be derived directly from stereo correspondences. We then present methods to recover volumetric shape from stereo using LSHGCs and SHGCs as the shape models. Our methods are based on some invariant properties of LSHGCs and SHGCs in their monocular and stereo projections. Experimental results on both synthetic and real images of objects with curved surfaces are given. Our technique allows dense surface descriptions to be recovered even for objects without much texture, and it is not restricted to narrow stereo angles or low resolution images. Our technique can also handle objects in close range where perspective distortion in the images can be significant.
Similar content being viewed by others
References
Barrow, H.G. and Tenenbaum, J.M. 1981. Interpretting line drawings as three dimensional surfaces. Artificial Intelligence, 17:75–116.
Biederman, I. 1987. Recognition by components. Psychological Review, 94:115–147.
Binford, T.O. 1971. Visual perception by computer. In IEEE Conference on Systems and Controls, Miami, Florida.
Brooks, R.A. 1983. Model based three dimensional interpretations of two-dimensional images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 5(2):140–150.
Canny, J.F. 1986. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6):679–698.
Chung, R. and Nevatia, R. 1991. Use of monocular groupings and occlusion analysis in a hierarchical stereo system. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Maul, Hawaii, pp. 50–56.
Chung, R. and Nevatia, R. 1992. Recovering LSHGCs and SHGCs from stereo. In Proceedings of the IEEE Conference on computer Vision, and Pattern Recognition, Champaign, Illinois, pp. 42–48.
Chung, R. and Nevatia, R. 1995. Use of monocular groupings and occlusions analysis in a hierarchical stereo system. Computer Vision and Image Understanding, 62(3):245–268.
Clowes, M.B. 1971. On seeing things. Artificial Intelligence, 2(1):79–116.
Dhond, U.R. and Aggarwal, J.K. 1989. Structure from stereo—A review. IEEE Transactions on Systems, Man and Cybernetics, 19(6):1489–1510.
Horaud, R. and Brady, M. 1988. On the geometric interpretation of image contours. Artificial Intelligence, 37:333–353.
Huffman, D. 1971. Impossible objects as nonsense sentences. In Machine Intelligence 6, B.Meltzer and D.Michie (Eds.), pp. 295–323. Edinburgh University Press: Edinburgh.
Kanade, T. 1981. Recovery of the three-dimensional shape of an object from a single view. Artificial Intelligence, 17:409–460.
Lim, H.S. and Binford, T.O. 1988. Curved surface reconstruction using stereo correspondence. In Proceedings of the DARPA Image Understanding Workshop, Cambridge, Massachusetts, pp. 809–819.
Mackworth, A. 1973. Interpreting pictures of polyhedral scenes. Artificial Intelligence, 4:121–137.
Mohan, R. and Navatia, R. 1989a. Segmentation and description based on perceptual organization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Diego, California, pp. 333–341.
Mohan, R. and Nevatia, R. 1989b. Using perceptual organization to extract 3-D structures. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(11):1121–1139.
Ponce, J. Chelberg, D., and Mann, W.B. 1989. Invariant properties of straight homogeneous generalized cylinders and their contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(9):951–966.
Rao, K. 1988. Shape description from sparse and imperfect data. Ph.D. thesis, University of Southern California, IRIS fechnical Report 250.
Rao, K. and Navatia, R. 1987. Computing volume descriptions from sparse 3-D data. International Journal of Computer Vision, 2(1):33–50.
Shafer, S.A. and Kanade, T. 1983. The theory of straight homogeneous generalized cylinders. Technical Report CMU-CS-083-105, Carnegie, Mellon University.
Stevens, K.A. 1981. The visual interpretations of surface contours. Artificial Intelligence, 17:47–73.
Terzopoulos, D. 1986. Regularization of inverse visual problems involving discontinuities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8:413–424.
Ulupinar, F. and Nevatia, R. 1990a. Inferring shape from contour for curved surfaces. In Proceedings of the International Conference on Pattern Recognition, Atlantic City, New Jersey, Vol. 1, pp. 147–154.
Ulupinar, F. and Nevatia, R. 1990b. Recovering shape from contour for SHGCs. In Proceedings of the DARPA Image Understanding Workshop, pp. 544–556, Pittsburgh, Pennsylvania.
Xu, G. Tanaka, H.T. and Tsuji, S. 1992. Right straight homogeneous generalized cylinders with symmetrical cross-sections: Recovery of pose and shape from image contours. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Champaign, Illinois, pp. 692–694.
Xu, G. and Tsuji, S. 1987. Inferring surfaces from boundaries. In Proceedings of the IEEE International Conference on Computer Vision, London, pp. 716–720.
Zerroug, M. and Nevatia, R. 1993. Scene segmentation and volumetric descriptions of SHGCs from a single intensity image. In Proceedings of the DARPA Image Understanding Workshop, Washington, D.C.
Author information
Authors and Affiliations
Additional information
This research was performed at Institute for Robotics and Intelligent Systems, University of Southern California. It was supported by the Advanced Research Projects Agency of the Department of Defense and was monitored by the Air Force Office of Scientific Research under Contract No. F49620-90-C-0078. The United States Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright notation hereon.
Rights and permissions
About this article
Cite this article
Chung, R., Nevatia, R. Recovering LSHGCs and SHGCs from stereo. Int J Comput Vision 20, 43–58 (1996). https://doi.org/10.1007/BF00144116
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00144116