Abstract
We present a new approach to the stereo-matching problem. Images are individually described by aneighborhood graph of line segments coming from a polygonal approximation of the contours. The matching process is defined as the exploration of the largest components of adisparity graph built from the descriptions of the two images, and is performed by an efficient prediction and propagation technique. This approach was tested on a variety of man-made environments, and it appears to be fast and robust enough for mobile robot navigation and three-dimensional part-positioning applications.
Similar content being viewed by others
References
D. Marr and T. Poggio, “Cooperative computation of stereo disparity,” SCIENCE vol. 194, pp. 283–287, 1976.
W.E.L. Grimson. FROM IMAGES TO SURFACES. M.I.T. Press: Cambridge, MA, 1981.
W.E.L. Grimson. “Computational experiments with a feature based stereo algorithm,” M.I.T., Cambridge, MA, A.I. Memo. 762, 1984.
Y. Ohta and T. Kanade, “Stereo by intra- and interscanline search,” IEEE TRANS. PAMI vol. PAMI-7, pp. 139–154, 1985.
H. Baker and T.O. Binford, “Depth from edge and intensity based stereo,” in PROC. 7TH INT. JOINT CONF. ARTIF. INTELL., Vancouver, Canada, 1981, pp. 631–636.
K. Ben Rhouma et al., “A K2-D perception approach for assembly robots,” in PROC. EURASIP 1983, Erlangen, FRG, 1983.
M. Benard, “Extracting 3-D coordinates of an object from a digital stereopair: an automated method,” in PROC EURASIP, Erlangen, FRG, 1983, pp. 227–230.
R. Mohr and W. Wrobel, “La correspondance en stéréovision vue comme unc recherche de chemin optimal” [in French], in PROC. 4TH AFCET-INRIA CONF. REC. FORMES INTELL. ARTIF., 1984, pp. 71–79.
G. Medioni and R. Nevatia, “Segment based stereo matching,” in PROC. IMAGE UNDERSTANDING WORKSHOP, Arlington, VA, 1983, pp. 128–136.
M. Berthod and P. Long, “Graph matching by parallel optimization methods: an application to stereo vision,” in PROC. 7TH INT. CONF. PATTERN RECOGNITION, Montreal, Canada, 1984, pp. 841–843.
S.T. Barnard and W.B. Thompson, “Disparity analysis of images,” IEEE TRANS. PAMI vol. PAMI-2, pp. 333–340, 1980.
J.E.W. Mayhew and J.P. Frisby, “Computational and psychophysical studies towards a theory of human stereopsis,” ANTIF. INTELL. vol. 17, pp. 349–386, 1981.
S. Pollard, J. Porril, J. Mayhew, and J. Frisby, “Disparity gradient, Lipschitz continuity, and computing binocular correspondence,” University of Sheffield, England, Intern. Rep. AIVRU-010, 1986.
H.K. Nishihara, “Prism, a practical real-time imaging stereo matcher,” M.I.T., Cambridge, MA, A.I. Memo. 780, 1984, 31 pages.
S. Castan and J. Shen, “A stereo vision algorithm taking into account the perspective distorsions,” in PROC. 7TH INT. CONF. PATTERN RECOGNITION, Montreal, Canada, 1984, pp. 444–446.
H.P. Moravec, “Towards automatic visual obstacle avoidance,” in PROC. 5TH INT. JOINT CONF. ARTIF. INTELL., Cambridge, MA, 1977, p. 584.
R. Nevatia, “Depth measurement by motion stereo,” COMPUT. VISION, GRAPHICS AND IMAGE PROCESSING vol. 5, pp. 203–214, 1976.
D.B. Gennery, “A stereovision system for an autonomous vehiele,” in PROC. 5TH INT. JOINT CONF. ARTIF, INTELL., Cambridge, MA, 1977, pp. 576–582.
K. Mori, M. Kidode, and H. Asada, “An iterative prediction and correction method for automatic stereocomparison,” COMPUT. VISION, GRAPHICS IMAGE PROCESSING vol. 2, pp. 393–401, 1973.
M.D. Levine et al., “Computer determination of depth maps,” COMPUT. VISION, GRAPHICS IMAGE PROCESSING vol. 2, pp. 131–150, 1973.
J.J. Hwang and E.L. Hall, “Matching of featured objects using relational tables from stereo images,” COMPUT. VISION, GRAPHICS IMAGE PROCESSING vol. 20, pp. 22–42, 1982.
G. Poggio and T. Poggio, “The analysis of stereopsis,” ANNU. REV. NEUROSCI. vol. 7, pp. 379–412, 1984.
N. Ayache and B. Faverjon, “Fast stereo matching of edge segments using prediction and verification of hypotheses,” in PROC. CONF. COMPUT. VISION AND PATTERN RECOGNITION, San Francisco, CA, 1985, pp. 662–664.
N. Ayache and B. Faverjon, “A fast stereovision matcher based on prediction and recursive verification of hypotheses,” in PROC. 3RD WORKSHOP COMPUT. VISION: REPRESENTATION AND CONTROL, Bellaire, MI, 1985, pp. 27–37.
D. Marr and E. Hildreth, “Theory of edge detection,” PROC. R. SOC. LONDON [B] vol. 207, pp. 187–217, 1980.
N. Keskes, A. Boulanouar, and O.D. Faugeras, “Application of images analysis techniques to seismic data,” in PROC. INT. CONF. ASSP, Paris, pp. 855–857, 1982.
N. Ayache and O.D. Faugeras, “Hyper: a new approach for the recognition and positioning of 2-D objects,” IEEE TRANS. PAMI vol. PAMI-8, pp. 44–54, 1986.
J.F. Canny, “Finding edges and lines in images,” M.I.T. Artif. Intell. Lab., Cambridge, MA, A.I. Memo, 720, 1983.
R.Deriche, “Optimal edge detection using recursive filtering,” INT. J. COMPUT. VISION, 1987.
T. Pavlidis, STRUCTURAL PATTERN RECOGNITION. Springer-Verlag: New York, 1977.
M. Berthod, “Polygonal approximation of edge chains,” INRIA Intern. Rep. 1987 (in press).
D. Knuth, THE ART OF COMPUTER PROGRAMMING, vol. 3: SORTING AND SEARCHING. Addison Wesley: Reading, MA, 1975.
O.D. Faugeras and G. Toscani, “The calibration problem for stereo,” in PROC. CONF. COMPUT. VISION AND PATTERN RECOGNITION, Miami, FL, 1986, pp. 15–20.
R.D. Arnold and T.O. Binford, “Geometric constraints in stereo vision,” in PROC. SPIE, 238, San Diego, CA, 1980, pp. 281–292.
N. Ayache, O.D. Faugeras, B. Faverjon, and G. Toscani, “Matching depth maps obtained by passive stereovision,” in PROC. 3RD WORKSHOP COMPUT. VISION: REPRESENTATION AND CONTROL, Bellaire, MI, 1985, pp. 197–204.
O.D. Faugeras, N. Ayache, and B. Faverjon, “Building visual maps by combining noisy stereo measurements,” in PROC. INT. CONF. ROBOTICS AND AUTOMATION, vol. 3, San Francisco, CA, 1986, pp. 1433–1438.
N. Ayache and O.D. Faugeras, “Building, registrating and fusing noisy visual maps,” in PROC. 1ST INT. CONF. COMPUT. VISION, London, England, 1987.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Ayache, N., Faverjon, B. Efficient registration of stereo images by matching graph descriptions of edge segments. Int J Comput Vision 1, 107–131 (1987). https://doi.org/10.1007/BF00123161
Issue Date:
DOI: https://doi.org/10.1007/BF00123161