This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Full Volumetric Descriptions From Three Intensity Images
May 1998 (vol. 20 no. 5)
pp. 540-545

Abstract—We address the problem of recovering high-level, volumetric and segmented (or part-based) descriptions of objects from intensity images. As input we use three closely spaced images of an object and recover descriptions based on Generalized Cylinders (GCCs). We start by extracting a hierarchy of groups from contour images in the three views. Grouping is based on proximity, parallelism, and symmetry. The groups in the three views are matched and their contours are labeled as "true" edges, which correspond to surface normal/reflectance discontinuities and "limb" edges, which are viewpoint dependent edges. We then infer the GC axis, its cross-section, and the scaling function. The properties of straight and curved axis generalized cylinders are used locally on the visible surfaces to obtain the GC axis. The cross-section is recovered if seen in the images, else it is inferred using the visible surfaces and GC properties. We consider groups with true edges, limb edges, or a combination of both. The final descriptions are volumetric and in terms of parts. The coarse volumetric descriptions obtained are then refined to include surface details as seen in the intensity images. We demonstrate results on real images of moderately complex objects with texture and shadows.

[1] I. Bergevin and M.D. Levine, "Generic Object Recognition: Building and Matching Coarse Descriptions from Line Drawings," IEEE Trans. Pattern Recognition and Machine Intelligence, vol. 15, no. 1, pp. 19-36, Jan. 1993.
[2] I. Biederman, "Recognition by Components: A Theory of Human Image Understanding," Psychological Review, vol. 94, no. 2, pp. 115-147, 1987.
[3] R. Cipolla and A. Blake, "Surface Shape from the Deformation of Apparent Contours," Int'l J. Computer Vision, vol. 9, no. 2, pp. 83-112, 1992.
[4] S.D. Cochran and G. Medioni, "3-D Surface Description From Binocular Stereo," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 10, pp. 981-994, Oct. 1992.
[5] U. Dhond and J.K. Aggarwal, "Structure From Stereo—A Review," IEEE Trans. Systems, Man, and Cybernetics, vol. 19, no. 6, pp. 1,489-1,510, Nov. 1989.
[6] A. Gross and T. Boult, "Recovery of Generalized Cylinders From a Single Intensity View," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 2, pp. 161-180, Feb. 1996.
[7] P. Havaldar, G. Medioni, and F. Stein, "Extraction of Groups for Recognition," Proc. European Conf. Computer Vision, vol. 1, pp. 251-261,Stolkholm, 1994.
[8] P. Havaldar, G. Medioni, and F. Stein, "Perceptual Grouping for Generic Recognition," Int'l J. Computer Vision, pp. 59-80, 1996.
[9] P. Havaldar and G. Medioni, "Segmented Shape Description From 3-View Stereo," Int'l Conf. Computer Vision, pp. 102-108,Boston, June 1995.
[10] P. Havaldar and G. Medioni, "Inference of Segmented, Volumetric Shape from 3 Intensity Images," Proc. Computer Vision and Pattern Recognition, pp. 278-284,San Francisco, June 1996.
[11] W. Hoff and N. Ahuja, "Surfaces From Stereo: Integrating Feature Matching, Disparity Estimation, and Contour Detection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 2, pp. 121-136, Feb. 1989.
[12] T. Joshi, N. Ahuja, J. Ponce, "Structure and Motion Estimation From Dynamic Silhouettes Under Perspective Projection," Int'l Conf. Computer Vision, pp. 290-295,Boston, June 1995.
[13] T. Kanade, "Recovery of the Three-Dimensional Shape of an Object From a Single View," Artificial Intelligence, vol. 17, pp. 409-460, 1981.
[14] D.J. Kriegman and J. Ponce, "On Recognizing and Positioning Curve 3-D Objects From Image Contours," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, pp. 1,127-1,137, Dec. 1990.
[15] A.K. Mackworth, "Interpreting Pictures of Polyhedral Scenes," Artificial Intelligence, vol. 4, pp. 121-137, 1973.
[16] R. Nevatia and T.O. Binford, "Description and Recognition of Complex Curved Objects," Artificial Intelligence, vol. 8, no. 1, pp. 77-98, 1977.
[17] J. Ponce, D. Chelberg, and W.B. Mann, "Invariant Properties of Straight Homogeneous Generalized Cylinders and Their Contours," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 9, pp. 951-966, Sept. 1989.
[18] H. Sato and T.O. Binford, "On Finding the Ends of SHGCs in an Edge Image," Proc. Image Understanding Workshop,San Diego, Jan. 1992.
[19] C. Tomasi and T. Kanade, "Factoring Image Sequences Into Shape and Motion," IEEE Workshop Visual Motion, pp. 21-28,Princeton, N.J., Oct. 1991.
[20] F. Ulupinar and R. Nevatia, "Perception of 3-D surfaces From 2-D Contours," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 1, pp. 3-18, Jan. 1993.
[21] F. Ulupinar and R. Nevatia, "Shape From Contour: Straight Homogeneous Generalized Cylinders and Constant Cross Section Generalized Cylinders," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 2, pp. 120-135, Feb. 1995.
[22] R. Vaillant and O.D. Faugeras, "Using Extremal Boundaries for 3-D Object Modelling," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 157-173, Feb. 1992.
[23] M. Zerroug and R. Nevatia, "Quasi-Invariant Properties and 3-D Shape Recovery of Non-Straight, Non-Constant Generalized Cylinders," Proc. Computer Vision and Pattern Recognition, pp. 96-103,New York, 1993.
[24] M. Zerroug and R. Nevatia, "Segmentation and Recovery of SHGCs from a Single Intensity Image," Proc. European Conf. Computer Vision, pp. 319-340,Stolkholm, 1994.
[25] M. Zerroug and R. Nevatia, "Segmentation and 3-D Recovery of Curved Axis Generalized Cylinders From an Intensity Image," Proc. Int'l Conf. Pattern Recognition, vol. A, pp. 678-681, 1994.
[26] Z.Y Zhang, R. Deriche, O. Faugeras, Q.T. Luong, "A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry," Artificial Intelligence, vol. 78, no. 1-2, Oct. 1995, pp. 87-119.

Index Terms:
Shape description, grouping, stereo, generalized cylinders.
Citation:
Parag Havaldar, Gérard Medioni, "Full Volumetric Descriptions From Three Intensity Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 5, pp. 540-545, May 1998, doi:10.1109/34.682183
Usage of this product signifies your acceptance of the Terms of Use.