This Article 
 Bibliographic References 
 Add to: 
Integrating Vision Modules: Stereo, Shading, Grouping, and Line Labeling
September 1995 (vol. 17 no. 9)
pp. 831-842

Abstract—It is generally agreed that individual visual cues are fallible and often ambiguous. This has generated a lot of interest in design of integrated vision systems which are expected to give a reliable performance in practical situations. The design of such systems is challenging since each vision module works under a different and possibly conflicting set of assumptions. We have proposed and implemented a multiresolution system which integrates perceptual organization (grouping), segmentation, stereo, shape from shading, and line labeling modules. We demonstrate the efficacy of our approach using images of several different realistic scenes. The output of the integrated system is shown to be insensitive to the constraints imposed by the individual modules. The numerical accuracy of the recovered depth is assessed in case of synthetically generated data. Finally, we have qualitatively evaluated our approach by reconstructing geons from the depth data obtained from the integrated system. These results indicate that integrated vision systems are likely to produce better reconstruction of the input scene than the individual modules.

[1] D. Marr,Vision.San Francisco: W.H. Freeman and Co., 1982.
[2] T. Poggio, V. Torre, and C. Koch, “Computational Vision and Regularization Theory,” Nature, vol. 317, pp. 314-319, 1985.
[3] S. Grossberg, ed., Neural Networks and Natural Intelligence.Cambridge, Mass.: The MIT Press, 1988.
[4] S. Sarkar and K.L. Boyer, "Integration, Inference, and Management of Spatial Information Using Bayesian Networks: Perceptual Organization," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 3, pp. 256-274, Mar. 1993. Special Section on Probabilistic Reasoning.
[5] S. G. Nadabar and A. K. Jain,“Edge Detection and Labeling by Fusion of Intensity and Range Images,” Proc. SPIE Conf. on Applications of AI: Machine Vision and Robotics, vol. 1,708, pp. 108-119, 1992.
[6] A. Jepson and W. Richards,“A lattice framework for integrating vision modules,” IEEE Trans. Systems, Man, and Cybernetics, vol. 22, pp. 1,087-1,096, 1992.
[7] H.I. Bozma and J.S. Duncan, "A Game-Theoretic Approach to Integration of Modules," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, pp. 1,074-1,086, 1994.
[8] M. Kass,A. Witkin,, and D. Terzopoulos,“Snakes: Active contour models,” Int’l J. Computer Vision, vol. 1, pp. 321-331, 1988.
[9] A. Blake and A. Zisserman, Visual Reconstruction. MIT Press, 1987.
[10] S. Pankanti,A. K. Jain,, and M. Tuceryan,“On integration of vision modules,” Proc. IEEE Conf. Computer Vision and Pattern Recognition,Seattle, Wash., pp. 316-322, June 1994.
[11] J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp. 679-698, June 1986.
[12] T. Pavlidis, Algorithms for Graphics and Image Processing, pp. 199-201 Rockville, Md.: Computer Science Press, 1982.
[13] N. Ahuja and M. Tuceryan, “Extraction of Early Perceptual Structure in Dot Patterns: Integrating Region, Boundary, and Gestalt,” Computer Vision, Graphics, and Image Processing, vol. 48, pp. 304-356, 1989.
[14] S. Pankanti and A. K. Jain,“On integration of vision modules,” Tech. Rep. TR-CS, Michigan State Univ., June 1994.
[15] B. K. P. Horn,“Obtaining shape from shading information,” Shape from Shading, pp. 123-173,Cambridge, MA: The {MIT} Press, 1989.
[16] J. Oliensis, “Shape from Shading as a Partially Well-Constrained Problem,” Computer Vision, Graphics, and Image Processing: Image Understanding, vol. 54, pp. 163-183, 1991.
[17] J. Weng,N. Ahuja,, and T. S. Huang,“Matching two perspective views,” Trans. Pattern Analysis and Machine Intelligence Intell., vol. 14, no. 8, pp. 806-825, 1992.
[18] H. H. Bulthoff and H. A. Mallot,“Integration of depth modules: Stereo and shading,” J. Optical Society of America, vol. 5, pp. 1749-1758, Oct. 1988.
[19] W. Grimson,“Binocular shading and visual surface reconstruction,” Computer Vision, Graphics, and Image Processing, vol. 28, pp. 19-43, 1984.
[20] A. Blake,A. Zisserman,, and G. Knowles,“Surface descriptions from stereo and shading,” Shape from Shading (B.K.P. Horn and M.J. Brooks, eds.), ch. 2, pp. 29-52,Cambridge, Mass The MIT Press, 1989.
[21] Y.G. Leclerc and A.F. Bobick, “The Direct Computation of Height from Shading,” IEEE Computer Vision and Pattern Recognition, pp. 552-558, 1991.
[22] J. Cryer, P. Tsai, and M. Shah, “Integration of Shape from x Modules: Combining Stereo and Shading,” IEEE Proc. Computer Vision and Pattern Recognition, pp. 720-721, June 1993.
[23] J. Malik,“Interpreting line drawings of curved objects,” Int’l J. Computer Vision, vol. 1, pp. 73-103, 1987.
[24] D. A. Trytten, Integrating Diverse Perceptual Modules to Create a 2.5 Dimensional Sketch, PhD thesis, Michigan State Univ., E. Lansing, Mich., 1992.
[25] E. Lehmann,Nonparametrics: Statistical Methods Based on Ranks.San Francisco: Holden-Day, 1975.
[26] S.K. Nayar, X. Fang, and T. Boult, Removal of Specularities Using Color and Polarization Proc. Computer Vision and Pattern Recognition, pp. 583-590, 1993.
[27] V.S. Nalwa,“Line-drawing interpretation: A mathematical framework,” Int’l J. Computer Vision, vol. 2, pp. 103-124, 1988.
[28] T. Lozano-Perèz,W.E.L. Grimson,, and S.J. White,“Finding cylinders in range data,” Proc. IEEE Int’l Conf. on Robotics&Automation,(Raleigh, N.C.), pp. 202-207, 1987.

Index Terms:
Stereo, shape from shading, perceptual organization, line labeling, integration, fusion.
Sharath Pankanti, Anil K. Jain, "Integrating Vision Modules: Stereo, Shading, Grouping, and Line Labeling," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 9, pp. 831-842, Sept. 1995, doi:10.1109/34.406649
Usage of this product signifies your acceptance of the Terms of Use.