The Community for Technology Leaders
RSS Icon
Issue No.03 - March (2010 vol.32)
pp: 416-430
Ankur Agarwal , Microsoft Research UK Ltd., Cambridge
Stereo matching algorithms conventionally match over a range of disparities sufficient to encompass all visible 3D scene points. Human vision, however, works over a narrow band of disparities—Panum's fusional band—whose typical range may be as little as 1/20 of the full range of disparities for visible points. Only points inside the band are fused visually; the remainder of points are seen diplopically. A probabilistic approach is presented for dense stereo matching under the Panum band restriction. It is shown that existing dense stereo algorithms are inadequate in this problem setting and the main problem is segmentation, marking the image into the areas that fall inside the band. An approximation is derived that makes up for missing out-of-band information with a “proxy” based on image autocorrelation. It is shown that the Panum Proxy algorithm achieves accuracy close to what can be obtained when the full disparity band is available, and with gains of between one and two orders of magnitude in computation time. There are also substantial gains in computation space. Panum band processing is also demonstrated in an active stereopsis framework.
Stereoscopic vision, energy minimization, Panum's fusional area, 3D vision, active vision.
Ankur Agarwal, "Dense Stereo Matching over the Panum Band", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.32, no. 3, pp. 416-430, March 2010, doi:10.1109/TPAMI.2008.298
[1] A.L. Abbott and N. Ahuja, “Surface Reconstruction by Dynamic Integration of Focus, Camera Vergence, and Stereo,” Proc. Int'l Conf. Computer Vision, pp. 532-541, 1988.
[2] A. Agarwal and A. Blake, “The Panum Proxy Algorithm for Dense Stereo Matching over a Volume of Interest,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 2339-2346, 2006.
[3] H.H. Baker and T.O. Binford, “Depth from Edge and Intensity Based Stereo,” Proc. Int'l Joint Conf. Artificial Intelligence, pp. 631-636, 1981.
[4] P.N. Belhumeur, J.P. Hespanha, and D.J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” Proc. European Conf. Computer Vision, pp. 45-58, 1996.
[5] Y.Y. Boykov and M.-P. Jolly, “Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images,” Proc. Int'l Conf. Computer Vision, pp. 105-112, 2001.
[6] Y.Y. Boykov, O. Veksler, and R.D. Zabih, “Fast Approximate Energy Minimization via Graph Cuts,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 11, pp. 1222-1239, Nov. 2001.
[7] C.M. Brown, D. Coombs, and J. Soong, “Real-Time Smooth Pursuit Tracking,” Active Vision, A. Blake and A.L. Yuille, eds., pp.123-136, MIT Press, 1992.
[8] I.J. Cox, S.L. Hingorani, and S.B. Rao, “A Maximum Likelihood Stereo Algorithm,” Computer Vision and Image Understanding, vol. 63, no. 3, pp. 542-567, 1996.
[9] A. Criminisi, J. Shotton, A. Blake, and P.H.S. Torr, “Gaze Manipulation for One to One Teleconferencing,” Proc. Int'l Conf. Computer Vision, pp. 191-198, 2003.
[10] J. Frisby and J. Mayhew, “The Role of Spatial Frequency Tuned Channels in Vergence Control,” Vision Research, vol. 20, pp. 727-732, 1980.
[11] H. Hirschmuller and D. Scharstein, “Evaluation of Cost Functions for Stereo Matching,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2007.
[12] B. Julesz, Foundations of Cyclopean Perception. Univ. of Chicago Press, 1971.
[13] T. Uhlin, K. Pahlavan, and J.-O. Eklundh, “Dynamic Fixation,” Proc. Int'l Conf. Computer Vision, pp. 412-419, 1993.
[14] V. Kolmogorov, A. Criminisi, A. Blake, G. Cross, and C. Rother, “Probabilistic Fusion of Stereo with Colour and Contrast for Bi-Layer Segmentation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 9, pp. 1480-1492, Sept. 2006.
[15] V. Kolmogorov and R. Zabih, “Computing Visual Correspondences with Occlusions Using Graph Cuts,” Proc. Int'l Conf. Computer Vision, 2001.
[16] V. Kolmogorov and R. Zabih, “Multi-Camera Scene Reconstruction via Graph Cuts,” Proc. European Conf. Computer Vision, pp. 82-96, 2002.
[17] Y. Ohta and T. Kanade, “Stereo by Intra- and Inter-Scan Line Search Using Dynamic Programming,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 7, no. 2, pp. 139-154, 1985.
[18] G.F. Poggio and T. Poggio, “The Analysis of Stereopsis,” Ann. Rev. Neuroscience, vol. 7, pp. 379-412, 1984.
[19] I.D. Reid and D.W. Murray, “Tracking Foveated Corner Clusters Using Affine Structure,” Proc. Int'l Conf. Computer Vision, pp. 76-83, 1993.
[20] D. Scharstein and R. Szeliski, “A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms,” Int'l J. Computer Vision, vol. 47, nos. 1-3, pp. 7-42, 2002.
59 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool