This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Patch-Based Stereo in a General Binocular Viewing Geometry
March 1997 (vol. 19 no. 3)
pp. 247-253

Abstract—This paper presents a one-stage stereo algorithm that yields 3D planar surface patches directly from matching image patch intensity information. The method allows an arbitrary rotation and translation between the cameras; it is not limited to parallel-axis, narrow-baseline, or vergent geometries. The key to the approach is to match image patches that have positions, shapes, sizes, orientations, and samplings consistent with a hypothesized surface patch and with each other. The match error then reflects only the mismatch of patch contents and not the mismatch of patch geometries or samplings. The algorithm is quantitatively evaluated against ground truth on real images with difficult viewing geometries, and demonstrates an average accuracy of about 1% in estimating surface depths and 10° in estimating surface normals.

[1] S. Barnard and M. Fischler, "Computational Stereo," Computing Surveys, vol. 14, pp. 555-572, 1982.
[2] J.R. Bergen, P. Anandan, K.J. Hanna, and R. Hingorani, "Hierarchical Model-Based Motion Estimation," Proc. Second European Conf. Computer Vision, pp. 237-252, 1992.
[3] F. Devernay and O.D. Faugeras, "Computing Differential Properties of 3D Shapes from Stereoscopic Images Without 3D Models," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 208-213, 1994.
[4] 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.
[5] J. Gårding and T. Lindeberg, "Direct Estimation of Local Surface Shape in a Fixating Binocular Vision System," Proc. Third European Conf. Computer Vision, pp. 365-376, 1994.
[6] J. Gårding and T. Lindeberg, "Direct Computation of Shape Cues Using Scale-Adapted Spatial Derivative Operators," Int'l. J. Computer Vision, vol. 17, pp. 163-191, 1996.
[7] D. Jones and J. Malik, "A Computational Framework for Determining Stereo Correspondence from a Set of Linear Spatial Filters," Proc. Second European Conf. Computer Vision, pp. 395-410, 1992.
[8] D. Jones and J. Malik, "Determining Three-Dimensional Shape from Orientation and Spatial Frequency Disparities," Proc. Second European Conf. Computer Vision, pp. 661-669, 1992.
[9] M. Kass, "Linear Image Features in Stereopsis," Intl. J. Computer Vision, vol. 1, pp. 357-368, 1988.
[10] J.J. Koenderink and A.J. van Doorn, "Local Structure of Movement Parallax of the Plane," J. Optical Soc. of America, vol. 66, no. 7, pp. 717-723, 1976.
[11] J.J. Koenderink and A.J. van Doorn, "Geometry of Binocular Vision and a Model for Stereopsis," Biological Cybernetics, vol. 11, pp. 29-35, 1976.
[12] J.J. Koenderink and A.J. van Doorn, "Affine Structure from Motion," J. Optical Soc. of America A, vol. 8, no. 2, pp. 377-385, 1991.
[13] R. Lane, N. Thacker, and N. Seed, "Stretch Correlation as a Real-Time Alternative to Feature-Based Stereo Matching Algorithms," Image and Vision Computing, vol. 12, pp. 203-212, 1994.
[14] T. Lindeberg and J. Gårding, "Shape-Adapted Smoothing in Estimation of 3D Depth Cues from Affine Distortions of Local 2D Brightness Structure," Proc. Third European Conf. Computer Vision, pp. 389-400, 1994.
[15] R. Manmatha, "A Framework for Recovering Affine Transforms Using Points, Lines, or Image Brightnesses," Proc. Conf. Computer Vision and Pattern Recognition, pp. 141-146, 1994.
[16] J.E.W. Mayhew and H.C. Longuet-Higgins, "A Computational Model of Binocular Depth Perception," Nature, vol. 297, pp. 376-378, 1982.
[17] H. Schweitzer, "A Surface Matching Algorithm for Two Perspective Views," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 742-743, 1993.
[18] B. Super and A. Bovik, "Three-Dimensional Orientation from Texture Using Gabor Wavelets," Proc. SPIE Conf. Visual Commun. and Image Processing, vol. 1,606, pp. 574-586, Nov. 1991.
[19] B. Super, "Filters for Directly Detecting Surface Orientation in an Image," Proc. SPIE Conf. Visual Commun. and Image Processing, vol. 1,818, pp. 144-155, Nov. 1992.
[20] B. Super and W. Klarquist, "Patch Matching and Stereopsis in a General Stereo Viewing Geometry," Technical Report TR-94-006, Univ. of Texas at Austin, Center for Vision and Image Sciences, Nov. 1994; revised Feb. 1995.
[21] B.J. Super and A.C. Bovik, “Shape from Texture Using Local Spectral Moments,” IEEE Trans. Pattern Analysis Machine Intelligence, vol. 17, no. 4, pp. 333-343, Apr. 1995.
[22] B. Super and A. Bovik, "Planar Surface Orientation from Texture Spatial Frequencies," Pattern Recognition J., vol. 28, no. 5, pp. 728-743, 1995.
[23] B. Super and W. Klarquist, "Patch Matching and Stereopsis in a General Stereo Viewing Geometry," Proc. Int'l. Conf. Digital Signal Processing, pp. 500-505, June 1995.
[24] A. Witkin, "Recovering Surface Shape and Orientation from Texture," Artificial Intelligence, vol. 17, pp. 17-45, 1981.

Index Terms:
Stereo, shape, depth, correspondence, patch matching, area correlation, sampling, perspective, surfaces, computer vision.
Citation:
Boaz J. Super, William N. Klarquist, "Patch-Based Stereo in a General Binocular Viewing Geometry," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 3, pp. 247-253, March 1997, doi:10.1109/34.584102
Usage of this product signifies your acceptance of the Terms of Use.