Abstract
We present a new feature based algorithm for stereo correspondence. Most of the previous feature based methods match sparse features like edge pixels, producing only sparse disparity maps. Our algorithm detects and matches dense features between the left and right images of a stereo pair, producing a semi-dense disparity map. Our dense feature is defined with respect to both images of a stereo pair, and it is computed during the stereo matching process, not a preprocessing step. In essence, a dense feature is a connected set of pixels in the left image and a corresponding set of pixels in the right image such that the intensity edges on the boundary of these sets are stronger than their matching error (which is the difference in intensities between corresponding boundary pixels). Our algorithm produces accurate semi-dense disparity maps, leaving featureless regions in the scene unmatched. It is robust, requires little parameter tuning, can handle brightnessdifferences between images, nonlinear errors, and is fast (linear complexity).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Barnard, S.T. 1989. Stochastic stereo matching over scale. IJCV, 3(1):17–32.
Birchfield, S. and Tomasi, C. 1998. Apixel dissimilarity measure that is insensitive to image sampling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(4):401–406.
Boykov, Y., Veksler, O., and Zabih, R. 1998. A variable window approach to early vision. PAMI, 20(12):1283–1295.
Boykov, Y., Veksler, O., and Zabih, R. 1999. Fast approximate energy minimization via graph cuts. In International Conference on Computer Vision, pp. 377–384.
Cohen, L.D., Vinet, L., Sander, P.T., and Gagalowicz, A. 1989. Hierarchical region based stereo matching. In CVPR89, pp. 416–421.
Fusiello, A. and Roberto, V. 1997. Efficient stereo with multiple windowing. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 858–863.
Geiger, D., Ladendorf, B., and Yuille, A. 1995. Occlusions and binocular stereo. International Journal of Computer Vision, 14:211–226.
Gennery, D.B. 1980. Modelling the environment of an exploring vehicle by means of stereo vision. Ph.D, Stanford.
Grimson, W.E.L. 1981. A computer implementation of a theory of human stereo vision. Royal, B-292:217–253.
Ishikawa, H. and Geiger, D. 1998. Occlusions, discontinuities, and epipolar lines in stereo. In ECCV98, pp. I:232–248.
Jermyn, I. and Ishikawa, H. 1999. Globally optimal regions and boundaries. In ICCV99, pp. 904–910.
Kanade, T. and Okutomi, M. 1994. Astereo matching algorithm with an adaptive window: Theory and experiment. PAMI, 16(9):920–932.
Ma, J. and Ahuja, N. 2000. Region correspondence by global configuration matching and progressive delaunay triangulation. In CVPR00, pp. II:637–642.
Maas, R., ter Haar Romeny, B.M., and Viergever, M.A. 1999. Area-based computation of stereo disparity with model-based window size selection. In CVPR99, pp. I:106–112.
Marr, D. and Poggio, T.A. 1976. Cooperative computation of stereo disparity. Science, 194(4262):283–287.
Marr, D. and Poggio, T.A. 1979. A computational theory of human stereo vision. RoyalP, B-204:301–328.
Medioni, G.G. and Nevatia, R. 1985. Segment-based stereo matching. CVGIP, 31(1):2–18.
Mori, K., Kidode, M., and Asada, H. 1973. Aniterative prediction and correction method for automatic stereocomparison. CGIP, 2:393–401.
Ayache, N. and Faverjon, B. 1987. Efficient registration of stereo images by matching graph descriptions of edge segments. International Journal of Computer Vision, 1.
Okutomi, M. 2001. A simple stereo algorithm to recover precise object boundaries and smooth surfaces. In CVPR01, II:138–144.
Panton, D.J. 1978. A flexible approach to digital stereo mapping. PhEngRS, 44(12):1499–1512.
Robert, L. and Faugeras, O. 1991. Curve-based stereo: Figural continuity and curvature. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 57–62.
Roy, S. 1999. Stereo without epipolar lines: A maximum-flow formulation. IJCV, 34(2/3):1–15.
Scharstein, D., Szeliski, R., and Zabih, R. 2001. A taxonomy and evaluation of dense two-frame stereo methods. In SMBV01, pp. 131–140.
Szeliski, R. and Zabih, R. 1999. An experimental comparison of stereo algorithms. In IEEE Workshop on Vision Algorithms, Sept. 1999.
Tao, H. and Sawhney, H.S. 2000. Global matching criterion and color segmentation based stereo. In WACV00, pp. 246–253.
Tao, H., Sawhney, H.S., and Kumar., R. 2001. A global matching framework for stereo computation. In ICCV01, pp. I:532–539.
Veksler, O. 2001. Stereo matching by compact windows via minimum ratio cycle. In ICCV01. pp. I:540–547.
Wang, S. and Siskind, J. M. 2001. Image segmentation with minimum mean cut. In ICCV01. pp. I:517–524.
Zitnick, C.L. and Kanade, T. 2000. A cooperative algorithm for stereo matching and occlusion detection. PAMI, 22(7):675–684.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Veksler, O. Dense Features for Semi-Dense Stereo Correspondence. International Journal of Computer Vision 47, 247–260 (2002). https://doi.org/10.1023/A:1014506211316
Issue Date:
DOI: https://doi.org/10.1023/A:1014506211316