Matching feature points in stereo pairs: a comparative study of some matching strategies

• Autorzy: Vincent E. , Laganiere R.
• Języki publikacji: EN

Abstrakty

EN

Several algorithms are proposed in the literature to solve the difficult problem of feature point correspondence between image pairs. In order to obtain good quality results, they make use of different aproaches and constraints to improve the quality of the matching set. A matching strategy is considered useful if it is able to filter out many of the mismatches found in an input matching set while keeping in most of the good matches present. In this paper, we present a survey of different matching strategies. We propose an empirical evaluation of thier performance. The validation process used here determines the number of good matches and the proportion of good matches in a given match set for the different parameter values of a matching constraint.

Słowa kluczowe

EN

feature point correspondence; stereo matching; interest point detection; corners

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2001
• Tom: Vol. 10, No. 3
• Strony: 237--259
• Opis fizyczny: Bibliogr. 34 poz.

Twórcy

autor

Vincent E.

• School of Information Technology and Engineering, University of Ottawa, Ottawa, ONT K1N 6N5

autor

Laganiere R.

• School of Information Technology and Engineering, University of Ottawa, Ottawa, ONT K1N 6N5

Bibliografia

• [1] Delp E., Mitchell O.: Image compression using block truncation coding. IEEE Trans. on Communication, 27(9), 1335-1342, 1979.
• [2] Fischler M., Bolles R.: random sample concensus: a paradigm for model fitting with application to image analysis and automated cartography. Comm. ACM, 24, 381-395, 1981.
• [3] Nishihara H., Poggio T.: Stereo vision for robotics. ISRR, 1983.
• [4] Anandan P.: Computing dense displacement fields with confidence measures in scenes containing occlusion. Intel. Robots and Comp. Vision, 521, 1984.
• [5] Harris C.: Determination of ego-motion from matched points. Proc. Alvey Vision Conf, 1987.
• [6] Guelch E.: Result of test on image matching of ISPR wg iii. Int. Archives of Photogrammetry and Remote Sensing, 27 (III), 254-271, 1988.
• [7] Harris C., Stephens M.: A combined corner and edge detector. Alvey Vision Conf., 147-151, 1988.
• [8] Noble J.: Finding corners. Image and Vision Computing, 6, 121-128, 1988.
• [9] Fua P.: Combining Stereo and Monocular Information to Compute Dense Depth Maps that Preserve Depth Discontinuities. ijcai , 1991.
• [10] Faugeras O.D., Fua P., Hotz B., Ma R., Robert L., Thonnat M., Zhang Z.: Quantitative and qualitative comparison of some area and feature-based stereo algorithms. Workshop on Robust Computer Vision, 1-26, 1992.
• [11] Hsieh Y., McKeown D., Perlant F.: Performance evaluation of scene registration and stereo matching for cartographic feature extraction. PAMI, 14, 214-237, 1992.
• [12] Koschan A.: A framework for area based and feature based stereo vision. MGV, 2(4), 1993.
• [13] Zhang Z.: Le problème de la mise en correspondence: L’etat de l’art. TR, INRIA, 1993.
• [14] Deriche R., Zhang Z., Luong Q.-T., Faugeras O.: Robust recovery of the epipolar gepmetry for an uncalibrated stereo rig. Proc. ECCV, 567-576, 1994.
• [15] Hu X., Ahuja N.: Matching point features with ordered geometric, rigidity, and disparity constraints. PAMI, 16(10), 1041-1049, 1994.
• [16] Zhang Z., Deriche R., Faugeras O., Luong Q.-T.: A Robust Technique for Matching Two Uncali-brated Images Through the Recovery of the Unknown Epipolar Geomerty. TR, INRIA, 1994.
• [17] Horaud R., Monga O.: Vision par ordinateur outils fondamentaux, Hermes, 1995.
• [18] Smith S.M., Brady J.M.: SUSAN A New Approach to Low Level Image Processing. TR, Oxford University, 1995.
• [19] Klette R., Schluns K., Koschan A.: Computer Vision: three-dimensional data from images. Sprigner , 1996.
• [20] Jones G.: Constraint, optimization, and hierarchy: reviewing stereoscopic correspondence of complex features, CVIU, 65(1), 57-58, 1997.
• [21] Schmid C., Mohr R.: Local Grayvalue invariants for image retrieval. PAMI, 530-535, 1997.
• [22] Bhat D., Nayar S.: Ordinal Measures for Image Correspondence. PAMI, 20(4) , 1998.
• [23] Darell T.: A radial cumulative similarity transform for robust image correspondence. CVPR, 656-662, 1998.
• [24] Laganière R.: A morphological operator for corner detection PR, 1643-1652, 1998.
• [25] Schmid C., Mohr R., Bauckhage C.: Comparing and evaluating interest points, Proc. ICCV, 230-235, 1998.
• [26] Torr P., Zisserman A.: Robust computation and parameterization of multiple view relations. Proc. ICCV, 727-732, 1998.
• [27] Arbouche S.: Feature Point Correspondences: A Matching Constraints Survey. M.C.S. Thesis, University of Ottawa, 1999.
• [28] Lowe D.: Object recognition from local scale-invariant features. Proc. ICCV, 1999.
• [29] Tuytelaars T., Van Gool L., D’haene L., Koch R.: Marching of affinely invariant regions for visual servoing, ICRA, 1601-1606, 1999.
• [30] Baumberg A.: Reliable feature matching across widely seperated views. CVPR, 2000.
• [31] Hartley R., Zisserman A.: Multiple View Geometry in Computer Vision. Cambridge University Press, 2000.
• [32] Roth G., Whitehead A.: Using projective vision to find camera positions in an image sequence. Proc. of Vision Interface, 225-232, 2000.
• [33] Jung L.-K., Lacroix S.: A robust interest points matching algorithm. Proc. ICCV, 538-543, 2001.
• [34] Scharstein D., Szeliski R., Zabih R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. CVPR, Workshop on Stereo and Multi-Baseline Vision, 2001.