
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
X. Hu, N. Ahuja, "Matching Point Features with Ordered Geometric, Rigidity, and Disparity Constraints," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 10, pp. 10411049, October, 1994.  
BibTex  x  
@article{ 10.1109/34.329004, author = {X. Hu and N. Ahuja}, title = {Matching Point Features with Ordered Geometric, Rigidity, and Disparity Constraints}, journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {16}, number = {10}, issn = {01628828}, year = {1994}, pages = {10411049}, doi = {http://doi.ieeecomputersociety.org/10.1109/34.329004}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Pattern Analysis and Machine Intelligence TI  Matching Point Features with Ordered Geometric, Rigidity, and Disparity Constraints IS  10 SN  01628828 SP1041 EP1049 EPD  10411049 A1  X. Hu, A1  N. Ahuja, PY  1994 KW  computational complexity; feature extraction; image sequences; geometry; point features; disparity constraints; geometric constraints; rigidity constraints; matching algorithm; feature detectors; intensitybased matching algorithm; heuristic tests; twodimensional geometrical relationships; rigidity test; disparity test; epipolar line; computational complexity; indoor images VL  16 JA  IEEE Transactions on Pattern Analysis and Machine Intelligence ER   
This correspondence presents a matching algorithm for obtaining feature point correspondences across images containing rigid objects undergoing different motions. First point features are detected using newly developed feature detectors. Then a variety of constraints are applied starting with simplest and following with more informed ones. First, an intensitybased matching algorithm is applied to the feature points to obtain unique point correspondences. This is followed by the application of a sequence of newly developed heuristic tests involving geometry, rigidity, and disparity. The geometric tests match twodimensional geometrical relationships among the feature points, the rigidity test enforces the three dimensional rigidity of the object, and the disparity test ensures that no matched feature point in an image could be rematched with another feature, if reassigned another disparity value associated with another matched pair or an assumed match on the epipolar line. The computational complexity is proportional to the numbers of detected feature points in the two images. Experimental results with indoor and outdoor images are presented, which show that the algorithm yields only correct matches for scenes containing rigid objects.
[1] O. A. Zuniga and R. M. Haralick, "Corner detection using the facet model," inProc. Comput. Vision Pattern Recognition 7, 1983, pp. 303.
[2] L. Kitchen and A. Rosenfeld, "Graylevel corner detection,"Pattern Recognit. Lett., vol. 1, pp. 95102, 1982.
[3] H. P. Moravec, "Towards automatic visual obstacle," inProc. Int. Joint Conf. on Artificial Intell., 1977, p. 584.
[4] H. P. Moravec, "Visual mapping by a robot rover," inProc. Int. Joint Conf. Artificial Intell., 1979, pp. 598600.
[5] A. Singh and M. Shneier, "Grey level corner detection: a generalization and a robust real time implementation,"Comput. Vision. Graphics. Image Processing, vol. 51, pp. 5469, 1990.
[6] I.K. Sethi and R. Jain, "Finding trajectories of feature points in a monocular image sequence,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI9, pp. 5673, Jan. 1987.
[7] P. R. Beaudet, "Rotationally invariant image operators," inProc. Int. Joint Conf. Pattern Recognit., 1978, pp. 573583.
[8] R. Deriche and G. Giraudon, "Accurate corner detection: An analytical study," inProc. Int. Joint Conf. Comput. Vision, 1990, pp. 6670.
[9] A. Rattarangsi and R. T. Chin, "Scalebased detection of corners of planar curves," inProc. Int. Joint Conf. Pattern Recognit., 1990, pp. 923930.
[10] C.L. Cheng and J. K. Aggarwal, "A twostage hybrid approach to the correspondence problem via forwardsearching and backwardcorrecting," inProc. Int. Joint Conf. Pattern Recognit., 1990, pp. 173179.
[11] Y. Lamdan, J. T. Schwartz, and H. J. Wolfson, "Object recognition by affine invariant matching," inProc. CVPR 88, 1988.
[12] M. S. Costa and R. M. Haralick, and L. Shapiro, "Optimal affineinvariant point matching," inProc. Int. Joint Conf. Pattern Recognit., 1990, pp. 233236.
[13] J. R. Beveridge and R. Weiss, and E. M. Riseman, "Combinatorial optimization applied to variable scale 2D model matching," inProc. Int. Joint Conf. Pattern Recognit., 1990, pp. 1822.
[14] X.J. Wang, J. Fu, and L. Wu, "A matching algorithm based on hierarchical primitive structure," inProc. Int. Joint Conf. Pattern Recognit., 1990, pp. 285287.
[15] W. K. Gu, J. Y. Yang, and T. S. Huang, "Matching perspective views of a polyhedron using circuits,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI9, no. 3, pp. 390400, 1987.
[16] J. F. Canny, "A computational approach to edge detection,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI8, pp. 679697, 1986.
[17] B. K. P. Horn and B. G. Schunk, "Determining optical flow,"Artifial Intell., vol. 17, pp. 185203, 1981.
[18] J. Weng, "A theory of image matching," inProc. Int. Joint Conf. Comput. Vision, 1990, pp. 200209.
[19] J. Weng, N. Ahuja, and T. S. Huang, "Twoview matching," inProc. Int. Joint Conf. Comput. Vision, 1988, pp. 6473.
[20] W. E. L. Grimson and T. LozanoPerez, "Modelbased recognition and localization from sparse range or tactile data,"Int. J. Robotics Res., vol. 3, no. 3, pp. 335, 1984.
[21] W. E. L. Grimson and T. LozanoPerez, "Localizing overlapping parts by searching the interpretation tree,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI9, no. 4, July 1987.
[22] W. E. L. Grimson, "Recognition of object families using parameterized models," inFirst Int. Conf. Comput. Vision, 1987, pp. 93101.
[23] W.E.L. Grimson, "The combinatorics of object recognition in cluttered environments using constrained search," inProc. 1988 Int. Conf. Computer Vision (ICCV '88), 1988, pp. 218227.
[24] W. E. L. Grimson, "The effect of indexing on the complexity of object recognition," inProc. Third Int. Conf. Comput. Vision(Osaka, Japan), 1990, pp. 644651.
[25] D. Huttenlocher and S. Ullman, "Object recognition using alignment," inFirst Int. Conf. Comput. Vision, 1987, pp. 102111.
[26] P. Flynn and A. Jain, "Bonsai: 3D object recognition using constrained search," inThird Int. Conf. Comput. Vision, 1990, pp. 263267.
[27] R. G. Gonzalez and P. Wintz,Digital Image Processing. New York: AddisonWesley, 1977.
[28] D. Marr,Vision. New York: W. H. Freeman, 1982.
[29] D. Marr and T. Poggio, "A computational theory of human stereo vision," inProc. Roy. Soc. Lon., vol. B, no. 204, pp. 301328, 1979.
[30] W. Hoff and N. Ahuja, "Surfaces from stereo: integrating feature matching, disparity estimation and contour detection,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, pp. 121136, Feb. 1989.
[31] W. Hoff and N. Ahuja, "Surfaces from stereo images: an integrated approach," inFirstInt. Conf. Comput. Vision, 1987, pp. 284294.
[32] L. Cohen, L. Vinet, P. Sander, and A. Gagalowicz, "Hierarchical region based stereo matching," inProc. Comput. Vision Pattern Recognit., 1989, pp. 416421.
[33] Y. C. Hsieh, F. Perlant, and D. M. McKeown, "Recovering 3D information from complex aerial imagery, " inProc. 10th ICPR(Atlantic City), 1990, pp. 136146.
[34] X. Hu and N. Ahuja, "Estimation of motion of constant acceleration from image sequences," inProc. Int. Joint Conf. Pattern Recognit., Hague, The Netherlands, vol. 1, 1992, pp. 655659.
[35] X. Hu, "Perception of shape and motion," Ph.D. dissertation, Dep. Elec. and Comput. Eng., Univ. of Illinois at UrbanaChampaign, 1993.
[36] X. Hu and N. Ahuja, "Feature extraction and matching as signal detection," inProc. SPIE Conf. Applicat. Artificial Intell. XI: Machine Vision and Robotics, Orlando, FL, 1993.
[37] X. Hu and N. Ahuja, "Feature extraction and matching as signal detection," to appear inInt. J. Pattern Recognit. Artificial Intell., vol. 8, no. 6, 1994.
[38] K. Prazdny, "Egomotion and relative depth map from optical flow,"Biolog. Cybern., vol. 36, pp. 87102, 1980.
[39] G. Adiv, "Determining threedimensional motion and structure from optical flow generated by several moving objects,"Pattern Anal. Machine Intell., vol. PAMI7, no. 4, pp. 384401, 1985.
[40] V. Salari and I. K. Sethi, "Feature point correspondence in the presence of occlusion,"Pattern Anal. Machine Intell., vol. 12, no. 1, pp. 8791, 1990.
[41] J. J. Rodriguez and J. K. Aggarwal, "Matching aerial images to 3 D terrain maps,"Pattern Anal. Machine Intell., vol. 12, no. 12, pp. 11381149, 1990.
[42] W. Y. Kim and A. C. Kak, "3D object recognition using bipartite matching embedded in discrete relaxation,"Pattern Anal. Machine Intell., vol. 13, no. 3, pp. 224251, 1991.