This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Sensor Modeling, Probabilistic Hypothesis Generation, and Robust Localization for Object Recognition
March 1995 (vol. 17 no. 3)
pp. 252-265

Abstract—In an effort to make object recognition efficient and accurate enough for real applications, we have developed three probabilistic techniques—sensor modeling, probabilistic hypothesis generation, and robust localization—which form the basis of a promising paradigm for object recognition. Our techniques effectively exploit prior knowledge to reduce the number of hypotheses that must be tested during recognition. Our recognition approach utilizes statistical constraints on the matches between image and model features. These statistical constraints are computed using a model of the entire sensing process—resulting in more realistic and tighter constraints on matches. The candidate hypotheses are pruned by probabilistic constraint satisfaction to select likely matches based on the image evidence and prior statistical constraints. The resulting hypotheses are ordered most-likely first for verification, thus minimizing unnecessary verifications. The reliability of the verification decision is significantly increased by the use of a robust localization algorithm. Our localization algorithm reliably locates objects despite partial occlusion and significant errors in initial location estimates. We have implemented these techniques in a system that recognizes polyhedral objects in range images. Our results demonstrate accurate recognition while greatly limiting the number of verifications.

[1] M. D. Wheeler and K. Ikeuchi,“Sensor modeling, probabilistic hypothesis generation, and robustlocalization for object recognition,” Second CAD-Based Vision Workshop, pp. 46-53, 1994.
[2] M. Kass,A. Witkin,, and D. Terzopoulos,“Snakes: Active contour models,” Int’l. J. Computer. Vision, vol. 2, no.1, pp. 322-331, 1987.
[3] W.E.L. Grimson and T. Lozano-Perez, “Localizing Overlapping Parts by Searching the Interpretation Tree,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 4, pp. 469-482, Apr. 1987.
[4] R.C. Bolles and P. Haraud, "3DPO: A Three Dimensional Part Orientation System," Int'l J. Robotics Research, vol. 5, no. 3, pp. 3-26, 1986.
[5] O.D. Faugeras and M. Hebert,“The representation, recognition, and locating of 3D objects,” Int’l J. of Robotics Research, vol. 5, no. 3, pp. 27-52, Fall 1986.
[6] D.G. Lowe, Perceptual Organization and Visual Recognition. Boston: Kluwer Academic, 1985.
[7] P. Flynn and A. Jain, "BONSAI: 3D object recognition using constrained search," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, pp. 1066-1075, 1991.
[8] D.P. Huttenlocher and S. Ullman, “Recognizing Solid Objects by Alignment with an Image,” Int'l J. Computer Vision, vol. 5, no. 2, pp. 195-212, 1990.
[9] K. Ikeuchi,“Generating an interpretation tree from a CAD model for 3-d objectrecognition in bin-picking tasks,” Int’l. J. Computer. Vision, vol. 1, no. 2, pp. 145-165, 1987.
[10] O.I. Camps,R.M. Haralick,, and L.G. Shapiro,, and R.M. Haralick,“PREMIO: An overview,” in IEEE Workshop on Directions in Automated CAD-Based Vision, pp. 11-21, 1991.
[11] B. Bhanu,“Representation and shape matching of 3-Dd objects,” IEEE Trans. Patt. Anal. Machine Intell., vol. 6, no. 3, pp. 340-351, 1984.
[12] R.M. Bolle,A. Califano,, and R. Kjeldsen,“A complete and extendable approach to visual recognition,” IEEE Trans. Patt. Anal. Machine Intell., vol. 14, no. 5, 1992.
[13] P. Cooper,Parallel Object Recognition from Structure (The Tinkertoy Project). PhD thesis, Department. of Computer Science, Univ. of Rochester, 1989.
[14] W.M. Wells,Statistical Object Recognition, PhD thesis, Massachusetts Inst. of Tech nology, 1992.
[15] J. Ben-Arie, "The Probabilistic Peaking Effect of Viewed Angles and Distances With Application to 3D Object Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 8, pp. 760-774, August 1990.
[16] K. Ikeuchi and T. Kanade, “Automatic Generation of Object Recognition Programs,” Proc. IEEE, vol. 76, pp. 1,016–1,035, 1988.
[17] D.G. Lowe, "Fitting Parameterized Three-Dimensional Models to Images," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 5, pp. 441-450, May 1991.
[18] D. Kriegman and J. Ponce,“On recognizing and positioning curved 3Dd objects from image contours,” in DARPA IUS Workshop, pp. 461-470, 1989.
[19] R.M. Bolle and D.B. Cooper,“On optimally combining pieces of information, with application to estimating 3D complex-object position from range data,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 5, pp. 619-638, Sept. 1986.
[20] R.M. Haralick, H. Joo, C.-N. Lee, X. Zhuang, and M.B. Kim, “Pose Estimation from Corresponding Point Data,” IEEE Trans. Systems, Man, and Cybernetics, vol. 19, no. 6, p. 1426, 1989.
[21] P.J. Besl and N.D. McKay, "A Method for Registration of 3D Shapes," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 239-256, Feb. 1992.
[22] K. Ikeuchi and J.-C. Robert,“Modeling sensor detectability with {VANTAGE} geometric/sensor modeler,” IEEE Trans. Robotics Automat., vol. 7, no. 6, pp. 771-784, 1991.
[23] Y. Fujiwara,S. Nayar,, and K. Ikeuchi,“Appearance simulator for computer vision research,” Tech. Report CMU-RI-TR-91-16, Carnegie Mellon University, 1991.
[24] J.B. Burns and E. Riseman, "Matching complex images to multiple 3D objects using view description networks," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 328-334, 1992.
[25] P.B. Chou and C.M. Brown, “The Theory and Practice of Bayesian Image Labeling,” Int'l J. Computer Vision, vol. 4, no. 3, pp. 185-210, 1990.
[26] W.E.L. Grimson,D.P. Huttenlocher,, and D.W. Jacobs,“Affine matching with bounded sensor error: A study of geometrichashing and alignment,” Tech. Rep.ort 1250, Massachusetts Inst. of Tech nology, 1991.
[27] W.H. Press, S.A. Teukolsky, W.T. Vetterling, and B.P. Flannery, Numerical Recipes in C. Cambridge Univ. Press, 1992.
[28] J.H. Friedman, J.L. Bentley, and R.A. Finkel, "An Algorithm for Finding Best Matches in Logarithmic Expected Time," ACM Trans. on Math. Software, vol. 3, no. 3, pp. 209-226, Sept. 1977.
[29] T.M. Breuel, "Fast Recognition Using Adaptive Subdivisions of Transformation Space," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 445-451, June 1992.

Index Terms:
Computer vision, 3D object recognition, probabilistic recognition, Markov random fields, robust pose estimation.
Citation:
Mark D. Wheeler, Katsushi Ikeuchi, "Sensor Modeling, Probabilistic Hypothesis Generation, and Robust Localization for Object Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 3, pp. 252-265, March 1995, doi:10.1109/34.368190
Usage of this product signifies your acceptance of the Terms of Use.