Learning to Rank 3D Features

  • Oncel Tuzel
  • Ming-Yu Liu
  • Yuichi Taguchi
  • Arvind Raghunathan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8689)


Representation of three dimensional objects using a set of oriented point pair features has been shown to be effective for object recognition and pose estimation. Combined with an efficient voting scheme on a generalized Hough space, existing approaches achieve good recognition accuracy and fast operation. However, the performance of these approaches degrades when the objects are (self-)similar or exhibit degeneracies, such as large planar surfaces which are very common in both man made and natural shapes, or due to heavy object and background clutter. We propose a max-margin learning framework to identify discriminative features on the surface of three dimensional objects. Our algorithm selects and ranks features according to their importance for the specified task, which leads to improved accuracy and reduced computational cost. In addition, we analyze various grouping and optimization strategies to learn the discriminative pair features. We present extensive synthetic and real experiments demonstrating the improved results.


3D pose estimation feature selection max-margin learning 

Supplementary material

Electronic Supplementary Material (MOV 20,586 KB)


  1. 1.
    Bariya, P., Nishino, K.: Scale-hierarchical 3D object recognition in cluttered scenes. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 1657–1664 (2010)Google Scholar
  2. 2.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. Pattern Anal. Mach. Intell. 24(4), 509–522 (2002)CrossRefGoogle Scholar
  3. 3.
    Bookstein, F.L.: Principal warps: Thin-plate splines and the decomposition of deformations. IEEE Trans. Pattern Anal. Mach. Intell. 11(6), 567–585 (1989)CrossRefzbMATHGoogle Scholar
  4. 4.
    Borgefors, G.: Hierarchical chamfer matching: A parametric edge matching algorithm. IEEE Trans. Pattern Anal. Mach. Intell. 10(6), 849–865 (1988)CrossRefGoogle Scholar
  5. 5.
    Cao, Z., Qin, T., Liu, T.Y., Tsai, M.F., Li, H.: Learning to rank: From pairwise approach to listwise approach. In: Proc. Int’l Conf. Mach. Learning (ICML), pp. 129–136 (2007)Google Scholar
  6. 6.
    Choi, C., Taguchi, Y., Tuzel, O., Liu, M.Y., Ramalingam, S.: Voting-based pose estimation for robotic assembly using a 3D sensor. In: Proc. IEEE Int’l Conf. Robotics Automation (ICRA), pp. 1724–1731 (May 2012)Google Scholar
  7. 7.
    Drost, B., Ulrich, M., Navab, N., Ilic, S.: Model globally, match locally: Efficient and robust 3D object recognition. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 998–1005 (June 2010)Google Scholar
  8. 8.
    Frome, A., Huber, D., Kolluri, R., Bülow, T., Malik, J.: Recognizing objects in range data using regional point descriptors. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3023, pp. 224–237. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  9. 9.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference, Manchester, UK, vol. 15, p. 50 (1988)Google Scholar
  10. 10.
    Hinterstoisser, S., Holzer, S., Cagniart, C., Ilic, S., Konolige, K., Navab, N., Lepetit, V.: Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes. In: Proc. IEEE Int’l Conf. Computer Vision (ICCV), pp. 858–865 (November 2011)Google Scholar
  11. 11.
    Holzer, S., Shotton, J., Kohli, P.: Learning to efficiently detect repeatable interest points in depth data. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 200–213. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  12. 12.
    Horn, B.K.P.: Extended gaussian images. Proceedings of the IEEE 72(12), 1671–1686 (1984)CrossRefGoogle Scholar
  13. 13.
    Jain, V., Varma, M.: Learning to re-rank: query-dependent image re-ranking using click data. In: Proc. Int’l Conf. World Wide Web, pp. 277–286 (2011)Google Scholar
  14. 14.
    Joachims, T.: Optimizing search engines using clickthrough data. In: Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge discovery and Data Mining, pp. 133–142 (2002)Google Scholar
  15. 15.
    Johnson, A.E., Hebert, M.: Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 433–449 (1999)CrossRefGoogle Scholar
  16. 16.
    Kelley Jr., J.E.: The cutting-plane method for solving convex programs. Journal of the Society for Industrial & Applied Mathematics 8(4), 703–712 (1960)CrossRefMathSciNetGoogle Scholar
  17. 17.
    Knopp, J., Prasad, M., Willems, G., Timofte, R., Van Gool, L.: Hough transform and 3D SURF for robust three dimensional classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol. 6316, pp. 589–602. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  18. 18.
    Lamdan, Y., Wolfson, H.J.: Geometric hashing: A general and efficient model-based recognition scheme. In: Proc. IEEE Int’l Conf. Computer Vision (ICCV), vol. 88, pp. 238–249 (1988)Google Scholar
  19. 19.
    Liu, M.Y., Tuzel, O., Veeraraghavan, A., Chellappa, R.: Fast directional chamfer matching. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 1696–1703 (June 2010)Google Scholar
  20. 20.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int’l J. Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  21. 21.
    Maji, S., Malik, J.: Object detection using a max-margin hough transform. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 1038–1045 (2009)Google Scholar
  22. 22.
    Mian, A.S., Bennamoun, M., Owens, R.: Three-dimensional model-based object recognition and segmentation in cluttered scenes. IEEE Trans. Pattern Anal. Mach. Intell. 28, 1584–1601 (2006)CrossRefGoogle Scholar
  23. 23.
    Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: Proc. IEEE Int’l Conf. Computer Vision (ICCV), vol. 1, pp. 525–531 (2001)Google Scholar
  24. 24.
    Nguyen, H., Porikli, F.: Support vector shape: A classifier based shape representation. IEEE Trans. Pattern Anal. Mach. Intell. 35(4), 970–982 (2013)CrossRefGoogle Scholar
  25. 25.
    Parikh, D., Grauman, K.: Relative attributes. In: Proc. IEEE Int’l Conf. Computer Vision (ICCV), pp. 503–510 (2011)Google Scholar
  26. 26.
    Rodolà, E., Albarelli, A., Bergamasco, F., Torsello, A.: A scale independent selection process for 3D object recognition in cluttered scenes. Int’l J. Computer Vision 102(1-3), 129–145 (2013)CrossRefGoogle Scholar
  27. 27.
    Rusu, R.B., Blodow, N., Beetz, M.: Fast point feature histograms (FPFH) for 3D registration. In: Proc. IEEE Int’l Conf. Robotics Automation (ICRA), pp. 3212–3217 (May 2009)Google Scholar
  28. 28.
    Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from single depth images. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 1297–1304 (June 2011)Google Scholar
  29. 29.
    Stein, F., Medioni, G.: Structural indexing: Efficient 3-D object recognition. IEEE Trans. Pattern Anal. Mach. Intell. 14(2), 125–145 (1992)CrossRefGoogle Scholar
  30. 30.
    Taskar, B., Guestrin, C., Koller, D.: Max-margin markov networks. In: Proc. Neural Information Processing Systems (NIPS), vol. 16 (2003)Google Scholar
  31. 31.
    Tsochantaridis, I., Hofmann, T., Joachims, T., Altun, Y.: Support vector machine learning for interdependent and structured output spaces. In: Proc. Int’l Conf. Mach. Learning (ICML), p. 104 (2004)Google Scholar
  32. 32.
    Tutuncu, R., Toh, K., Todd, M.: Solving semidefinite-quadratic-linear programs using sdpt3. Mathematical Programming Ser. B 95, 198–217 (2003)CrossRefMathSciNetGoogle Scholar
  33. 33.
    Wahl, E., Hillenbrand, U., Hirzinger, G.: Surflet-pair-relation histograms: A statistical 3D-shape representation for rapid classification. In: Proc. Int’l Conf. 3-D Digital Imaging and Modeling (3DIM), pp. 474–481 (October 2003)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Oncel Tuzel
    • 1
  • Ming-Yu Liu
    • 1
  • Yuichi Taguchi
    • 1
  • Arvind Raghunathan
    • 1
  1. 1.Mitsubishi Electric Research Labs (MERL)CambridgeUSA

Personalised recommendations