Advertisement

Categorisation of 3D Objects in Range Images Using Compositional Hierarchies of Parts Based on MDL and Entropy Selection Criteria

  • Vladislav Kramarev
  • Krzysztof Walas
  • Aleš Leonardis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9127)

Abstract

This paper presents a new approach to object categorisation in range images using our novel hierarchical compositional representation of surfaces. The atomic elements at the bottom layer of the hierarchy encode quantized relative depth of pixels in a local neighbourhood. Subsequent layers are formed in the recursive manner, each higher layer is statistically learnt on the layer below via a growing receptive field. In this paper we mainly focus on the part selection problem, i.e. the choice of the optimisation criteria which provide the information on which parts should be promoted to the higher layer of the hierarchy. Namely, two methods based on Minimum Description Length and category based entropy are introduced.

The proposed approach was extensively tested on two widely-used datasets for object categorisation with results that are of the same quality as the best results achieved for those datasets.

Keywords

Range images Object categorisation Compositional hierarchies Shape parts 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aanæs, H., Dahl, A., Pedersen, K.S.: Interesting Interest Points. Int. J. of Computer Vision 97(1), 18–35 (2012)CrossRefGoogle Scholar
  2. 2.
    Akgul, C., Sankur, B., Yemez, Y., Schmitt, F.: 3D Model Retrieval Using Probability Density-Based Shape Descriptors. IEEE Trans. on Pattern Analysis and Machine Intell. 31(6), 1117–1133 (2009)CrossRefGoogle Scholar
  3. 3.
    Besl, P.J.: Surfaces in Range Image Understanding. Springer Series in Perception Engineering. Springer (1988)Google Scholar
  4. 4.
    Bo, L., Ren, X., Fox, D.: Unsupervised feature learning for RGB-D based object recognition. In: Desai, J.P., Dudek, G., Khatib, O., Kumar, V. (eds.) Experimental Robotics. STAR, vol. 88, pp. 387–402. Springer, Heidelberg (2013) CrossRefGoogle Scholar
  5. 5.
    Faugeras, O.: Three-Dimensional Computer Vision. A geometric view point. MIT Press (1993)Google Scholar
  6. 6.
    Fidler, S., Leonardis, A.: Towards scalable representations of object categories: learning a hierarchy of parts. In: IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1–8 (2007)Google Scholar
  7. 7.
    Giorgi, D., Biasotti, S., Paraboschi, L.: SHape REtrieval Contest 2007: Watertight Models TrackGoogle Scholar
  8. 8.
    Guo, G., Wang, Y., Jiang, T., Yuille, A., Fang, F., Gao, W.: A Shape Reconstructability Measure of Object Part Importance with Applications to Object Detection and Localization. Int. J. of Computer Vision 108(3), 241–258 (2014)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Guo, Y., Bennamoun, M., Sohel, F., Lu, M., Wan, J.: 3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey. IEEE Trans. on Pattern Analysis and Machine Intell. 36(11), 2270–2287 (2014)CrossRefGoogle Scholar
  10. 10.
    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
  11. 11.
    Kramarev, V., Zurek, S., Wyatt, J.L., Leonardis, A.: Object categorization from range images using a hierarchical compositional representation. In: 2014 22nd Int. Conf. on Pattern Recognition (ICPR) (2014)Google Scholar
  12. 12.
    Lai, K., Bo, L., Fox, D.: Unsupervised feature learning for 3D scene labeling. In: 2014 IEEE Int. Conf. on Robotics and Automation (ICRA), pp. 3050–3057 (2014)Google Scholar
  13. 13.
    Lai, K., Bo, L., Ren, X., Fox, D.: A large-scale hierarchical multi-view RGB-D object dataset. In: 2011 IEEE Int. Conf. on Robotics and Automation (ICRA), pp. 1817–1824 (2011)Google Scholar
  14. 14.
    Leonardis, A., Bischof, H., Maver, J.: Multiple eigenspaces. Pattern Recognition 35(11), 2613–2627 (2002)zbMATHCrossRefGoogle Scholar
  15. 15.
    Li, B., Wu, T., Zhu, S.-C.: Integrating context and occlusion for car detection by hierarchical and-or model. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VI. LNCS, vol. 8694, pp. 652–667. Springer, Heidelberg (2014) CrossRefGoogle Scholar
  16. 16.
    Ommer, B., Sauter, M., Buhmann, J.M.: Learning top-down grouping of compositional hierarchies for recognition. In: Proceedings of the 2006 Conf. on Computer Vision and Pattern Recognition Workshop, CVPRW 2006, pp. 194–211. IEEE Computer Society, Washington (2006)Google Scholar
  17. 17.
    Pele, O., Werman, M.: The quadratic-chi histogram distance family. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 749–762. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  18. 18.
    Socher, R., Huval, B., Bhat, B., Manning, C.D., Ng, A.Y.: Convolutional-Recursive Deep Learning for 3D Object Classification. In: Advances in Neural Information Processing Systems, vol. 25 (2012)Google Scholar
  19. 19.
    Salti, S., Tombari, F., Stefano, L.D.: On the use of implicit shape models for recognition of object categories in 3D data. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part III. LNCS, vol. 6494, pp. 653–666. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  20. 20.
    Tabia, H., Laga, H., Picard, D., Gosselin, P.H.: Covariance descriptors for 3D shape matching and retrieval. In: 2014 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 4185–4192 (2014)Google Scholar
  21. 21.
    Toldo, R., Castellani, U., Fusiello, A.: A bag of words approach for 3d object categorization. In: Computer Vision/Computer Graphics Collaboration Techniques, pp. 116–127. Springer (2009)Google Scholar
  22. 22.
    Tombari, F., Salti, S., Stefano, L.D.: Performance Evaluation of 3D Keypoint Detectors. Int. J. of Computer Vision 102(1–3), 198–220 (2013)CrossRefGoogle Scholar
  23. 23.
    Tuzel, O., Liu, M.-Y., Taguchi, Y., Raghunathan, A.: Learning to rank 3D features. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 520–535. Springer, Heidelberg (2014) CrossRefGoogle Scholar
  24. 24.
    Woodford, O., Pham, M.T., Maki, A., Perbet, F., Stenger, B.: Demisting the Hough Transform for 3D Shape Recognition and Registration. Int. J. of Computer Vision 106(3), 332–341 (2014)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Zamolotskikh, A., Cunningham, P.: An assessment of alternative strategies for constructing EMD-based kernel functions for use in an SVM for image classification. In: Int. Workshop on Content-Based Multimedia Indexing, CBMI 2007, pp. 11–17 (2007)Google Scholar
  26. 26.
    Zhang, J., Marszalek, M., Lazebnik, S., Schmid, C.: Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study. Int. J. of Computer Vision 73(2), 213–238 (2007)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Vladislav Kramarev
    • 1
  • Krzysztof Walas
    • 1
  • Aleš Leonardis
    • 1
  1. 1.Intelligent Robotics Laboratory, School of Computer ScienceUniversity of BirminghamEdgbaston, BirminghamUnited Kingdom

Personalised recommendations