Advertisement

Latent-Class Hough Forests for 3D Object Detection and Pose Estimation

  • Alykhan Tejani
  • Danhang Tang
  • Rigas Kouskouridas
  • Tae-Kyun Kim
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8694)

Abstract

In this paper we propose a novel framework, Latent-Class Hough Forests, for 3D object detection and pose estimation in heavily cluttered and occluded scenes. Firstly, we adapt the state-of-the-art template matching feature, LINEMOD [14], into a scale-invariant patch descriptor and integrate it into a regression forest using a novel template-based split function. In training, rather than explicitly collecting representative negative samples, our method is trained on positive samples only and we treat the class distributions at the leaf nodes as latent variables. During the inference process we iteratively update these distributions, providing accurate estimation of background clutter and foreground occlusions and thus a better detection rate. Furthermore, as a by-product, the latent class distributions can provide accurate occlusion aware segmentation masks, even in the multi-instance scenario. In addition to an existing public dataset, which contains only single-instance sequences with large amounts of clutter, we have collected a new, more challenging, dataset for multiple-instance detection containing heavy 2D and 3D clutter as well as foreground occlusions. We evaluate the Latent-Class Hough Forest on both of these datasets where we outperform state-of-the art methods.

Keywords

Leaf Node Split Function Background Clutter Segmentation Mask Template Feature 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT. ACM (1998)Google Scholar
  2. 2.
    Breiman, L.: Random forests. Machine Learning (2001)Google Scholar
  3. 3.
    Chan, J., Koprinska, I., Poon, J.: Co-training with a single natural feature set applied to email classification. In: WIC (2004)Google Scholar
  4. 4.
    Choi, C., Christensen, H.I.: 3D pose estimation of daily objects using an rgb-d camera. In: IROS (2012)Google Scholar
  5. 5.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)Google Scholar
  6. 6.
    Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: A benchmark. In: CVPR (2009)Google Scholar
  7. 7.
    Drost, B., Ulrich, M., Navab, N., Ilic, S.: Model globally, match locally: Efficient and robust 3D object recognition. In: CVPR (2010)Google Scholar
  8. 8.
    Fanelli, G., Gall, J., Van Gool, L.: Real time head pose estimation with random regression forests. In: CVPR (2011)Google Scholar
  9. 9.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. PAMI (2010)Google Scholar
  10. 10.
    Gall, J., Yao, A., Razavi, N., Van Gool, L., Lempitsky, V.: Hough forests for object detection, tracking, and action recognition. PAMI (2011)Google Scholar
  11. 11.
    Girshick, R., Shotton, J., Kohli, P., Criminisi, A., Fitzgibbon, A.: Efficient regression of general-activity human poses from depth images. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 415–422. IEEE (2011)Google Scholar
  12. 12.
    Goldman, S., Zhou, Y.: Enhancing supervised learning with unlabeled data. In: ICML (2000)Google Scholar
  13. 13.
    Hinterstoisser, S., Benhimane, S., Lepetit, V., Navab, N.: Simultaneous recognition and homography extraction of local patches with a simple linear classifier (2008)Google Scholar
  14. 14.
    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: ICCV (2011)Google Scholar
  15. 15.
    Hinterstoisser, S., Lepetit, V., Ilic, S., Fua, P., Navab, N.: Dominant orientation templates for real-time detection of texture-less objects. In: CVPR (2010)Google Scholar
  16. 16.
    Hinterstoisser, S., Lepetit, V., Ilic, S., Holzer, S., Bradski, G., Konolige, K., Navab, N.: Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part I. LNCS, vol. 7724, pp. 548–562. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  17. 17.
    Hsiao, E., Hebert, M.: Occlusion reasoning for object detection under arbitrary viewpoint. In: CVPR (2012)Google Scholar
  18. 18.
    Johnson, A.E., Hebert, M.: Using spin images for efficient object recognition in cluttered 3D scenes. PAMI (1999)Google Scholar
  19. 19.
    Khan, S.S., Madden, M.G.: One-class classification: Taxonomy of study and review of techniques. arXiv preprint arXiv:1312.0049 (2013)Google Scholar
  20. 20.
    Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: ECCV (2004)Google Scholar
  21. 21.
    Leibe, B., Leonardis, A., Schiele, B.: Robust object detection with interleaved categorization and segmentation. IJCV (2008)Google Scholar
  22. 22.
    Liu, R., Cheng, J., Lu, H.: A robust boosting tracker with minimum error bound in a co-training framework. In: ICCV (2009)Google Scholar
  23. 23.
    Moya, M., Koch, M., Hostetler, L.: One-class classifier networks for target recognition applications. Tech. rep. (1993)Google Scholar
  24. 24.
    Newcombe, R.A., Davison, A.J., Izadi, S., Kohli, P., Hilliges, O., Shotton, J., Molyneaux, D., Hodges, S., Kim, D., Fitzgibbon, A.: Kinectfusion: Real-time dense surface mapping and tracking. In: 2011 10th IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 127–136. IEEE (2011)Google Scholar
  25. 25.
    Okada, R.: Discriminative generalized hough transform for object dectection. In: ICCV (2009)Google Scholar
  26. 26.
    Opelt, A., Pinz, A., Zisserman, A.: Learning an alphabet of shape and appearance for multi-class object detection. IJCV (2008)Google Scholar
  27. 27.
    Perronnin, F., Sánchez, J., Liu, Y.: Large-scale image categorization with explicit data embedding. In: CVPR (2010)Google Scholar
  28. 28.
    Rios-Cabrera, R., Tuytelaars, T.: Discriminatively trained templates for 3D object detection: A real time scalable approach. In: ICCV (2013)Google Scholar
  29. 29.
    Shotton, J., Sharp, T., Kipman, A., Fitzgibbon, A., Finocchio, M., Blake, A., Cook, M., Moore, R.: Real-time human pose recognition in parts from single depth images. ACM (2013)Google Scholar
  30. 30.
  31. 31.
    Steger, C.: Similarity measures for occlusion, clutter, and illumination invariant object recognition. In: Radig, B., Florczyk, S. (eds.) DAGM 2001. LNCS, vol. 2191, pp. 148–154. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  32. 32.
    Tang, D., Liu, Y., Kim, T.K.: Fast pedestrian detection by cascaded random forest with dominant orientation templates. In: BMVC (2012)Google Scholar
  33. 33.
    Tang, D., Yu, T.H., Kim, T.K.: Real-time articulated hand pose estimation using semi-supervised transductive regression forests. In: ICCV (2013)Google Scholar
  34. 34.
    Tax, D.M.: One-class classification (2001)Google Scholar
  35. 35.
    Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR (2011)Google Scholar
  36. 36.
    Weise, T., Wismer, T., Leibe, B., Van Gool, L.: In-hand scanning with online loop closure. In: 2009 IEEE 12th International Conference on Computer Vision Workshops (ICCV Workshops), pp. 1630–1637. IEEE (2009)Google Scholar
  37. 37.
    Yu, S., Krishnapuram, B., Rosales, R., Steck, H., Rao, R.B.: Bayesian co-training. In: NIPS (2007)Google Scholar
  38. 38.
    Zhang, Z.: Iterative point matching for registration of free-form curves and surfaces. International Journal of Computer Vision 13(2), 119–152 (1994)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Alykhan Tejani
    • 1
  • Danhang Tang
    • 1
  • Rigas Kouskouridas
    • 1
  • Tae-Kyun Kim
    • 1
  1. 1.Imperial Collge LondonUK

Personalised recommendations