Advertisement

Improved Object Detection and Pose Using Part-Based Models

  • Fangyuan Jiang
  • Olof Enqvist
  • Fredrik Kahl
  • Kalle Åström
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7944)

Abstract

Automated object detection is perhaps the most central task of computer vision and arguably the most difficult one. This paper extends previous work on part-based models by using accurate geometric models both in the learning phase and at detection. In the learning phase manual annotations are used to reduce perspective distortion before learning the part-based models. That training is performed on rectified images, leads to models which are more specific, reducing the risk of false positives. At the same time a set of representative object poses are learnt. These are used at detection to remove perspective distortion. The method is evaluated on the bus category of the Pascal dataset with promising results.

Keywords

Training Image Object Detection Aspect Model Planar Aspect Visible Aspect 
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.

References

  1. 1.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Conf. Computer Vision and Pattern Recognition (2001)Google Scholar
  2. 2.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Conf. Computer Vision and Pattern Recognition (2005)Google Scholar
  3. 3.
    Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Analysis and Machine Intelligence (2010)Google Scholar
  4. 4.
    Lampert, C., Blaschko, M., Hofmann, T.: Efficient subwindow search: A branch and bound framework for object localization. IEEE Trans. Pattern Analysis and Machine Intelligence (2009)Google Scholar
  5. 5.
    Vedaldi, A., Gulshan, V., Varma, M., Zisserman, A.: Multiple kernels for object detection. In: Int. Conf. Computer Vision (2009)Google Scholar
  6. 6.
    Fischler, M., Elschlager, R.: The representation and matching of pictorial structures. Transactons on Computers (1973)Google Scholar
  7. 7.
    Zhu, L., Chen, Y., Yuille, A.L., Freeman, W.T.: Latent hierarchical structural learning for object detection. In: Conf. Computer Vision and Pattern Recognition (2010)Google Scholar
  8. 8.
    Vedaldi, A., Zisserman, A.: Structured output regression for detection with partial occulsion. In: Advances in Neural Information Processing Systems (2009)Google Scholar
  9. 9.
    Torralba, A., Murphy, K., Freeman, W.: Sharing visual features for multiclass and multiview object detection. IEEE Trans. Pattern Analysis and Machine Intelligence (2007)Google Scholar
  10. 10.
    Ott, P., Everingham, M.: Shared parts for deformable part-based models. In: Conf. Computer Vision and Pattern Recognition (2011)Google Scholar
  11. 11.
    Bourdev, L., Malik, J.: Poselets: Body part detectors trained using 3d human pose annotations. In: Int. Conf. Computer Vision (2010)Google Scholar
  12. 12.
    Xiang, Y., Savarese, S.: Estimating the aspect layout of object categories. In: Conf. Computer Vision and Pattern Recognition (2012)Google Scholar
  13. 13.
    Thomas, A., Ferrari, V., Leibe, B., Tuytelaars, T., Schiele, B., Gool, L.V.: Towards multi-view object class detection. In: Conf. Computer Vision and Pattern Recognition (2006)Google Scholar
  14. 14.
    Savarese, S., Fei-Fei, L.: 3d generic object categorization, localization and pose estimation. In: Int. Conf. Computer Vision (2007)Google Scholar
  15. 15.
    Liebelt, J., Schmid, C.: Multi-view object class detection with a 3d geometric model. In: Conf. Computer Vision and Pattern Recognition (2010)Google Scholar
  16. 16.
    Yang, Y., Ramanan, D.: Articulated pose estimation using flexible mixtures of parts. In: Conf. Computer Vision and Pattern Recognition (2011)Google Scholar
  17. 17.
    Branson, S., Perona, P., Belongie, S.: Strong supervision from weak annotation: Interactive training of deformable part models. In: Int. Conf. Computer Vision (2011)Google Scholar
  18. 18.
    Chiu, H., Kaelbling, L., Lozano-Pérez, T.: Virtual training for multi-view object class recognition. In: Conf. Computer Vision and Pattern Recognition (2007)Google Scholar
  19. 19.
    Triggs, B.: Camera pose and calibration from 4 or 5 known 3d points. In: ICCV 8, pp. 278–284 (1999)Google Scholar
  20. 20.
    Josephson, K., Byröd, M.: Pose estimation with radial distortion and unknown focal length. In: Conf. Computer Vision and Pattern Recognition (2009)Google Scholar
  21. 21.
    Felzenszwalb, P., Girshick, R., McAllester, D.: Cascade object detection with deformable part models. In: Conf. Computer Vision and Pattern Recognition (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Fangyuan Jiang
    • 1
  • Olof Enqvist
    • 1
  • Fredrik Kahl
    • 1
  • Kalle Åström
    • 1
  1. 1.Centre for Mathematical SciencesLund UniversitySweden

Personalised recommendations