Recognizing Multiple Objects via Regression Incorporating the Co-occurrence of Categories

  • Takahiro Okabe
  • Yuhi Kondo
  • Kris M. Kitani
  • Yoichi Sato
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5414)

Abstract

Most previous methods for generic object recognition explicitly or implicitly assume that an image contains objects from a single category, although objects from multiple categories often appear together in an image. In this paper, we present a novel method for object recognition that explicitly deals with objects of multiple categories coexisting in an image. Furthermore, our proposed method aims to recognize objects by taking advantage of a scene’s context represented by the co-occurrence relationship between object categories. Specifically, our method estimates the mixture ratios of multiple categories in an image via MAP regression, where the likelihood is computed based on the linear combination model of frequency distributions of local features, and the prior probability is computed from the co-occurrence relation. We conducted a number of experiments using the PASCAL dataset, and obtained the results that lend support to the effectiveness of the proposed method.

Keywords

Feature Point Visual Word Area Under Curve Object Category Multiple Category 
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.
    Biederman, I., Mezzanotte, R., Rabinowitz, J.: Scene perception: detecting and judging objects undergoing relational violations. Cognitive Psychology 14(2), 143–177 (1982)CrossRefGoogle Scholar
  2. 2.
    Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Proc. ECCV 2004 Workshop on Statistical Learning in Computer Vision, pp. 1–22 (2004)Google Scholar
  3. 3.
    Everingham, M., Zisserman, A., Williams, C., Van Gool, L.: The 2006 PASCAL Visual Object Classes Challenge (VOC 2006) Results, http://www.pascal-network.org/challenges/VOC/voc2006/results.pdf
  4. 4.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. IEEE CS Conf. Computer Vision and Pattern Recognition (CVPR 2003), pp. II-264–II-271 (2003)Google Scholar
  5. 5.
    Frome, A., Singer, Y., Sha, F., Malik, J.: Learning globally-consistent local distance functions for shape-based image retrieval and classification. In: Proc. IEEE Int’l Conf. Computer Vision (ICCV 2007), pp. 1–8 (2007)Google Scholar
  6. 6.
    Galleguillos, C., Rabinovich, A., Belongie, S.: Object categorization using co-occurrence, location and appearance. In: Proc. IEEE CS Conf. Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–8 (2008)Google Scholar
  7. 7.
    Hoiem, D., Efros, A., Hebert, M.: Putting objects in perspective. In: Proc. IEEE CS Conf. Computer Vision and Pattern Recognition (CVPR 2006), pp. 2137–2144 (2006)Google Scholar
  8. 8.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Int’l Journal of Compute Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  9. 9.
    Qi, G.-J., Hua, X.-S., Rui, Y., Mei, T., Tang, J., Zhang, H.-J.: Concurrent multiple instance learning for image categorization. In: Proc. IEEE CS Conf. Computer Vision and Pattern Recognition (CVPR 2007), pp. 1–8 (2007)Google Scholar
  10. 10.
    Rabinovich, A., Vedaldi, A., Galleguillos, C., Wiewiora, E., Belongie, S.: Objects in context. In: Proc. IEEE Int’l Conf. Computer Vision (ICCV 2007), pp. 1–8 (2007)Google Scholar
  11. 11.
    Savarese, S., Fei-Fei, L.: 3D generic object categorization, localization and pose estimation. In: Proc. IEEE Int’l Conf. Computer Vision (ICCV 2007), pp. 1–8 (2007)Google Scholar
  12. 12.
    Sivic, J., Russell, B., Efros, A., Zisserman, A., Freeman, W.: Discovering objects and their location in images. In: Proc. IEEE Int’l Conf. Computer Vision (ICCV 2005), pp. 370–377 (2005)Google Scholar
  13. 13.
    Yang, L., Jin, R., Sukthankar, R., Jurie, F.: Unifying discriminative visual codebook generation with classifier training for object category recognition. In: Proc. IEEE CS Conf. Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–8 (2008)Google Scholar
  14. 14.
    Zhang, J., Marszalek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: a comprehensive study. Int’l Journal of Computer Vision 73(2), 213–238 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Takahiro Okabe
    • 1
  • Yuhi Kondo
    • 1
    • 2
  • Kris M. Kitani
    • 1
    • 3
  • Yoichi Sato
    • 1
  1. 1.Institute of Industrial ScienceThe University of TokyoJapan
  2. 2.Sony CorporationJapan
  3. 3.Graduate School of Information SystemsThe University of Electro-CommunicationsJapan

Personalised recommendations