Advertisement

Individualness and Determinantal Point Processes for Pedestrian Detection

  • Donghoon Lee
  • Geonho Cha
  • Ming-Hsuan Yang
  • Songhwai OhEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9910)

Abstract

In this paper, we introduce individualness of detection candidates as a complement to objectness for pedestrian detection. The individualness assigns a single detection for each object out of raw detection candidates given by either object proposals or sliding windows. We show that conventional approaches, such as non-maximum suppression, are sub-optimal since they suppress nearby detections using only detection scores. We use a determinantal point process combined with the individualness to optimally select final detections. It models each detection using its quality and similarity to other detections based on the individualness. Then, detections with high detection scores and low correlations are selected by measuring their probability using a determinant of a matrix, which is composed of quality terms on the diagonal entries and similarities on the off-diagonal entries. For concreteness, we focus on the pedestrian detection problem as it is one of the most challenging problems due to frequent occlusions and unpredictable human motions. Experimental results demonstrate that the proposed algorithm works favorably against existing methods, including non-maximal suppression and a quadratic unconstrained binary optimization based method.

Keywords

Determinantal point process Individualness Object detection Pedestrian detection 

Notes

Acknowledgements

The work of D. Lee, G. Cha, and S. Oh is supported in part by a grant to Bio-Mimetic Robot Research Center funded by Defense Acquisition Program Administration and Agency for Defense Development (UD130070ID) and Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (NRF-2015R1A2A1A15052493). The work of M.-H. Yang is supported in part by the NSF CAREER grant #1149783, and gifts from Adobe and Nvidia.

Supplementary material

419981_1_En_20_MOESM1_ESM.pdf (371 kb)
Supplementary material 1 (pdf 370 KB)

References

  1. 1.
    Andriluka, M., Roth, S., Schiele, B.: People-tracking-by-detection and people-detection-by-tracking. In: Proceeding of the IEEE Computer Vision and Pattern Recognition (2008)Google Scholar
  2. 2.
    Li, L.J., Socher, R., Fei-Fei, L.: Towards total scene understanding: classification, annotation and segmentation in an automatic framework. In: Proceeding of the IEEE Computer Vision and Pattern Recognition (2009)Google Scholar
  3. 3.
    Yao, B., Jiang, X., Khosla, A., Lin, A.L., Guibas, L., Fei-Fei, L.: Human action recognition by learning bases of action attributes and parts. In: Proceeding of the IEEE International Conference on Computer Vision (2011)Google Scholar
  4. 4.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceeding of the IEEE Computer Vision and Pattern Recognition (2001)Google Scholar
  5. 5.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceeding of the IEEE Computer Vision and Pattern Recognition (2005)Google Scholar
  6. 6.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627–1645 (2010)CrossRefGoogle Scholar
  7. 7.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceeding of the IEEE Computer Vision and Pattern Recognition (2014)Google Scholar
  8. 8.
    Kulesza, A., Taskar, B.: Determinantal point processes for machine learning. arXiv preprint arXiv:1207.6083 (2012)
  9. 9.
    Ferryman, J., Shahrokni, A.: PETS2009: dataset and challenge. In: Winter-PETS (2009)Google Scholar
  10. 10.
    Fleuret, F., Berclaz, J., Lengagne, R., Fua, P.: Multicamera people tracking with a probabilistic occupancy map. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 267–282 (2008)CrossRefGoogle Scholar
  11. 11.
    Dollár, P., Appel, R., Belongie, S., Perona, P.: Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1532–1545 (2014)CrossRefGoogle Scholar
  12. 12.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)Google Scholar
  13. 13.
    Liu, S., Lu, C., Jia, J.: Box aggregation for proposal decimation: last mile of object detection. In: Proceeding of the IEEE International Conference on Computer Vision, pp. 2569–2577 (2015)Google Scholar
  14. 14.
    Wan, L., Eigen, D., Fergus, R.: End-to-end integration of a convolution network, deformable parts model and non-maximum suppression. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 851–859 (2015)Google Scholar
  15. 15.
    Rujikietgumjorn, S., Collins, R.T.: Optimized pedestrian detection for multiple and occluded people. In: Proceeding of the IEEE Computer Vision and Pattern Recognition (2013)Google Scholar
  16. 16.
    Rothe, R., Guillaumin, M., Gool, L.V.: Non-maximum suppression for object detection by passing messages between windows. In: Proceeding of the IEEE Asian Conference on Computer Vision (2014)Google Scholar
  17. 17.
    Çivril, A., Magdon-Ismail, M.: On selecting a maximum volume sub-matrix of a matrix and related problems. Theoret. Comput. Sci. 410(47), 4801–4811 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Meinshausen, N., Bickel, P., Rice, J.: Efficient blind search: optimal power of detection under computational cost constraints. Ann. Appl. Stat. 38–60 (2009)Google Scholar
  19. 19.
    Kulesza, A., Taskar, B.: Structured determinantal point processes. In: Advances in neural information processing systems, pp. 1171–1179 (2010)Google Scholar
  20. 20.
    Schur, J.: Bemerkungen zur theorie der beschränkten bilinearformen mit unendlich vielen veränderlichen. J. l für die reine und Angewandte Mathematik 140, 1–28 (1911)MathSciNetzbMATHGoogle Scholar
  21. 21.
    Gillenwater, J., Kulesza, A., Taskar, B.: Near-optimal MAP inference for determinantal point processes. In: Advances in Neural Information Processing Systems (2012)Google Scholar
  22. 22.
    Everingham, M., Gool, L.V., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2012 (VOC2012) results (2012)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Donghoon Lee
    • 1
  • Geonho Cha
    • 1
  • Ming-Hsuan Yang
    • 2
  • Songhwai Oh
    • 1
    Email author
  1. 1.Electrical and Computer Engineering and ASRISeoul National UniversitySeoulKorea
  2. 2.Electrical Engineering and Computer ScienceUniversity of CaliforniaMercedUSA

Personalised recommendations