Pacific-Rim Symposium on Image and Video Technology

Image and Video Technology pp 99-110 | Cite as

Rendered Benchmark Data Set for Evaluation of Occlusion-Handling Strategies of a Parts-Based Car Detector

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9431)

Abstract

Despite extensive efforts, state-of-the-art detection approaches show a strong degradation of performance with increasing level of occlusion. A fundamental problem for the development and analysis of occlusion-handling strategies is that occlusion information can not be labeled accurately enough in real world video streams. In this paper we present a rendered car detection benchmark with controlled levels of occlusion and use it to extensively evaluate a visibility-based existing occlusion-handling strategy for a parts-based detection approach. Thereby we determine the limitations and the optimal parameter settings of this framework. Based on these findings we later propose an improved strategy which is especially helpful for strongly occluded views.

Keywords

Object detection Benchmark data set Occlusion-handling 

References

  1. 1.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the CVPR, pp. 886–893 (2005)Google Scholar
  2. 2.
    Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: Proceedings of the CVPR, pp. 304–311 (2009)Google Scholar
  3. 3.
    Felzenszwalb, P.F., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. In: Proceedings of the PAMI, pp. 1627–1645 (2010)Google Scholar
  4. 4.
    Gao, T., Packer, B., Koller, D.: A segmentation-aware object detection model with occlusion handling. In: Proceedings of the CVPR, pp. 1361–1368 (2011)Google Scholar
  5. 5.
    Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the KITTI vision benchmark suite. In: Proceedings of the CVPR, pp. 3354–3361 (2012)Google Scholar
  6. 6.
    Gould, S., Baumstarck, P., Quigley, M., Ng, A.Y., Koller, D.: Integrating visual and range data for robotic object detection. In: ECCV Workshop M2SFA2 (2008)Google Scholar
  7. 7.
    Leibe, B., Schiele, B.: Interleaved object categorization and segmentation. In: Proceedings of the BMVC, pp. 759–768 (2003)Google Scholar
  8. 8.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  9. 9.
    Makris, A., Perrollaz, M., Laugier, C.: Probabilistic integration of intensity and depth information for part-based vehicle detection. IEEE Trans. Intell. Transp. Syst. 14, 1896–1906 (2013)CrossRefGoogle Scholar
  10. 10.
    Pepik, B., Stark, M., Gehler, P., Schiele, B.: Occlusion patterns for object class detection. In: Proceedings of the CVPR, pp. 3286–3293 (2013)Google Scholar
  11. 11.
    Struwe, M., Hasler, S., Bauer-Wersing, U.: Using the analytic feature framework for the detection of occluded objects. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds.) ICANN 2013. LNCS, vol. 8131, pp. 603–610. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  12. 12.
    Stückler, J., Behnke, S.: Hierarchical object discovery and dense modelling from motion cues in RGB-D video. In: Proceedings of the IJCAI, pp. 2502–2509 (2013)Google Scholar
  13. 13.
    Vedaldi, A., Zisserman, A.: Structured output regression for detection with partial truncation. In: Proceedings of the NIPS, pp. 1928–1936 (2009)Google Scholar
  14. 14.
    Winn, J., Shotton, J.D.J.: The layout consistent random field for recognizing and segmenting partially occluded objects. In: Proceedings of the CVPR, pp. 37–44 (2006)Google Scholar
  15. 15.
    Yi-Hsin, L., Tz-Huan, H., Tsai, A., Wen-Kai, L., Jui-Yang, T., Yung-Yu, C.: Pedestrian detection in images by integrating heterogeneous detectors. In: IEEE Computer Symposium (ICS), pp. 252–257 (2010)Google Scholar
  16. 16.
    Zia, M.Z., Stark, M., Schindler, K.: Explicit occlusion modeling for 3D object class representations. In: Proceedings of the CVPR, pp. 3326–3333 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Marvin Struwe
    • 1
  • Stephan Hasler
    • 2
  • Ute Bauer-Wersing
    • 1
  1. 1.Frankfurt University of Applied SciencesFrankfurtGermany
  2. 2.Honda Research Institute Europe GmbHOffenbachGermany

Personalised recommendations