Real-time Pedestrian Detection in a Truck’s Blind Spot Camera

Kristof Van Beeck, Toon Goedemé

Abstract

In this paper we present a multi-pedestrian detection and tracking framework targeting a specific application: detecting vulnerable road users in a truck’s blind spot zone. Research indicates that existing non-vision based safety solutions are not able to handle this problem completely. Therefore we aim to develop an active safety system which warns the truck driver if pedestrians are present in the truck’s blind spot zone. Our system solely uses the vision input from the truck’s blind spot camera to detect pedestrians. This is not a trivial task, since the application inherently requires real-time operation while at the same time attaining very high accuracy. Furthermore we need to cope with the large lens distortion and the extreme viewpoints introduced by the blind spot camera. To achieve this, we propose a fast and efficient pedestrian detection and tracking framework based on our novel perspective warping window approach. To evaluate our algorithm we recorded several realistically simulated blind spot scenarios with a genuine blind spot camera mounted on a real truck. We show that our algorithm achieves excellent accuracy results at real-time performance, using a single core CPU implementation only.

References

  1. Benenson, R., Markus, M., Tuytelaars, T., and Van Gool, L. (2013). Seeking the strongest rigid detector. In Proceedings of CVPR, pages 3666-3673, Portland, Oregon.
  2. Benenson, R., Mathias, M., Timofte, R., and Van Gool, L. (2012a). Fast stixels computation for fast pedestrian detection. In ECCV, CVVT workshop, pages 11-20.
  3. Benenson, R., Mathias, M., Timofte, R., and Van Gool, L. (2012b). Pedestrian detection at 100 frames per second. In Proceedings of CVPR, pages 2903-2910.
  4. Cho, H., Rybski, P., Bar-Hillel, A., and Zhang, W. (2012). Real-time pedestrian detection with deformable part models. In IEEE Intelligent Vehicles Symposium, pages 1035-1042.
  5. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In Proceedings of CVPR, volume 2, pages 886-893.
  6. Dollár, P., Belongie, S., and Perona, P. (2010). The fastest pedestrian detector in the west. In Proceedings of BMVC, pages 68.1-68.11.
  7. Dollár, P., Tu, Z., Perona, P., and Belongie, S. (2009a). Integral channel features. In Proceedings of BMVC, pages 91.1-91.11.
  8. Dollár, P., Wojek, C., Schiele, B., and Perona, P. (2009b). Pedestrian detection: A benchmark. In Proceedings of CVPR, pages 304-311.
  9. Dollár, P., Wojek, C., Schiele, B., and Perona, P. (2012). Pedestrian detection: An evaluation of the state of the art. In IEEE PAMI, 34:743-761.
  10. Enzweiler, M. and Gavrila, D. M. (2009). Monocular pedestrian detection: Survey and experiments. In IEEE PAMI, volume 31, pages 2179-2195.
  11. Ess, A., Leibe, B., Schindler, K., and Van Gool, L. (2008). A mobile vision system for robust multi-person tracking. In Proceedings of CVPR, pages 1-8.
  12. EU (22 february 2006). Commision of the european communities, european road safety action programme: mid-term review.
  13. Felzenszwalb, P., Girschick, R., and McAllester, D. (2010). Cascade object detection with deformable part models. In Proceedings of CVPR, pages 2241-2248.
  14. Felzenszwalb, P., McAllester, D., and Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In Proceedings of CVPR.
  15. Gavrila, D. and Munder, S. (2007). Multi-cue pedestrian detection and tracking from a moving vehicle. In IJCV, volume 73, pages 41-59.
  16. Huang, C., Ai, H., Li, Y., and Lao, S. (2005). Vector boosting for rotation invariant multi-view face detection. In ICCV, pages 446-453.
  17. Lampert, C., Blaschko, M., and Hoffmann, T. (2009). Efficient subwindow search: A branch and bound framework for object localization. In IEEE PAMI, volume 31, pages 2129-2142.
  18. Martensen, H. (2009). Themarapport vrachtwagenongevallen 2000 - 2007 (BIVV).
  19. Mathias, M., Timofte, R., Benenson, R., and Van Gool, L. (2013). Traffic sign recognition - how far are we from the solution? In ICJNN.
  20. Pedersoli, M., Gonzalez, J., Hu, X., and Roca, X. (2013). Toward real-time pedestrian detection based on a deformable template model. In IEEE ITS.
  21. Prisacariu, V. and Reid, I. (2009). fastHOG - a real-time gpu implementation of HOG. Technical report, Department of Engineering Science, Oxford University.
  22. Seitner, F. and Hanbury, A. (2006). Fast pedestrian tracking based on spatial features and colour. In Proceedings of CVWW, pages 105-110.
  23. Van Beeck, K., Goedemé, T., and Tuytelaars, T. (2011). Towards an automatic blind spot camera: Robust realtime pedestrian tracking from a moving camera. In Proceedings of MVA, Nara, Japan.
  24. Van Beeck, K., Tuytelaars, T., and Goedemé, T. (2012). A warping window approach to real-time vision-based pedestrian detection in a truck's blind spot zone. In Proceedings of ICINCO.
  25. Viola, P., Jones, M., and Snow, D. (2005). Detecting pedestrians using patterns of motion and appearance. In IJCV, volume 63, pages 153-161.
Download


Paper Citation


in Harvard Style

Van Beeck K. and Goedemé T. (2014). Real-time Pedestrian Detection in a Truck’s Blind Spot Camera . In Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-018-5, pages 412-420. DOI: 10.5220/0004821304120420


in Bibtex Style

@conference{icpram14,
author={Kristof Van Beeck and Toon Goedemé},
title={Real-time Pedestrian Detection in a Truck’s Blind Spot Camera},
booktitle={Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2014},
pages={412-420},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004821304120420},
isbn={978-989-758-018-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Real-time Pedestrian Detection in a Truck’s Blind Spot Camera
SN - 978-989-758-018-5
AU - Van Beeck K.
AU - Goedemé T.
PY - 2014
SP - 412
EP - 420
DO - 10.5220/0004821304120420