Can We Detect Pedestrians using Low-resolution LIDAR? - Integration of Multi-frame Point-clouds

Yoshiki Tatebe, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Utsushi Sakai

Abstract

In recent years, demand for pedestrian detection using inexpensive low-resolution LIDAR (LIght Detection And Ranging) is increasing, as it can be used to prevent traffic accidents involving pedestrians. However, it is difficult to detect pedestrians from a low-resolution (sparse) point-cloud obtained by a low-resolution LIDAR. In this paper, we propose multi-frame features calculated by integrating point-clouds over multiple frames for increasing the point-cloud resolution, and extracting their temporal changes. By combining these features, the accuracy of the pedestrian detection from low-resolution point-clouds can be improved. We conducted experiments using LIDAR data obtained in actual traffic environments. Experimental results showed that the proposed method could detect pedestrians accurately from low-resolution LIDAR data.

References

  1. World Health Organization. (2015). Global status report on road safety 2015.
  2. Arras, K. O., Mozos, O. M., and Burgard, W. (Apr. 2007). Using boosted features for the detection of people in 2D range data. In Proc. 2007 IEEE Int. Conf. on Robotics and Automation, pages 3402-3407.
  3. Kidono, K., Miyasaka, T., Watanabe, A., Naito, T., and Miura, J. (June 2011). Pedestrian recognition using high-definition LIDAR. In Proc. 2011 IEEE Intelligent Vehicles Symposium, pages 405-410.
  4. Maturana, D. and Scherer, S. (Sept. 2015). Voxnet: A 3D convolutional neural network for real-time object recognition. In Proc. 2015 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, pages 922-928.
  5. Narasimhan, H. and Agarwal, S. (Aug. 2013). SVM pAUC tight: A new support vector method for optimizing partial AUC based on a tight convex upper bound. In Proc. 19th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, pages 167-175.
  6. Navarro-Serment, L. E., Mertz, C., and Hebert, M. (Oct. 2010). Pedestiran detection and tracking using threedimensional LADAR data. Int. J. of Robotics Research, vol.29, no.12, pages 1516-1528.
  7. Ogawa, T., Sakai, H., Suzuki, Y., Takagi, K., and Morikawa, K. (June 2011). Pedestrian detection and tracking using in-vehicle LIDAR for automotive application. In Proc. 2011 IEEE Intelligent Vehicles Symposium, pages 734-739.
  8. Premebida, C., Ludwig, O., and Nunes, U. (Oct. 2009). Exploiting LIDAR-based features on pedestrian detection in urban scenarios. In Proc. 2009 IEEE Int. Conf. on Intelligent Transportation Systems, pages 1-6.
  9. Shroff, D., Nangalia, H., Metawala, A., Parulekar, M., and Padte, V. (Jan. 2013). Dynamic matrix and model predictive control for a semi-auto pilot car. In Proc. 2013 IEEE Int. Conf. on Advances in Technology and Engineering, pages 1-5.
  10. Spinello, L., Luber, M., and Arras, K. O. (May 2011). Tracking people in 3D using a bottom-up top-down detector. In Proc. 2011 IEEE Int. Conf. on Robotics and Automation, pages 1304-1310.
Download


Paper Citation


in Harvard Style

Tatebe Y., Deguchi D., Kawanishi Y., Ide I., Murase H. and Sakai U. (2017). Can We Detect Pedestrians using Low-resolution LIDAR? - Integration of Multi-frame Point-clouds . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-226-4, pages 157-164. DOI: 10.5220/0006100901570164


in Bibtex Style

@conference{visapp17,
author={Yoshiki Tatebe and Daisuke Deguchi and Yasutomo Kawanishi and Ichiro Ide and Hiroshi Murase and Utsushi Sakai},
title={Can We Detect Pedestrians using Low-resolution LIDAR? - Integration of Multi-frame Point-clouds},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={157-164},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006100901570164},
isbn={978-989-758-226-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)
TI - Can We Detect Pedestrians using Low-resolution LIDAR? - Integration of Multi-frame Point-clouds
SN - 978-989-758-226-4
AU - Tatebe Y.
AU - Deguchi D.
AU - Kawanishi Y.
AU - Ide I.
AU - Murase H.
AU - Sakai U.
PY - 2017
SP - 157
EP - 164
DO - 10.5220/0006100901570164