MULTI-CAMERA PEDESTRIAN DETECTION BY MEANS OF TRACK-TO-TRACK FUSION AND CAR2CAR COMMUNICATION

Anselm Haselhoff, Lars Hoehmann, Anton Kummert, Christian Nunn, Mirko Meuter, Stefan Müller-Schneiders

2011

Abstract

In this paper a system for fusion of pedestrian detections from multiple vehicles is presented. The application area is narrowed down to driver assistance systems, where single cameras are mounted in the moving vehicles. The main contribution of this paper is a comparison of three fusion algorithms based on real image data. The methods under review include Covariance Fusion, Covariance Intersection, and Covariance Union. An experimental setup is presented, with known ground truth positions of the detected objects. This information can be incorporated for the evaluation of the fusion methods. The system setup consists of two vehicles equipped with LANCOM® wireless access points, cameras, inertial measurement units (IMU) and IMU enhanced GPS receivers. Each vehicle detects pedestrians by means of the camera and an AdaBoost detection algorithm. The results are tracked and transmitted to the other vehicle in appropriate coordinates. Afterwards each vehicle is responsible for reasonable treatment or fusion of the detection data.

References

  1. Bar-Shalom, Y. and Blair, W. D. (2000). MultitargetMultisensor Tracking: Applications and Advances. Artech House Inc, Norwood, USA.
  2. Hartley, R. and Zisserman, A. (2003). Multi View Geometry in Computer Vision (2nd Edition). Cambridge University Press, Cambridge, United Kingdom.
  3. Kaempchen, N. (2007). Feature-level fusion of laser scanner and video data for advanced driver assistance systems. Technical report, Fakultaet fuer Ingenieurwissenschaften und Informatik, Universitaet Ulm.
  4. Matzka, S. and Altendorfer, R. (2008). A comparison of track-to-track fusion algorithms for automotive sensor fusion. In Proc. of International Conference on Multisensor and Integration for Intelligent Systems , 2008 IEEE, pages 189-194.
  5. Merwe, R. V. D. and Wan, E. (2003). Sigma-point kalman filters for probabilistic inference in dynamic statespace models. In In Proceedings of the Workshop on Advances in Machine Learning.
  6. Meuter, M., Iurgel, U., Park, S.-B., and Kummert, A. (2008). The unscented kalman filter for pedestrian tracking from a moving host. In Proc. of Intelligent Vehicles Symposium, 2008 IEEE, pages 37-42.
  7. Nunn, C., Kummert, A., Muller, D., Meuter, M., and Muller-Schneiders, S. (2009). An improved adaboost learning scheme using lda features for object recognition. In Proc. of Intelligent Transportation Systems, 2009. ITSC 7809. 12th International IEEE Conference on, pages 1-6.
  8. Ponsa, D. and Lopez, A. (2007). Vehicle trajectory estimation based on monocular vision. In Marti, J., Benedi, J., Mendonca, A., and Serrat, J., editors, Pattern Recognition and Image Analysis, volume 4477 of Lecture Notes in Computer Science, pages 587-594. Springer Berlin / Heidelberg.
  9. Ponsa, D., Lopez, A., Lumbreras, F., Serrat, J., and Graf, T. (2005). 3d vehicle sensor based on monocular vision. In Proceedings of the 8th International IEEE Conference on Intelligent Transportation Systems, Vienna, Austria.
  10. Smith, D. and Singh, S. (2006). Approaches to multisensor data fusion in target tracking: A survey. Knowledge and Data Engineering, IEEE Transactions on, 18(12):1696 -1710.
  11. Smith, R. C. and Cheeseman, P. (1986). On the representation and estimation of spatial uncertainly. Int. J. Rob. Res., 5(4):56-68.
Download


Paper Citation


in Harvard Style

Haselhoff A., Hoehmann L., Kummert A., Nunn C., Meuter M. and Müller-Schneiders S. (2011). MULTI-CAMERA PEDESTRIAN DETECTION BY MEANS OF TRACK-TO-TRACK FUSION AND CAR2CAR COMMUNICATION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011) ISBN 978-989-8425-47-8, pages 307-312. DOI: 10.5220/0003315603070312


in Bibtex Style

@conference{visapp11,
author={Anselm Haselhoff and Lars Hoehmann and Anton Kummert and Christian Nunn and Mirko Meuter and Stefan Müller-Schneiders},
title={MULTI-CAMERA PEDESTRIAN DETECTION BY MEANS OF TRACK-TO-TRACK FUSION AND CAR2CAR COMMUNICATION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)},
year={2011},
pages={307-312},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003315603070312},
isbn={978-989-8425-47-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2011)
TI - MULTI-CAMERA PEDESTRIAN DETECTION BY MEANS OF TRACK-TO-TRACK FUSION AND CAR2CAR COMMUNICATION
SN - 978-989-8425-47-8
AU - Haselhoff A.
AU - Hoehmann L.
AU - Kummert A.
AU - Nunn C.
AU - Meuter M.
AU - Müller-Schneiders S.
PY - 2011
SP - 307
EP - 312
DO - 10.5220/0003315603070312