PRINCIPLED DETECTION-BY-CLASSIFICATION FROM MULTIPLE VIEWS

Jérôme Berclaz, François Fleuret, Pascal Fua

2008

Abstract

Machine-learning based classification techniques have been shown to be effective at detecting objects in complex scenes. However, the final results are often obtained from the alarms produced by the classifiers through a post-processing which typically relies on ad hoc heuristics. Spatially close alarms are assumed to be triggered by the same target and grouped together. Here we replace those heuristics by a principled Bayesian approach, which uses knowledge about both the classifier response model and the scene geometry to combine multiple classification answers. We demonstrate its effectiveness for multi-view pedestrian detection. We estimate the marginal probabilities of presence of people at any location in a scene, given the responses of classifiers evaluated in each view. Our approach naturally takes into account both the occlusions and the very low metric accuracy of the classifiers due to their invariance to translation and scale. Results show our method produces one order of magnitude fewer false positives than a method that is representative of typical state-of-the-art approaches. Moreover, the framework we propose is generic and could be applied to any detection-by-classification task.

References

  1. Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2):123-140.
  2. Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J. (1984). Classification and Regression Trees. Chapman & Hall, New York.
  3. Dalal, N. and Triggs, B. (2005). Histograms of Oriented Gradients for Human Detection. In CVPR.
  4. Elfes, A. (1989). Occupancy Grids: A Probabilistic Framework for Robot Perception and Navigation. PhD thesis, Carnegie Mellon University.
  5. Fleuret, F. and Geman, D. (2002). Fast Face Detection with Precise Pose Estimation. In CVPR.
  6. Khan, S. and Shah, M. (2006). A multiview approach to tracking people in crowded scenes using a planar homography constraint. In ECCV.
  7. Leibe, B., Seemann, E., and Schiele, B. (2005). Pedestrian detection in crowded scenes. In CVPR.
  8. Mittal, A. and Davis, L. (2003). M2tracker: A multi-view approach to segmenting and tracking people in a cluttered scene. IJCV.
  9. Okuma, K., Taleghani, A., de Freitas, N., Little, J., and Lowe, D. (2004). A boosted particle filter: multitarget detection and tracking. In ECCV.
  10. Viola, P. and Jones, M. (2001). Rapid Object Detection using a Boosted Cascade of Simple Features. In CVPR.
  11. Viola, P., Jones, M., and D.Snow (2003). Detecting pedestrians using patterns of motion and appearance. In ICCV.
  12. Zhao, T. and Nevatia, R. (2001). Car detection in low resolution aerial image. In ICCV.
Download


Paper Citation


in Harvard Style

Berclaz J., Fleuret F. and Fua P. (2008). PRINCIPLED DETECTION-BY-CLASSIFICATION FROM MULTIPLE VIEWS . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 375-382. DOI: 10.5220/0001081003750382


in Bibtex Style

@conference{visapp08,
author={Jérôme Berclaz and François Fleuret and Pascal Fua},
title={PRINCIPLED DETECTION-BY-CLASSIFICATION FROM MULTIPLE VIEWS},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={375-382},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001081003750382},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - PRINCIPLED DETECTION-BY-CLASSIFICATION FROM MULTIPLE VIEWS
SN - 978-989-8111-21-0
AU - Berclaz J.
AU - Fleuret F.
AU - Fua P.
PY - 2008
SP - 375
EP - 382
DO - 10.5220/0001081003750382