AUTOMATIC PROCESS TO BUILD A CONTEXTUALIZED DETECTOR

Thierry Chesnais, Nicolas Allezard, Yoann Dhome, Thierry Chateau

Abstract

This article tackles the real-time pedestrian detection problem using a stationary uncalibrated camera. More precisely we try to specialize a classifier by taking into account the context of the scene. To achieve this goal, we introduce an offline semi-supervised approach which uses an oracle. This latter must automatically label a video, in order to obtain contextualized training data. The proposed oracle is composed of several detectors. Each of them is trained on a different signal: appearance, background subtraction and optical flow signals. Then we merge their responses and keep the more confident detections. A specialized detector is then built on the resulting dataset. Designed for improving camera network installation procedure, the presented method is completely automatic and does not need any knowledge about the scene.

References

  1. Agarwal, S., Awan, A., and Roth, D. (2004). Learning to detect objects in images via a sparse, part-based representation. Pattern Analysis and Machine Intelligence.
  2. Black, M. (1996). The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields. Computer Vision and Image Understanding.
  3. Blum, A. and Mitchell, T. (1998). Combining labeled and unlabeled data with co-training. In Proceedings of the eleventh annual conference on Computational learning theory.
  4. Dalal, N. and Triggs, B. (2005). Histograms of oriented gradients for human detection. In Int. Conf. on Computer Vision and Pattern Recognition.
  5. Dollár, P., Wojek, C., Schiele, B., and Perona, P. (2011). Pedestrian detection: An evaluation of the state of the art. Pattern Analysis and Machine Intelligence.
  6. Enzweiler, M. and Gavrila, D. M. (2009). Monocular pedestrian detection: Survey and experiments. Pattern Analysis and Machine Intelligence.
  7. Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., and Zisserman, A. (2009). The PASCAL Visual Object Classes Challenge 2009 (VOC2009) Results.
  8. Friedman, J., Hastie, T., and Tibshirani, R. (1998). Additive logistic regression: a statistical view of boosting. Annals of Statistics.
  9. Grabner, H. and Bischof, H. (2006). On-line boosting and vision. In Int. Conf. on Computer Vision and Pattern Recognition.
  10. Leistner, C., Saffari, A., Roth, P. M., and H., B. (2009). On robustness of on-line boosting - a competitive study. In Int. Conf. on Computer Vision - Workshop on Online Learning for Computer Vision.
  11. Levin, A., Viola, P., and Freund, Y. (2003). Unsupervised improvement of visual detectors using co-training. Int. Conf. on Computer Vision.
  12. Rosenberg, C., Hebert, M., and Schneiderman, H. (2005). Semi-supervised self-training of object detection models. IEEE Workshop on Applications of Computer Vision.
  13. Schapire, R. E. and Singer, Y. (1999). Improved boosting algorithms using confidence-rated predictions. Machine Learning.
  14. Stalder, S., Grabner, H., and Gool, L. V. (2009). Exploring context to learn scene specific object detectors. In IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.
  15. Stauffer, C. and Grimson, W. E. L. (1999). Adaptive background mixture models for real-time tracking. In Int. Conf. on Computer Vision and Pattern Recognition.
  16. Vapnik, V. N. (1995). The Nature of Statistical Learning Theory. Springer.
Download


Paper Citation


in Harvard Style

Chesnais T., Allezard N., Dhome Y. and Chateau T. (2012). AUTOMATIC PROCESS TO BUILD A CONTEXTUALIZED DETECTOR . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 513-520. DOI: 10.5220/0003822105130520


in Bibtex Style

@conference{visapp12,
author={Thierry Chesnais and Nicolas Allezard and Yoann Dhome and Thierry Chateau},
title={AUTOMATIC PROCESS TO BUILD A CONTEXTUALIZED DETECTOR},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={513-520},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003822105130520},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - AUTOMATIC PROCESS TO BUILD A CONTEXTUALIZED DETECTOR
SN - 978-989-8565-03-7
AU - Chesnais T.
AU - Allezard N.
AU - Dhome Y.
AU - Chateau T.
PY - 2012
SP - 513
EP - 520
DO - 10.5220/0003822105130520