AN ANALYSIS OF SAMPLING FOR FILTER-BASED FEATURE EXTRACTION AND ADABOOST LEARNING

Anselm Haselhoff, Anton Kummert

2009

Abstract

In this work a sampling scheme for filter-based feature extraction in the field of appearance-based object detection is analyzed. Optimized sampling radically reduces the number of features during the AdaBoost training process and better classification performance is achieved. The signal energy is used to determine an appropriate sampling resolution which then is used to determine the positions at which the features are calculated. The advantage is that these positions are distributed according to the signal properties of the training images. The approach is verified using an AdaBoost algorithm with Haar-like features for vehicle detection. Tests of classifiers, trained with different resolutions and a sampling scheme, are performed and the results are presented.

References

  1. Lienhart, R., Kuranov, A., and Pisarevsky, V. (2002). Empirical analysis of detection cascades of boosted classifiers for rapid object detection. Technical report, Mic. Research Lab, Intel Corporation, Santa Clara, CA 95052, USA.
  2. Ohm, J.-R. (2004). Multimedia Communication Technology. Springer, Berlin, Heidelberg, Germany.
  3. Overett, G. and Petersson, L. (2007). Boosting with multiple classifier families. Proc. of IEEE Intelligent Vehicles Symposium, pages 1039-1044.
  4. Ponsa, D., Lopez, A., Lumbreras, F., Serrat, J., and Graf, T. (2005). 3d vehicle sensor based on monocular vision. In Proc. of the 8th Int. IEEE Conf. on Intelligent Transportation Systems, Vienna, Austria.
  5. Russell, B., Torralba, A., and Freeman, W. T. (2005). Labelme image database. http://labelme.csail.mit.edu.
  6. Sun, Z., Bebis, G., and Miller, R. (2004). On-road vehicle detection using optical sensors: A review.
  7. Viola, P. and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Accepted Conf. on Computer Vision and Pattern Recognition.
Download


Paper Citation


in Harvard Style

Haselhoff A. and Kummert A. (2009). AN ANALYSIS OF SAMPLING FOR FILTER-BASED FEATURE EXTRACTION AND ADABOOST LEARNING . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 180-185. DOI: 10.5220/0001791201800185


in Bibtex Style

@conference{visapp09,
author={Anselm Haselhoff and Anton Kummert},
title={AN ANALYSIS OF SAMPLING FOR FILTER-BASED FEATURE EXTRACTION AND ADABOOST LEARNING},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={180-185},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001791201800185},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)
TI - AN ANALYSIS OF SAMPLING FOR FILTER-BASED FEATURE EXTRACTION AND ADABOOST LEARNING
SN - 978-989-8111-69-2
AU - Haselhoff A.
AU - Kummert A.
PY - 2009
SP - 180
EP - 185
DO - 10.5220/0001791201800185