An Analysis of Sampling for Filter-based Feature Extraction and AdaBoost Learning

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.

[1]  L. Petersson,et al.  Boosting with Multiple Classifier Families , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[2]  Jens-Rainer Ohm,et al.  Multimedia Communication Technology , 2004 .

[3]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[4]  G. Bebis,et al.  On-road vehicle detection using optical sensors: a review , 2004, Proceedings. The 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No.04TH8749).

[5]  A. Lopez,et al.  3D vehicle sensor based on monocular vision , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[6]  Rainer Lienhart,et al.  Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection , 2003, DAGM-Symposium.