On-road vehicle detection using Gabor filters and support vector machines
Zehang Sun
Bebis, G.
Miller, R.
Comput. Vision Lab., Nevada Univ., Reno, NV, USA;
This paper appears in: Digital Signal Processing, 2002. DSP 2002. 2002 14th International Conference on
Publication Date: 2002
Volume: 2,
On page(s): 1019- 1022 vol.2
ISSN:
ISBN: 0-7803-7503-3
INSPEC Accession Number: 7516160
Digital Object Identifier: 10.1109/ICDSP.2002.1028263
Posted online: 2002-11-07 17:07:23.0
Abstract
On-road vehicle detection is an important problem with application to driver assistance systems and autonomous, self-guided vehicles. The focus of this paper is on the problem of feature extraction and classification for rear-view vehicle detection. Specifically, we propose using Gabor filters for vehicle feature extraction and support vector machines (SVM) for vehicle detection. Gabor filters provide a mechanism for obtaining some degree of invariance to intensity due to global illumination, selectivity in scale, and selectivity in orientation. Basically, they are orientation and scale tunable edge and line detectors. Vehicles do contain strong edges and lines at different orientation and scales, thus, the statistics of these features (e.g., mean, standard deviation, and skewness) could be very powerful for vehicle detection. To provide robustness, these statistics are not extracted from the whole image but rather are collected from several subimages obtained by subdividing the original image into subwindows. These features are then used to train a SVM classifier. Extensive experimentation and comparisons using real data, different features (e.g., based on principal components analysis (PCA)), and different classifiers (e.g., neural networks (NN)) demonstrate the superiority of the proposed approach which has achieved an average accuracy of 94.81% on completely novel test images.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
