Combination of Feature Extraction Methods for SVM Pedestrian Detection

This paper describes a comprehensive combination of feature extraction methods for vision-based pedestrian detection in Intelligent Transportation Systems. The basic components of pedestrians are first located in the image and then combined with a support-vector-machine-based classifier. This poses...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on intelligent transportation systems Vol. 8; no. 2; pp. 292 - 307
Main Authors:	Alonso, I.P., Llorca, D.F., Sotelo, M.A., Bergasa, L.M., Pedro Revenga de Toro, Nuevo, J., Ocana, M., Garrido, M.A.G.
Format:	Journal Article
Language:	English
Published:	Piscataway, NJ IEEE 01-06-2007 Institute of Electrical and Electronics Engineers The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Applied sciences Artificial intelligence Calibration Cameras Computer science; control theory; systems Control theory. Systems Data processing. List processing. Character string processing Exact sciences and technology Feature extraction Features combination Ground, air and sea transportation, marine construction Infrared detectors Intelligent transportation systems Learning Lighting Mass production Memory organisation. Data processing Pattern recognition. Digital image processing. Computational geometry pedestrian detection Pedestrians Robotics Software Stereo vision subtractive clustering support vector machine (SVM) classifier Support vector machine classification Support vector machines Traffic engineering Traffic flow Transportation systems Cluster analysis Occlusion Transportation system support vector machine (SVM) classifier Image interpretation pedestrian detection Variability Pedestrian Visual servoing Clutter Classification Vector support machine Illumination Probability learning Stereopsis stereo vision Pattern extraction Intelligent system Computer vision Statistical analysis subtractive clustering Stereo image processing Software component Pattern recognition Luminance Features combination Feature extraction Artificial intelligence
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	This paper describes a comprehensive combination of feature extraction methods for vision-based pedestrian detection in Intelligent Transportation Systems. The basic components of pedestrians are first located in the image and then combined with a support-vector-machine-based classifier. This poses the problem of pedestrian detection in real cluttered road images. Candidate pedestrians are located using a subtractive clustering attention mechanism based on stereo vision. A components-based learning approach is proposed in order to better deal with pedestrian variability, illumination conditions, partial occlusions, and rotations. Extensive comparisons have been carried out using different feature extraction methods as a key to image understanding in real traffic conditions. A database containing thousands of pedestrian samples extracted from real traffic images has been created for learning purposes at either daytime or nighttime. The results achieved to date show interesting conclusions that suggest a combination of feature extraction methods as an essential clue for enhanced detection performance
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 ObjectType-Article-2 ObjectType-Feature-1
ISSN:	1524-9050 1558-0016
DOI:	10.1109/TITS.2007.894194