Pedestrian Detection Using SVM and Multi-Feature Combination
- 1 January 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
This paper describes a comprehensive combination of feature extraction methods for vision-based pedestrian detection in the framework of intelligent transportation systems. The basic components of pedestrians are first located in the image and then combined with a SVM-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 by-components learning approach is proposed in order to better deal with pedestrians 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, either at daytime and nighttime. The results achieved up to date show interesting conclusions that suggest a combination of feature extraction methods as an essential clue for enhanced detection performanceKeywords
This publication has 21 references indexed in Scilit:
- Cooperative Fusion for Multi-Obstacles Detection With Use of Stereovision and Laser ScannerAutonomous Robots, 2005
- Pedestrian Detection and Tracking With Night VisionIEEE Transactions on Intelligent Transportation Systems, 2005
- A comparative study of fast dense stereo vision algorithmsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Shape-based pedestrian detection and localizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Probabilistic template based pedestrian detection in infrared videosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Shape-based pedestrian detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Example-based object detection in images by componentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Stereo- and neural network-based pedestrian detectionIEEE Transactions on Intelligent Transportation Systems, 2000
- Autonomous driving goes downtownIEEE Intelligent Systems and their Applications, 1998
- Texture Unit, Texture Spectrum, And Texture AnalysisIEEE Transactions on Geoscience and Remote Sensing, 1990