This article is
- freely available
Boosting-Based On-Road Obstacle Sensing Using Discriminative Weak Classifiers
Division of Electronics and Information Engineering, Chonbuk National University, Jeonju 561-756, Korea
Department of IT Engineering, Sangmyung University, Chonan 330-720, Korea
* Author to whom correspondence should be addressed.
Received: 14 January 2011; in revised form: 20 March 2011 / Accepted: 12 April 2011 / Published: 14 April 2011
Abstract: This paper proposes an extension of the weak classifiers derived from the Haar-like features for their use in the Viola-Jones object detection system. These weak classifiers differ from the traditional single threshold ones, in that no specific threshold is needed and these classifiers give a more general solution to the non-trivial task of finding thresholds for the Haar-like features. The proposed quadratic discriminant analysis based extension prominently improves the ability of the weak classifiers to discriminate objects and non-objects. The proposed weak classifiers were evaluated by boosting a single stage classifier to detect rear of car. The experiments demonstrate that the object detector based on the proposed weak classifiers yields higher classification performance with less number of weak classifiers than the detector built with traditional single threshold weak classifiers.
Keywords: weak classifiers; Haar-like features; AdaBoost; quadratic discriminant analysis
Article StatisticsClick here to load and display the download statistics.
Notes: Multiple requests from the same IP address are counted as one view.
Cite This Article
MDPI and ACS Style
Adhikari, S.P.; Yoo, H.-J.; Kim, H. Boosting-Based On-Road Obstacle Sensing Using Discriminative Weak Classifiers. Sensors 2011, 11, 4372-4384.
Adhikari SP, Yoo H-J, Kim H. Boosting-Based On-Road Obstacle Sensing Using Discriminative Weak Classifiers. Sensors. 2011; 11(4):4372-4384.
Adhikari, Shyam Prasad; Yoo, Hyeon-Joong; Kim, Hyongsuk. 2011. "Boosting-Based On-Road Obstacle Sensing Using Discriminative Weak Classifiers." Sensors 11, no. 4: 4372-4384.