DocumentCode :
70083
Title :
Efficient Feature Selection and Classification for Vehicle Detection
Author :
Xuezhi Wen ; Ling Shao ; Wei Fang ; Yu Xue
Author_Institution :
Jiangsu Eng. Center of Network Monitoring, Nanjing Univ. of Inf. Sci. & Technol., Nanjing, China
Volume :
25
Issue :
3
fYear :
2015
fDate :
Mar-15
Firstpage :
508
Lastpage :
517
Abstract :
The focus of this paper is on the problem of Haar-like feature selection and classification for vehicle detection. Haar-like features are particularly attractive for vehicle detection because they form a compact representation, encode edge and structural information, capture information from multiple scales, and especially can be computed efficiently. Due to the large-scale nature of the Haar-like feature pool, we present a rapid and effective feature selection method via AdaBoost by combining a sample´s feature value with its class label. Our approach is analyzed theoretically and empirically to show its efficiency. Then, an improved normalization algorithm for the selected feature values is designed to reduce the intra-class difference, while increasing the inter-class variability. Experimental results demonstrate that the proposed approaches not only speed up the feature selection process with AdaBoost, but also yield better detection performance than the state-of-the-art methods.
Keywords :
Haar transforms; edge detection; feature extraction; image classification; image representation; learning (artificial intelligence); road vehicles; traffic engineering computing; AdaBoost; Haar-like feature classification; Haar-like feature pool; Haar-like feature selection; compact representation; encode edge; improved normalization algorithm; interclass variability; intraclass difference; structural information; vehicle detection; Educational institutions; Feature extraction; Information science; Support vector machines; Training; Vehicle detection; Vehicles; AdaBoost; Haar-like features; support vector machine (SVM); vehicle detection; weak classifier;
fLanguage :
English
Journal_Title :
Circuits and Systems for Video Technology, IEEE Transactions on
Publisher :
ieee
ISSN :
1051-8215
Type :
jour
DOI :
10.1109/TCSVT.2014.2358031
Filename :
6898836
Link To Document :
بازگشت