COLOR EXPLOITATION IN HOG-BASED TRAFFIC SIGN DETECTION

被引:79
作者
Creusen, I. M. [1 ,3 ]
Wijnhoven, R. G. J. [2 ,3 ]
Herbschleb, E. [3 ]
de With, P. H. N. [1 ,3 ]
机构
[1] CycloMedia BV, POB 68, NL-4180 BB Waardenburg, Netherlands
[2] ViNot BV, Eindhoven, Netherlands
[3] Eindhoven Univ Technol, Eindhoven, Netherlands
来源
2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING | 2010年
关键词
Object detection; Object recognition;
D O I
10.1109/ICIP.2010.5651637
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
We study traffic sign detection on a challenging large-scale real-world dataset of panoramic images. The core processing is based on the Histogram of Oriented Gradients (HOG) algorithm which is extended by incorporating color information in the feature vector. The choice of the color space has a large influence on the performance, where we have found that the CIELab and YCbCr color spaces give the best results. The use of color significantly improves the detection performance. We compare the performance of a specific and HOG algorithm, and show that HOG outperforms the specific algorithm by up to tens of percents in most cases. In addition, we propose a new iterative SVM training paradigm to deal with the large variation in background appearance. This reduces memory consumption and increases utilization of background information.
引用
收藏
页码:2669 / 2672
页数:4
相关论文
共 9 条
[1]  
Baro Xavier, 2009, Proceedings of the 2009 International Conference on Image Processing, Computer Vision, & Pattern Recognition. IPCV 2009, P839
[2]   Mean shift: A robust approach toward feature space analysis [J].
Comaniciu, D ;
Meer, P .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (05) :603-619
[3]   Histograms of oriented gradients for human detection [J].
Dalal, N ;
Triggs, B .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :886-893
[4]  
Dollár P, 2009, PROC CVPR IEEE, P304, DOI 10.1109/CVPRW.2009.5206631
[5]  
Fleyeh H., 2005, 10th EWGT Meeting and 16th Mini-EURO Conference, P644
[6]  
Herbschleb Ernst, 2009, VISUAL COMMUNICATION, V7257, p0A1
[7]  
Leibe Bastian., 2003, In British Machine Vison Conference (BMVC'03), P759
[8]   Distinctive image features from scale-invariant keypoints [J].
Lowe, DG .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 60 (02) :91-110
[9]   Rapid object detection using a boosted cascade of simple features [J].
Viola, P ;
Jones, M .
2001 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2001, :511-518