DocumentCode :
671473
Title :
A robust, coarse-to-fine traffic sign detection method
Author :
Gangyi Wang ; Guanghui Ren ; Zhilu Wu ; Yaqin Zhao ; Lihui Jiang
Author_Institution :
Sch. of Electron. & Inf. Eng., Harbin Inst. of Technol., Harbin, China
fYear :
2013
fDate :
4-9 Aug. 2013
Firstpage :
1
Lastpage :
5
Abstract :
We present a traffic sign detection method which has won the first place for the prohibitory and mandatory signs and the third place for the danger signs in the GTSDB competition. The method uses the histogram of oriented gradient (HOG) and a coarse-to-fine sliding window scheme. Candidate ROIs are first roughly detected within a small-sized window, and then further verified within a large-sized window for higher accuracy. Experimental results show that the proposed method achieves high recall and precision ratios, and is robust to various adverse situations including bad lighting condition, partial occlusion, low quality and small projective deformation.
Keywords :
driver information systems; object detection; GTSDB competition; HOG; coarse-to-fine sliding window scheme; danger signs; histogram of oriented gradient; large-sized window; mandatory signs; small-sized window; traffic sign detection method; Accuracy; Feature extraction; Image color analysis; Robustness; Shape; Support vector machines; Training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks (IJCNN), The 2013 International Joint Conference on
Conference_Location :
Dallas, TX
ISSN :
2161-4393
Print_ISBN :
978-1-4673-6128-6
Type :
conf
DOI :
10.1109/IJCNN.2013.6706812
Filename :
6706812
Link To Document :
بازگشت