DocumentCode :
679247
Title :
Blur-invariant traffic sign recognition using compact local phase quantization
Author :
Aly, Sherin ; Deguchi, Daisuke ; Murase, Hiroshi
Author_Institution :
Dept. of Electr. Eng., Aswan Univ., Aswan, Egypt
fYear :
2013
fDate :
6-9 Oct. 2013
Firstpage :
821
Lastpage :
827
Abstract :
Traffic signs are characterized by a wide variability in their visual appearance in real-world environments. For example, changes in illumination, varying weather conditions, blurring and partial occlusions impact the perception of road signs. One of the principal causes for traffic image quality degradation is blur. This is frequently due to car motion, camera out of focus, low resolution and atmospheric turbulence. In this paper, we employ a new feature extraction method named Compact Local Phase Quantization (CLPQ) for blur insensitive traffic sign recognition. Various local descriptors such as HOG, LBP are investigated and LPQ shows a high robustness to blur. LPQ features are extracted from phase information of local regions of the traffic signs, this produces a large dimension feature vector which is not practical for real-time application. Minimum-redundancy Maximum-relevance (mRMR) feature selection method is employed to select the most discriminative and non-redundant features. Experimental results show the effectiveness of combining local phase quantization descriptor and mRMR feature selection. The proposed method achieved 98:6% average recognition accuracy on the German traffic sign recognition benchmark (GTSRB) database.
Keywords :
feature extraction; feature selection; image recognition; image restoration; object recognition; quantisation (signal); traffic engineering computing; GTSRB database; German traffic sign recognition benchmark database; HOG; LBP; LPQ feature extraction; blur insensitive traffic sign recognition; blur-invariant traffic sign recognition; compact local phase quantization; discriminative feature selection; feature vector; local phase quantization descriptor; local regions; mRMR feature selection; minimum-redundancy maximum-relevance feature selection method; nonredundant feature selection; phase information; recognition accuracy; traffic image quality degradation; visual appearance; Accuracy; Feature extraction; Image recognition; Quantization (signal); Robustness; Training; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Transportation Systems - (ITSC), 2013 16th International IEEE Conference on
Conference_Location :
The Hague
Type :
conf
DOI :
10.1109/ITSC.2013.6728333
Filename :
6728333
Link To Document :
بازگشت