Salient traffic sign recognition based on sparse representation of visual perception

• Published in: 2012 International Conference on Computer Vision in Remote Sensing pp. 273 - 278
• Main Authors: Ce Li, Yaling Hu, Limei Xiao, Lihua Tian
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2012
• Subjects: Accuracy; Artificial neural networks; Quaternion Fourier transform; Robustness; Sparse coding; Support Vector Machine (SVM); Support vector machines; Traffic sign detection; Traffic sign recogntion; Visual saliency
• ISBN: 146731272X; 9781467312721
• DOI: 10.1109/CVRS.2012.6421274

This paper proposes a new approach to recognize salient traffic signs, which is based on sparse representation of visual perception via visual saliency and speeded up robust features (SURF) algorithm. The proposed algorithm deals with two tasks: traffic signs detection and traffic signs recognition. Firstly, multi-scale phase spectrum of quaternion Fourier transformation method is used to obtain the location of traffic signs in scenes image. Secondly, traffic signs local sparse features are extracted by the improved algorithm based on SURF descriptors and locality-constrained linear coding (LLC) method. Finally, linear support vector machine (SVM) is used to train classifier and test recognition accuracy rate of ban traffic signs. Extensive experiments on 1000 images show that our approach can improve recognition accuracy rate and reduce running time.