FPGA Based Traffic Sign Detection Using Support Vector Machine and Hybrid Filters

Abstract

Aiming at the problems of low recognition accuracy and algorithm efficiency of existing recognition methods for traffic signs, a Principal Component Analysis-Support Vector Machine (PCA-SVM) road traffic sign recognition method based on grid search was proposed. In this method, the principal component analysis (PCA) method is used to reduce the dimensionality of the traffic signs, and the principal component features of the traffic signs are extracted. The SVM classifier with optimized parameters realizes the recognition of traffic signs. Through experimental simulation and analysis and comparison with other existing traffic sign recognition algorithms, the experimental results show that the method in this paper can ensure high recognition accuracy, and the algorithm efficiency is significantly improved. The system is implemented on a Spartan-6-FPGA. For image acquisition, an off-the-shelf car camera is used. The developed system is able to reliably detect traffic signs on short distances on static images as well as on image streams.