An Efficient Method for Traffic Sign Recognition Based on Extreme Learning Machine

• Published in: IEEE transactions on cybernetics Vol. 47; no. 4; pp. 920 - 933
• Main Authors: Huang, Zhiyong, Yu, Yuanlong, Gu, Jason, Liu, Huaping
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Classifiers; Computational efficiency; Computing time; Datasets; Extreme learning machine (ELM); Feature extraction; Histograms; HOG variant (HOGv); Machine learning; Mapping; Neural networks; Recognition; Redundancy; Robustness; Shape; Traffic control; traffic sign recognition (TSR); Traffic signs; Training
• ISSN: 2168-2267; 2168-2275
• DOI: 10.1109/TCYB.2016.2533424

This paper proposes a computationally efficient method for traffic sign recognition (TSR). This proposed method consists of two modules: (1) extraction of histogram of oriented gradient variant (HOGv) feature and (2) a single classifier trained by extreme learning machine (ELM) algorithm. The presented HOGv feature keeps a good balance between redundancy and local details such that it can represent distinctive shapes better. The classifier is a single-hidden-layer feedforward network. Based on ELM algorithm, the connection between input and hidden layers realizes the random feature mapping while only the weights between hidden and output layers are trained. As a result, layer-by-layer tuning is not required. Meanwhile, the norm of output weights is included in the cost function. Therefore, the ELM-based classifier can achieve an optimal and generalized solution for multiclass TSR. Furthermore, it can balance the recognition accuracy and computational cost. Three datasets, including the German TSR benchmark dataset, the Belgium traffic sign classification dataset and the revised mapping and assessing the state of traffic infrastructure (revised MASTIF) dataset, are used to evaluate this proposed method. Experimental results have shown that this proposed method obtains not only high recognition accuracy but also extremely high computational efficiency in both training and recognition processes in these three datasets.