Abstract | ||
---|---|---|
The paper presents a Traffic Sign Recognition (TSR) system, which can fast and accurately recognize traffic signs of different sizes in images. The system consists of two well-designed Convolutional Neural Networks (CNNs), one for region proposals of traffic signs and one for classification of each region. In the proposal CNN, a Fully Convolutional Network (FCN) with a dual multi-scale architecture is proposed to achieve scale invariant detection. In training the proposal network, a modified Online Hard Example Mining (OHEM) scheme is adopted to suppress false positives. The classification network fuses multi-scale features as representation and adopts an Inception module for efficiency. We evaluate the proposed TSR system and its components with extensive experiments. Our method obtains $99.88%$ precision and $96.61%$ recall on the Swedish Traffic Signs Dataset (STSD), higher than state-of-the-art methods. Besides, our system is faster and more lightweight than state-of-the-art deep learning networks for traffic sign recognition. |
Year | DOI | Venue |
---|---|---|
2017 | 10.5244/c.31.168 | british machine vision conference |
DocType | Volume | Citations |
Conference | abs/1805.12289 | 0 |
PageRank | References | Authors |
0.34 | 17 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuchen Yang | 1 | 73 | 3.93 |
Shuo Liu | 2 | 30 | 11.34 |
Wei Ma | 3 | 9 | 1.77 |
Qiuyuan Wang | 4 | 13 | 2.16 |
Liu Zheng | 5 | 47 | 12.80 |