Efficent Traffic-Sign Recognition with Scale-aware CNN

Yuchen Yang, Shuo Liu, Wei Ma, Qiuyuan Wang and Zheng Liu

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.

Session

Posters

Files

Paper (PDF)
Supplementary (PDF)

DOI

10.5244/C.31.168
https://dx.doi.org/10.5244/C.31.168

Citation

Bibtex

            @inproceedings{BMVC2017_168,
                title={Efficent Traffic-Sign Recognition with Scale-aware CNN},
                author={Yuchen Yang, Shuo Liu, Wei Ma, Qiuyuan Wang and Zheng Liu},
                year={2017},
                month={September},
                pages={168.1-168.13},
                articleno={168},
                numpages={13},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.168},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.168}
            }