Traffic Signs Detection Based on Faster R-CNN
Zhongrong Zuo, Kai Yu, Qiao Zhou, Xu Jie Wang, Ting Li · 2017
In this paper, we use a advanced method called Faster R-CNN to detect traffic signs. This new method represents the highest level in object recognition, which don't need to extract image feature manually anymore and can segment image to get candidate region proposals automatically. Our experiment is based on a traffic sign detection competition in 2016 by CCF and UISEE company. The mAP(mean average precision) value of the result is 0.3449 that means Faster R-CNN can indeed be applied in this field. Even though the experiment did not achieve the best results, we explore a new method in the area of the traffic signs detection. We believe that we can get a better achievement in the future.