文献类型：期刊文献

英文题名：Traffic Sign Detection via Efficient ROI Detector and Deep Convolution Neural Network

作者：Pan, Weiguo[1,2]; Fu, En[1,2]; Xu, Bingxin[1,2]; Dai, Songyin[1,2]; Pan, Feng[1,2]

第一作者：潘卫国

通讯作者：Pan, Weiguo

机构：[1] Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China; [2] College of Robotics, Beijing Union University, Beijing, 100020, China

第一机构：北京联合大学北京市信息服务工程重点实验室

年份：2020

卷号：16

期号：10

起止页码：1566-1578

外文期刊名：International Journal of Performability Engineering

收录：EI(收录号：20204709505778);Scopus(收录号：2-s2.0-85096097240)

基金：This work was supported by the National Natural Science Foundation of China (Nos. 61802019, 61871039) and Beijing Municipal Education Commission Science and Technology Program (Nos. KM201911417009, KM201911417001).

语种：英文

外文关键词：Deep neural networks - Image segmentation - Neural networks - Object detection - Statistical tests - Tunneling (excavation)

摘要：With the rapid development of intelligent driving and self-driving, how to quickly identify traffic signs in traffic scenes image is an urgent problem that needs to be solved. The existing object detection method can be divided into two categories: The one-staged method, which has a fast detection speed, and the two-stage method, which has higher detection accuracy. How to quickly and accurately detect targets in traffic scenes images is a current research focus. In this paper, an effective detection operator for the region of interest of traffic signs that utilizes the color, shape, and layout characteristics of traffic signs was proposed. It can accurately extract the region of interest in the traffic scene image for detection stage. The existing two-stage network was also fine-tuned to improve the accuracy of traffic sign detection. On the basis of the existing public data set, 13,000 images were collected and annotated to expand the training and test data. These data were used to verify the method proposed in this article. Experiments demonstrated that the proposed method has been improved in detection speed and detection accuracy. ? 2020 Totem Publishers Ltd. All rights reserved.