文献类型：期刊文献

英文题名：REAL-TIME TRAFFIC LIGHT RECOGNITION BASED ON C-HOG FEATURES

作者：Zhou, Xuanru[1];Yuan, Jiazheng[2];Liu, Hongzhe[1]

第一作者：Zhou, Xuanru

通讯作者：Yuan, JZ[1]

机构：[1]Beijing Union Univ, Beijing Key Lab Informat Serv, Beijing 100101, Peoples R China;[2]Beijing Open Univ, Sci Res Off, Beijing 100081, Peoples R 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

通讯机构：[1]corresponding author), Beijing Open Univ, Sci Res Off, Beijing 100081, Peoples R China.

年份：2017

卷号：36

期号：4

起止页码：793-814

外文期刊名：COMPUTING AND INFORMATICS

收录：;EI(收录号：20174504373237);Scopus(收录号：2-s2.0-85032798620);WOS:【SCI-EXPANDED(收录号:WOS:000419276100003)】；

基金：This project was supported by The National Natural Science Foundation of China (Nos.61571045, 61372148), Beijing Natural Science Foundation (4152016) and The National Key Technology R&D Program (2014BAK08B02, 2015BAH55F03).

语种：英文

外文关键词：C-HOG features; SVM; traffic light recognition; intelligent vehicles

摘要：This paper proposes a real-time traffic light detection and recognition algorithm that would allow for the recognition of traffic signals in intelligent vehicles. This algorithm is based on C-HOG features (Color and HOG features) and Support Vector Machine (SVM). The algorithm extracted red and green areas in the video accurately, and then screened the eligible area. Thereafter, the C-HOG features of all kinds of lights could be extracted. Finally, this work used SVM to build a classifier of corresponding category lights. This algorithm obtained accurate real-time information based on the judgment of the decision function. Furthermore, experimental results show that this algorithm demonstrated accuracy and good real-time performance.