期刊名称：International Journal of Hybrid Information Technology
印刷版ISSN：1738-9968
出版年度：2015
卷号：8
期号：6
页码：323-332
DOI：10.14257/ijhit.2015.8.6.31
出版社：SERSC
摘要：According to the traffic light recognition problem of intelligent vehicle, this paper proposes a traffic light recognition algorithm based on compressive tracking. First, the candidate regions of traffic light are extracted. Second, after extracting the HOG feature of candidate regions, using the machine learning for classification and recognition, compressive tracking algorithm is used to track lights that have been identified a automatically. This algorithm combines feature recognition and tracking identification of traffic light and traffic light changes in scale and color can be identified normally. The algorithm proposed in this paper has been tested on actual road in intelligent vehicle; traffic light recognition effect is good.
