基于YOLOv5的交通灯识别系统建立

Study on Traffic Light Recognition System Based on YOLOv5

随着云计算、人工智能、传感探测技术、自动控制技术、通信技术等的不断进步,无人驾驶技术也得到了快速发展,同时人们对无人驾驶汽车的接受度正在逐渐提升。其中,道路交通的环境感知是研究无人驾驶汽车技术的重点和难点,对交通灯的自动检测与识别是道路交通环境感知的重要组成部分。为了保证交通灯识别的准确性,文章提出了一种基于YOLOv5的交通灯识别系统,该系统可以准确地检测和识别交通灯的颜色,区分方向与数字。试验结果表明,该交通灯识别系统的识别准确率可达95%以上。

With the continuous progress of cloud computing,artificial intelligence,sensor detection technology,automatic control technology and communication technology,autonomous driving has also been booming,and the public's acceptance of autonomous driving vehicles is gradually increasing.Among them,environmental perception of road traffic is the focus of researching autonomous vehicles,and the automatic detection and recognition of traffic lights is a vital component of environmental perception.In order to ensure the accuracy of traffic light recognition,the article proposes a system based on YOLOv5,which can accurately detect and recognize traffic lights and distinguish the direction and numbers.The experimental results indicate that the accuracy of the system can reach over 95%.