A Traffic Sign Detection Algorithm Based On Deep Convolutional Neural Network
2016 IEEE INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING (ICSIP)(2016)
摘要
Traffic sign detection plays an important role in driving assistance systems and traffic safety. But the existing detection methods are usually limited to a predefined set of traffic signs. Therefore we propose a traffic sign detection algorithm based on deep Convolutional Neural Network (CNN) using Region Proposal Network(RPN) to detect all Chinese traffic sign. Firstly, a Chinese traffic sign dataset is obtained by collecting seven main categories of traffic signs and their subclasses. Then a traffic sign detection CNN model is trained and evaluated by fine-tuning technology using the collected dataset. Finally, the model is tested by 33 video sequences with the size of 640x480. The result shows that the proposed method has towards real-time detection speed and above 99% detection precision. The trained model can be used to capture the traffic sign from videos by on-board camera or driving recorder and construct a complete traffic sign dataset.
更多查看译文
关键词
traffic sign, object detection, convolutional neural network, region proposal network, dataset
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要