基于多帧视频图像的交通标志实时检测.pdfVIP

Computer Science and Application 计算机科学与应用, 2017, 7(5), 463-472 Published Online May 2017 in Hans. /journal/csa /10.12677/csa.2017.75057 Real-Time Traffic Sign Detection Based on Multi-Frame Video Images 1 1 2 Fei Yang , Bo Qin , Wei Li 1 Department of Computer Science Technology, Ocean University of China, Qingdao Shandong 2 Zaozhuang Vocational College of Science and Technology, Zaozhuang Shandong th th st Received: May 10 , 2017; accepted: May 28 , 2017; published: May 31 , 2017 Abstract Detection of Urban road traffic sign is an important part of the Modern Intelligent Transportation System (ITS). In order to extract the integral areas of traffic signs and reduce the computation load, this paper has improved the fast color-segment compression algorithm. And, it verifies the traffic sign candidate areas to decrease false positives and raise the accuracy by analyzing the variation in preceding video-images sequence while implementing the proposed Spatial Temporal Model (STM). Experimental results indicate that the accuracy, efficiency and the robustness of the framework are better than the method based on one frame, and it can be applied to detect urban road traffic signs in real time. Keywords Traffic Sign Detection, ITS, Spatial Temporal Model (STM) 基于多帧视频图像的交通标志实时检测 1 1 2 杨 斐 ，秦 勃 ，李 伟 1 中国海洋大学计算机科学与技术系，山东 青岛 2枣庄科技职业学院，山东 枣庄 收稿日期：2017年5月10 日；录用日期：2017年5月28 日；发布日期：2017年5月31 日 摘 要 城市道路交通标志检测是现代智能交通的重要组成部分。本文通过改进基于颜色的图像快速分割算法， 文章引用: 杨斐, 秦勃, 李伟. 基于多帧视频图像的交通标志实时检测[J]. 计算机科学与应用, 2017, 7(5): 463-472. /10.12677/csa.2017.75057 杨斐 等