车辆尾灯灯语检测与识别①.PDFVIP

2015 年 第 24 卷 第 11 期 计 算 机 系 统 应 用 ① 车辆尾灯灯语的检测与识别 1,2 2 1,2 2 田 强 , 孔 斌 , 孙翠敏 , 王 灿 1( 中国科学技术大学 信息科学技术学院, 合肥 23007) 2( 中国科学院 合肥智能机械研究所, 合肥 230031) 摘 要: 针对有效利用车辆灯语信息的问题, 提出了一种基于图像的车辆尾灯灯语的检测识别新方法. 该方法首 先利用颜色、对称性特征在图像中检测出车辆尾灯对, 并对车辆尾灯进行连续的跟踪. 然后使用参数优化的最小 二乘支持向量机(Least Squares Support Vector Machines, 简称 LS-SVM)对得到的车尾灯状态进行分类判别. 最后 结合状态历史信息, 综合推断出各前方车辆当前灯语含义. 以实车拍摄的白天道路视频进行实验, 可以看到由识 别出的灯语信息能够准确判断出前方车辆刹车、转向、灯不亮, 表明该检测识别方法有效. 关键词: 无人车; 机器视觉; 灯语识别; 车尾灯检测; 支持向量机(Support Vector Machine) Detection and Recognition the Signals of Vehicle Taillight 1,2 2 1,2 2 TIAN Qiang , KONG Bin , SUN Cui-Min , WANG Can 1(School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China) 2(Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031, China) Abstract: In this paper, a new algorithm of taillight signals detection and recognition based on image is proposed. Firstly, the algorithm detects and tracks vehicle taillights using color and symmetry features of the images. Secondly, we employ parameters-optimized Least Squares Support Vector Machines (LS-SVM) to classify the current states of detected taillights. Finally, we set up state chains from past frames to recognize the signals of taillights. Through the experiments on the real road, we can see that the recognized signals can correctly indicate the behaviors of brake and turn of preceding cars, which shows that our algorithm is valid. Key words: unmanned vehicle; machine vision; light signal recognition; taillight detection; Support Vector Machine (SVM) 对车辆所行驶道路环境的感知, 是无人驾驶车辆 我国交通法规约定的灯语有 12