首页 | 本学科首页   官方微博 | 高级检索  
     

基于径向对称变换的自适应交通禁止标志检测
引用本文:李厚杰,邱天爽,宋海玉,王培昌,贺建军. 基于径向对称变换的自适应交通禁止标志检测[J]. 光电子.激光, 2014, 0(3): 532-539
作者姓名:李厚杰  邱天爽  宋海玉  王培昌  贺建军
作者单位:大连理工大学 电子信息与电气工程学部,辽宁 大连 116024;大连理工大学 电子信息与电气工程学部,辽宁 大连 116024;大连民族学院 计算机科学与工程学院,辽宁 大 连 116605;大连民族学院 信息 与通信工程学院,辽宁 大连 116605;大连民族学院 信息 与通信工程学院,辽宁 大连 116605
基金项目:国家自然科学基金(81241059,61172108,61139001)、国家科技支撑 计划(2012BAJ18B06)、中央高校基本科研基金(DC110313,DC120101073)和国家民 委科研(12DLZ011)资助项目 (1.大连理工大学 电子信息与电气工程学部,辽宁 大连 116024; 2.大连民族学院 信息 与通信工程学院,辽宁 大连 116605; 3.大连民族学院 计算机科学与工程学院,辽宁 大连 116605)
摘    要:提出一种基于径向对称变换的自适应交通禁止标志的检测算法。采用RGB归一化阈值分割算法对交通图像进行二值化处理,构造和利用区域轮廓特征矢量,判决和提取候选标志区域。对于标志互相遮挡候选区域,提出采用基于分水岭变换的自适应标志分离算法进行标志分离;然后,对于低维的标志候选区域,根据其自身尺度特征提出一种参数自适应的径向对称圆形检测器和检测算法,最终确定禁止标志。本文算法在标准交通标志数据集(GTSDB)进行了实验验证。实验结果表明,与现有方法相比,本文算法有效提高了算法执行效率和检测性能,降低了算法复杂度;并且,对交通标志尺度、亮度和天气变化、运动模糊以及标志互相遮挡等有着良好的鲁棒性。

关 键 词:区域轮廓特征  分水岭变换  径向对称变换  参数自适应性  交通禁止标志检测
收稿时间:2013-08-05

Adaptive traffic prohibitive sign detection based on radial symmetry transform
LI Hou-jie,QIU Tian-shuang,SONG Hai-yu,WA NG Pei-chang and HE Jian-jun. Adaptive traffic prohibitive sign detection based on radial symmetry transform[J]. Journal of Optoelectronics·laser, 2014, 0(3): 532-539
Authors:LI Hou-jie  QIU Tian-shuang  SONG Hai-yu  WA NG Pei-chang  HE Jian-jun
Affiliation:Faculty of Electronic Information & Electrical Engineering,Dalian Universi ty of Technology,Dalian 116024, China;Faculty of Electronic Information & Electrical Engineering,Dalian Universi ty of Technology,Dalian 116024, China;School of Computer Science & Engineering,Dalian Nationalities Univers ity,Dalian 116605,China;College of Information and Communication Engineering,Dalian Nationali ties University,Dalian 116605, China;College of Information and Communication Engineering,Dalian Nationali ties University,Dalian 116605, China
Abstract:Traffic sign detection is a key technology in driving assistance syste ms.The effective detection for prohibitive signs is crucial to ensure the driver safety and reduce the traffic accidence.In this paper,we propose an adaptive detection method for prohibitive signs based on the radial symmetry transform.A traffic image is segmented based on RGB normalized threshold algorithm and a binary image is gene rated.Then a regional contour feature vector is constructed and used to determine and extract every ca ndidate sign region.For the region with possible mutually occluding signs,an adaptive separation algorithm based on the watershed transform is presented to perform signs separation.For each abstracted cand idate sign region,the key parameters in the radial symmetry transform are set adaptively according to the scale feature of the region,and an adaptive radial symmetry circular detector and corresponding detection approa ch are constructed and used to detect the prohibitive signs and reject the non-sign regions.The performance of the propo sed method is tested on the German traffic sign detection benchmark (GTSDB).Experimental results demonstrate the effectiveness of our method.Our method outperforms the existing algorithms in terms of execution effi ciency,detection rate and algorithm complexity,and ours has the robustness to th e object scale variation,variable lighting condition and weather,motion blurring and mutual occlusion of signs,etc.
Keywords:regional contour feature   watershed transform   radial symmetry transf orm   parameter adaptability   traffic prohibitive sign detection
本文献已被 CNKI 等数据库收录!
点击此处可从《光电子.激光》浏览原始摘要信息
点击此处可从《光电子.激光》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号