|
|||||
|
|
| 鲁棒实时钢轨表面擦伤检测算法研究 | |
| 引用本文： | 任盛伟,李清勇,许贵阳,韩强,罗四维,冯其波.鲁棒实时钢轨表面擦伤检测算法研究[J].中国铁道科学,2011,32(1). |
| 作者姓名： | 任盛伟 李清勇 许贵阳 韩强 罗四维 冯其波 |
| 作者单位： | 1. 中国铁道科学研究院,基础设施检测研究所,北京,100081;北京交通大学,理学院,北京100044 2. 北京交通大学,计算机与信息技术学院,北京,100044 3. 中国铁道科学研究院,基础设施检测研究所,北京,100081 4. 北京交通大学,理学院,北京100044 |
| 基金项目： | 国家“八六三”计划项目(2009AA110301) |
| 摘 要： | 应用图像处理和模式识别技术,分析高速线阵扫描相机采集的钢轨数字图像,提出鲁棒实时的钢轨表面擦伤检测算法。这种算法首先分析采集图像在垂直方向的投影曲线,提取准确钢轨图像;之后,借鉴人类视觉对比度感知机理,将钢轨灰度图转换为灰度对比图,并基于最大熵原理进行二值化处理,分割出可疑擦伤区域;然后根据经验知识判定钢轨表面的可疑擦伤。实验验证表明:新算法的检测性能高,平均准确率为90.7%,平均漏检率为3.95%;检测速度快,平均检测时间不超过40 ms。 |
| 关 键 词： | 钢轨表面擦伤 检测 对比度感知 最大熵原理 算法 |
Research on Robust Fast Algorithm of Rail Surface Defect Detection |
|
| REN Shengwei,LI Qingyong,XU Guiyang,HAN Qiang,LUO Siwei,FENG Qibo.Research on Robust Fast Algorithm of Rail Surface Defect Detection[J].China Railway Science,2011,32(1). | |
| Authors: | REN Shengwei LI Qingyong XU Guiyang HAN Qiang LUO Siwei FENG Qibo |
| Institution: | REN Shengwei1,2,LI Qingyong3,XU Guiyang2,HAN Qiang1,LUO Siwei3,FENG Qibo1(1.Infrastructure Inspection Research Institute,China Academy of Railway Sciences,Beijing 100081,China,2.School of Science,Beijing Jiaotong University,Beijing 100044,3.School of Computer and Information Technology,China) |
| Abstract: | By applying the advanced technologies of image processing and pattern recognition,analyzing the digital rail image acquired by high speed linear-scanned camera,a robust fast algorithm of rail surface defect detection was proposed.Firstly,the exact rail region was extracted by analyzing the vertical projection of input images.Then the gray contrast image was transformed from the gray rail image utilizing the model of contrast perception of human being,and the suspected defect was segmented through binary pro... |
| Keywords: | Rail surface defect Detection Contrast perception Principle of maximum entropy Algorithm |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |