Visual detection algorithm for rail surface defects based on image sensor

MAO Zheng-chong; WU Feng

doi:10.13873/J.1000-9787(2015)09-0141-04

Chinese

您当前的位置：

首页 >

文章列表页 >

Visual detection algorithm for rail surface defects based on image sensor

更新时间：2025-09-11

- Visual detection algorithm for rail surface defects based on image sensor
- Vol. 34, Issue 9, Pages: 141-144(2015)
- 作者机构：
  
  江南大学物联网工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2015)09-0141-04
  CLC： TP391.41
- Published：2015
- 稿件说明：
移动端阅览
[1]茅正冲,邬锋.基于图像传感器的铁轨表面缺陷视觉检测算法[J].传感器与微系统,2015,34(09):141-144.

MAO Zheng-chong, WU Feng. Visual detection algorithm for rail surface defects based on image sensor[J]. 2015, 34(9): 141-144.
[1]茅正冲,邬锋.基于图像传感器的铁轨表面缺陷视觉检测算法[J].传感器与微系统,2015,34(09):141-144. DOI： 10.13873/J.1000-9787(2015)09-0141-04.

MAO Zheng-chong, WU Feng. Visual detection algorithm for rail surface defects based on image sensor[J]. 2015, 34(9): 141-144. DOI： 10.13873/J.1000-9787(2015)09-0141-04.

摘要

铁轨表面缺陷严重影响铁路系统的运行质量和安全

提出了基于图像传感器的铁轨表面缺陷视觉检测算法

并重点研究了图像增强和自动阈值分割。采用局部对比度测量法增强铁轨图像对比度

使缺陷区域明显突出于背景区域;采用改进的最大类间方差法分割铁轨增强图像

消除了更多的噪声且保持了必要的缺陷信息。实验结果表明:铁轨表面缺陷检测的准确率和检全率分别达到86.1%和91.9%。

Abstract

Rail surface defects impact the riding quality and safety of railway system seriously. Therefore

visual detection algorithm for rail surface defects based on image sensor is proposed

and it focuses on image enhancement and automatic threshold segmentation. Local contrast measurement method is adopted to enhance the contrast of rail images and highlights defects from background notably. Improved maximum between-cluster variance（ Otsu） is adopted to segment rail enhancement images

and it eliminates more noise and keeps the necessary information of defects. Experimental results show that accuracy and recall ratio is 86. 1 % and 91. 9 %

respectively.

关键词

Keywords

references

铁轨表面缺陷的视觉检测与识别算法 [J]. 唐湘娜,王耀南. 计算机工程 . 2013(03)

最大倒数熵/倒数灰度熵多阈值选取 [J]. 吴一全,殷骏,毕硕本. 信号处理 . 2013(02)

一种改进的最大类间方差图像分割法 [J]. 李敏,罗洪艳,郑小林,谭立文,朱文武. 南京理工大学学报 . 2012(02)

基于数字图像处理和特征提取的钢轨表面缺陷识别方法 [J]. 王平,刘泽,王嵬,张广伟,孙秀芳. 现代科学仪器 . 2012(02)

基于灰度迭代阈值脉冲耦合神经网络的图像分割 [J]. 李海燕,张榆锋,施心陵,陈建华. 计算机应用 . 2011(10)

一种二值图像连通区域标记的新方法 [J]. 刘奇琦,龚晓峰. 计算机工程与应用 . 2012(11)

图像处理技术在钢轨表面缺陷检测和分类中的应用 [J]. 官鑫,赵智雅,高晓蓉. 铁路计算机应用 . 2009(06)

基于对比度受限自适应直方图均衡的乳腺图像增强 [J]. 刘轩,刘佳宾. 计算机工程与应用 . 2008(10)

An Adaptive Histogram Equalization Algorithm on the Image Gray Level Mapping [J] . Youlian Zhu,Cheng Huang. Physics Procedia . 2012

Automatic thresholding for defect detection [J] . Hui-Fuang Ng. Pattern Recognition Letters . 2006 (14)

Views

216

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Small object detection on highway based on unmanned aerial vehicle image sensor

Cricket vision control system based on double-loop PID algorithm and Otsu method

New algorithm for X-ray image enhancement

Borehole image adaptive enhancement based on homomorphic filtering and Curvelet transform

Design of computer vision surveillance system for tower cranes

Related Author

ZHU Wenyao

LIU Songrong

CHEN Xiaoqiang

WANG Li

GONG Cheng

GONG Ming

XU Yunji

HU Wei-wei

Related Institution

School of Mathematics and Computer Science,Lishui University

Zhejiang Communications Investment Expressway Operation and Management Co Ltd

College of Information and Communication Engineering,Hainan University

College of Mechanical and Electrical Engineering,Nanchang University

Electrical and Information Engineering Branch,Institute of Technology,East China Jiaotong University

⁰