基于扩展Haar特征和DBSCAN的钢轨识别算法

doi:10.11896/JsJkx.200100008

计算机科学 ›› 2020, Vol. 47 ›› Issue (6A): 153-156.doi: 10.11896/JsJkx.200100008

• 计算机图形学 & 多媒体 • 上一篇下一篇

基于扩展Haar特征和DBSCAN的钢轨识别算法

罗晋楠, 张济民

同济大学铁道与城市轨道交通研究院上海 201804

发布日期:2020-07-07
通讯作者: 张济民(zJm397a@163.com)
作者简介:tJlJn@tongJi.edu.cn

Rail Area Extraction Using Extended Haar-like Features and DBSCAN Clustering

LUO Jin-nan and ZHANG Ji-min

Institute of Rail Transit,TongJi University,Shanghai 201804,China

Published:2020-07-07
About author:LUO Jin-nan, postgraduate.His main research interests include rolling stock intelligent control and active safety protection.
ZHANG Ji-min, born in 1969, Ph.D, professor.His main research interests include rolling stock dynamics, mechatronic system design and rolling stock intelligent control.

摘要/Abstract

摘要： 障碍物对列车的正常运营构成了极大的安全隐患,钢轨识别是实现障碍物检测的关键步骤。钢轨识别算法需要能够快速有效地检测列车前方钢轨的位置,同时不能占用过多的计算资源,影响障碍物检测程序的运行速度。为解决上述问题,文中提出一种基于扩展Haar特征提取和DBSCAN密度聚类的钢轨识别算法。首先通过仿射变换、池化、灰度均衡化、边缘检测等算法对图像进行预处理,然后基于扩展Haar特征提取图像中钢轨的特征点,最后利用DBSCAN算法对特征点进行聚类,提取出有效的特征数据点进行曲线拟合,从而识别钢轨的位置。通过车载实验结果表明,该方法能够在列车运行过程中有效检测到钢轨的位置,满足多场景、多工况的实际使用需求。

关键词: DBSCAN聚类, 钢轨识别, 轨道交通, 扩展haar特征, 障碍物检测

Abstract: Obstacle is a potential threat to the normal operation of trains.Rail area extraction is a key step in the process of using the train’s forward-looking camera to detect obstacles.Rail area extraction algorithm needs to be able to quickly and effectively detect the position of the rail while not occupying too much computing resources to keep the normal calculation speed of the obstacle recognition algorithm.This paper proposes a rail area extraction algorithm based on extended Haar-like feature extraction and DBSCAN density clustering.Firstly,the image is preprocessed by algorithms such as affine transformation,pooling,gray level equalization,and edge detection.Then the feature points of the rail are extracted based on multiple extended Haar-like features.Finally,the DBSCAN algorithm is used to extract valid feature data points and curve fitting is performed through these points.The experimental result shows that the algorithm can effectively detect the position of the rail area during the running of the train,and meet the practical needs of multiple scenarios and conditions

Key words: DBSCAN clustering, Extended Haar-like feature, ObJect detection, Rail area extraction, Rail tranist

中图分类号:

U298

罗晋楠, 张济民. 基于扩展Haar特征和DBSCAN的钢轨识别算法[J]. 计算机科学, 2020, 47(6A): 153-156. https://doi.org/10.11896/JsJkx.200100008

LUO Jin-nan and ZHANG Ji-min. Rail Area Extraction Using Extended Haar-like Features and DBSCAN Clustering[J]. Computer Science, 2020, 47(6A): 153-156. https://doi.org/10.11896/JsJkx.200100008

参考文献

[1] KAZANSKIY N L,POPOV S B.Integrated design technology for computer vision systems in railway transportation.Pattern Recognition & Image Analysis,2015,25(2):215-219.
[2] IEC 62267－2009,Railway applications－Automated urbanguided transport (AUGT) - Safety requirements.Geneva,Switzerland:International Electrotechnical Commission,2009.
[3] WANG Z,WU X,YU G,et al.Efficient rail area detection using convolutional neural network.IEEE Access,2018:1-1.
[4] ESPINO J C,STANCIULESCU B.Rail extraction technique using gradient information and a priori shape model//Intelligent Transportation Systems (ITSC),2012 15th International IEEE Conference on.IEEE,2012.
[5] WANG Z,CAI B,CHUNXIAO J,et al.Geometry constraints-based visual rail track extraction//2016 12th World Congress on Intelligent Control and Automation (WCICA).IEEE,2016.
[6] WANG Y Z.Design and Implementation of an algorithm to recognize the rail ahead of the train.ZheJiang:ZheJiang University,2017.
[7] SELVER M A,ER E,BELENLIOGLU B,et al.Camera based driver support system for rail extraction using 2-D Gabor wavelet decompositions and morphological analysis//2016 IEEE International Conference on Intelligent Rail Transportation (ICIRT).IEEE,2016.
[8] YUAN C L,XIONG Z L,ZHOU X H.Study of infrared image edge detection based on Sobel operator .Laser Infrared,2009(1):85-87.
[9] VIOLA P A,JONES M J.Rapid ObJect Detection using a Boos-ted Cascade of Simple Features//Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR 2001).IEEE,2001.
[10] LIENHART R,MAYDT J.An Extended Set of Haar-like Features for Rapid ObJect Detection//2002 International Conference on Image Processing.IEEE,2002.
[11] SANDER J,ESTER M,KRIEGEL H P,et al.Density-Based Clustering in Spatial Databases:The Algorithm GDBSCAN and Its Applications.Data Mining and Knowledge Discovery,1998,2(2):169-194.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于扩展Haar特征和DBSCAN的钢轨识别算法

Rail Area Extraction Using Extended Haar-like Features and DBSCAN Clustering

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

Metrics

本文评价

推荐阅读 0

[1]	张建新, 刘弘, 李焱. 一种面向人群疏散的高效分组方法 Efficient Grouping Method for Crowd Evacuation 计算机科学, 2019, 46(6): 231-238. https://doi.org/10.11896/j.issn.1002-137X.2019.06.035
[2]	刘康,李舟军,张小明. 基于Web数据的实证研究：城市轨道交通对住宅价格的时空效应分析 Empirical Research Based on Web Data:An Analysis on Spatio-temporal Effect of City Rail Transit on Residential House Prices 计算机科学, 2015, 42(9): 199-203. https://doi.org/10.11896/j.issn.1002-137X.2015.09.038
[3]	汤一平,姜荣剑,林璐璐. 基于主动式全景视觉的移动机器人障碍物检测 Obstacle Detection Method for Mobile Robot Using Active Omnidirectional Vision Sensor 计算机科学, 2015, 42(3): 284-288. https://doi.org/10.11896/j.issn.1002-137X.2015.03.059
[4]	李少伟,陈永生. 城市轨道交通客流预测算法设计与仿真 Design and Simulation of Passenger Flow Forecast Algorithm for Urban Rail Transit 计算机科学, 2014, 41(2): 276-279.
[5]	. 基于遗传算法的轨道交通线路排班优化研究计算机科学, 2007, 34(3): 211-212.