铁轨数据提取和轨道建模的机载激光雷达方法
|
摘要
机载激光雷达数据已经广泛应用于铁路的勘测工作,针对机载激光雷达采样密度低所引发的铁轨点提取精度低、建模难度大的问题,提出一种从机载激光雷达数据中自动检测铁轨和轨道建模的新方法。首先通过铁路区域特有的空间分布特征提取铁轨上方的悬链线,进而实现铁路区域分割;然后利用alpha-shapes算法检测轨道点;最后构建铁轨参数模型,采用基于主元分析的点云配准方法将检测出的铁轨点与铁轨参数模型进行匹配,实现轨道的整体建模。应用某铁路站点的机载激光雷达数据进行试验,实验表明:该方法可以实现铁轨点的高精度提取和铁轨模型的快速拟合;铁轨点提取的准确度可以达到97%,完整度可以达到94%以上。
The airborne LiDAR data has been widely used in railway survey work.The problem of low accuracy and difficult modeling of rail point extraction caused by low sampling density of airborne LiDAR is proposed.This paper presents a new method for automatic detection of orbit and orbit modeling from airborne LiDAR data.Firstly,the catenary line above the rail is extracted by using the unique spatial distribution characteristics of the railway area to realize the division of the railway area.Then use the alpha-shapes algorithm to detect orbit points.Finally,the rail parameter model is constructed,and the detected point of the rail is matched with the parametric model by the point cloud registration method based on principal component analysis to realize the overall modeling of the orbit.The airborne LiDAR data of a railway station is used to test.The experiment shows that the method can achieve high-precision extraction of rail points and rapid fitting of rail models.The accuracy of rail point extraction can reach 97%,and the integrity can reach more than 94%.
The airborne LiDAR data has been widely used in railway survey work.The problem of low accuracy and difficult modeling of rail point extraction caused by low sampling density of airborne LiDAR is proposed.This paper presents a new method for automatic detection of orbit and orbit modeling from airborne LiDAR data.Firstly,the catenary line above the rail is extracted by using the unique spatial distribution characteristics of the railway area to realize the division of the railway area.Then use the alpha-shapes algorithm to detect orbit points.Finally,the rail parameter model is constructed,and the detected point of the rail is matched with the parametric model by the point cloud registration method based on principal component analysis to realize the overall modeling of the orbit.The airborne LiDAR data of a railway station is used to test.The experiment shows that the method can achieve high-precision extraction of rail points and rapid fitting of rail models.The accuracy of rail point extraction can reach 97%,and the integrity can reach more than 94%.
引文
[1] 王平华,习晓环,王成,等.机载激光雷达数据中电力线的快速提取[J].测绘科学,2017,42(2):154-158.
[2] 余洁,穆超,冯延明,等.LiDAR点云数据中电力线的提取方法研究[J].武汉大学学报(信息科学版),2011,36(11):1275-1279.
[3] 陈驰,麦晓明,宋爽,等.机载激光点云数据中电力线自动提取方法[J].武汉大学学报(信息科学版),2015,40(12):1600-1605.
[4] STEIN D,SPINDLER M,LAUER M.Model-based rail detection in mobile laser scanning data[C]//Intelligent Vehicles Symposium.[S.l]:IEEE:654-661.
[5] Elberink S,Khoshelham K.Automatic extraction of railroad centerlines from mobile laser scanning data[J].Remote Sensing,2015,7(5):5565-5583.
[6] 方莉娜,杨必胜.车载激光扫描数据的结构化道路自动提取方法[J].测绘学报,2013(2):260-267.
[7] 袁鹏飞,黄荣刚,胡平波,等.基于多光谱LiDAR数据的道路中心线提取[J].地球信息科学学报,2018,20(4):452-461.
[8] 杨必胜,董震,魏征,等.从车载激光扫描数据中提取复杂建筑物立面的方法[J].测绘学报,2013,42(3):411-417.
[9] 于海洋,牛峰明,罗玲,等.一种综合机载LiDAR与高分辨率航空影像的铁路轨道提取方法[J].测绘工程,2016,25(5):42-46.
[10] OUDE ELBERINK S,KHOSHELHAM K,ARASTOUNIA M,et al.Rail track detection and modelling in mobile laser scanner data[J].ISPRS Annals of the Photogrammetry,Remote Sensing and Spatial Information Sciences,2013,II-5/W2(1):223-228.
[11] YANG B,FANG L.Automated extraction of 3-D railway tracks from mobile laser scanning point clouds[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2015,7(12):4750-4761.
[12] YANG B,FANG L,LI J.Semi-automated extraction and delineation of 3D roads of street scene from mobile laser scanning point clouds[J].Isprs Journal of Photogrammetry & Remote Sensing,2013,79(5):80-93.
[13] 姚顽强,郑俊良,陈鹏,等.八叉树索引的三维点云数据压缩算法[J].测绘科学,2016,41(7):18-22.
[2] 余洁,穆超,冯延明,等.LiDAR点云数据中电力线的提取方法研究[J].武汉大学学报(信息科学版),2011,36(11):1275-1279.
[3] 陈驰,麦晓明,宋爽,等.机载激光点云数据中电力线自动提取方法[J].武汉大学学报(信息科学版),2015,40(12):1600-1605.
[4] STEIN D,SPINDLER M,LAUER M.Model-based rail detection in mobile laser scanning data[C]//Intelligent Vehicles Symposium.[S.l]:IEEE:654-661.
[5] Elberink S,Khoshelham K.Automatic extraction of railroad centerlines from mobile laser scanning data[J].Remote Sensing,2015,7(5):5565-5583.
[6] 方莉娜,杨必胜.车载激光扫描数据的结构化道路自动提取方法[J].测绘学报,2013(2):260-267.
[7] 袁鹏飞,黄荣刚,胡平波,等.基于多光谱LiDAR数据的道路中心线提取[J].地球信息科学学报,2018,20(4):452-461.
[8] 杨必胜,董震,魏征,等.从车载激光扫描数据中提取复杂建筑物立面的方法[J].测绘学报,2013,42(3):411-417.
[9] 于海洋,牛峰明,罗玲,等.一种综合机载LiDAR与高分辨率航空影像的铁路轨道提取方法[J].测绘工程,2016,25(5):42-46.
[10] OUDE ELBERINK S,KHOSHELHAM K,ARASTOUNIA M,et al.Rail track detection and modelling in mobile laser scanner data[J].ISPRS Annals of the Photogrammetry,Remote Sensing and Spatial Information Sciences,2013,II-5/W2(1):223-228.
[11] YANG B,FANG L.Automated extraction of 3-D railway tracks from mobile laser scanning point clouds[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2015,7(12):4750-4761.
[12] YANG B,FANG L,LI J.Semi-automated extraction and delineation of 3D roads of street scene from mobile laser scanning point clouds[J].Isprs Journal of Photogrammetry & Remote Sensing,2013,79(5):80-93.
[13] 姚顽强,郑俊良,陈鹏,等.八叉树索引的三维点云数据压缩算法[J].测绘科学,2016,41(7):18-22.