车载激光点云中道路路灯提取方法
|
摘要
针对道路环境中路灯的提取,提出一种车载激光点云中路灯提取方法。该方法首先对原始点云建立三维格网索引,分析灯杆在二维投影平面中的圆弧形态以及在三维空间中的柱状形态,提取杆目标;然后根据树木与路灯上部点云三维形态的差异去除树木,提取候选路灯;最后,建立路灯灯头模板库,通过模板匹配精确去除交通信号灯和交通标志牌等,实现路灯的准确提取。实验证明,该方法可以有效提取实际道路环境中的不同路灯,提取准确率和召回率分别达到94.01%和89.47%,且不需要辅助数据,具有较强的适用性。数据处理效率较现有同类方法有大幅提高。
Aiming at the extraction of streetlamps in road environment,an extraction method of streetlamps in mobile laser scanning point cloud was proposed in this paper.Firstly,a 3 Dgrid index was built on the original point cloud,and the pole object was extracted by analyzing the arc projection pattern of the pole in the 2 Dplane and the column shape in the 3 Dspace.Then,according to the differences in the 3 Dshape of the point clouds above the trees and streetlamps,the trees were removed and the candidate streetlamps were extracted.Finally,the accurate extraction of streetlamps was realized by removing traffic lights and traffic signs through precise template matching with the established template library.Experiments show that the proposed method can effectively extract different streetlamps in actual road scenes and has strong applicability because the accuracy rate and recall rate of the extraction re-sults can reach 94.01%and 89.47%respectively and no auxiliary data is required.The efficiency of data processing is significantly higher than that of existing methods.
Aiming at the extraction of streetlamps in road environment,an extraction method of streetlamps in mobile laser scanning point cloud was proposed in this paper.Firstly,a 3 Dgrid index was built on the original point cloud,and the pole object was extracted by analyzing the arc projection pattern of the pole in the 2 Dplane and the column shape in the 3 Dspace.Then,according to the differences in the 3 Dshape of the point clouds above the trees and streetlamps,the trees were removed and the candidate streetlamps were extracted.Finally,the accurate extraction of streetlamps was realized by removing traffic lights and traffic signs through precise template matching with the established template library.Experiments show that the proposed method can effectively extract different streetlamps in actual road scenes and has strong applicability because the accuracy rate and recall rate of the extraction re-sults can reach 94.01%and 89.47%respectively and no auxiliary data is required.The efficiency of data processing is significantly higher than that of existing methods.
引文
[1]何东钢,何中平,刘长军.城市路灯管理GIS的设计与应用[J].长春大学学报,2008,18(10):38-41.HE Donggang,HE Zhongping,LIU Changjun.The design and application of urban street lamp management GIS[J].Journal of Changchun University,2008,18(10):38-41.
[2]卢秀山,李清泉,冯文灏,等.车载式城市信息采集与三维建模系统[J].武汉大学学报(工学版),2003,36(3):76-80.LU Xiushan,LI Qingquan,FENG Wenhao,et al.Vehicle-borne urban information acquisition and 3D modeling system[J].Engineering Journal of Wuhan University,2003,36(3):76-80..
[3]EL-HALAWANY S,MOUSSA A,LICHTI D D,et al.Detection of road curb from mobile terrestrial laser scanner point cloud[C]//Proceedings of the ISPRS Workshop on Laser Scanning,Calgary,AB,Canada,Aug.29-31.2011.
[4]刘如飞,田茂义,许君一.车载激光扫描数据中高速公路路面点滤波[J].武汉大学学报(信息科学版),2015,40(6):751-755.LIU Rufei,TIAN Maoyi,XU Junyi.Expressway road surface point filtering for mobile laser scanning data[J].Geomatics and Information Science of Wuhan University,2015,40(6):751-755.
[5]魏征,杨必胜,李清泉.车载激光扫描点云中建筑物边界的快速提取[J].遥感学报,2012,16(2):286-296.WEI Zheng,YANG Bisheng,LI Qingquan.Automated extraction of building footprints from mobile LIDAR point clouds[J].Journal of Remote Sensing,2012,16(2):286-296.
[6]CABO C,ORDOEZ C,GARCA-CORTS S,et al.An algorithm for automatic detection of pole-like street furniture objects from mobile laser scanner point clouds[J].ISPRS Journal of Photogrammetry&Remote Sensing,2014,87(1):47-56.
[7]RODRGUEZ-CUENCA B,GARCA-CORTS S,ORDOEZ C,et al.Automatic detection and classification of pole-like objects in urban point cloud data using an anomaly detection algorithm[J].Remote Sensing,2015,7(10):12680-12703.
[8]GUAN H,YU Y,LI J,et al.Pole-like road object detection in mobile LiDAR data via supervoxel and bag-of-contextual-visual-words representation[J].IEEE Geoscience&Remote Sensing Letters,2016,13(4):520-524.
[9]LI D,OUDE ELBERINK S.Optimizing detection of road furniture(pole-like object)in Mobile Laser Scanner data[J/OL].ISPRS Annals of the Photogrammetry,Romote Sensing and Spatial Information Sciences,2013:276020296.
[10]ZAI D,CHEN Y,LI J,et al.Inventory of 3Dstreet lighting poles using mobile laser scanning point clouds[C]//Geoscience&Remote Sensing Symposium.IEEE,2015:573-576.
[11]LUO H,WANG C,WANG H,et al.Exploiting location information to detect light pole in mobile LiDAR point clouds[C]//Geoscience and Remote Sensing Symposium.IEEE,2016:453-456.
[12]YAN W Y,MORSY S,SHAKER A,et al.Automatic extraction of highway light poles and towers from mobile LiDAR data[J].Optics&Laser Technology,2016,77:162-168.
[13]YANG B,DONG Z,ZHAO G,et al.Hierarchical extraction of urban objects from mobile laser scanning data[J].Isprs Journal of Photogrammetry&Remote Sensing,2015,99:45-57.
[14]董震,杨必胜.车载激光扫描数据中多类目标的层次化提取方法[J].测绘学报,2015,44(9):980-987.DONG Zhen,YANG Bisheng.Hierarchical extraction of multiple objects from mobile laser scanning data[J].Acta Geodaetica et Cartographica Sinica,2015,44(9):980-987.
[15]张西童,刘会云,李永强,等.车载LiDAR场景中路灯的提取与识别[J].测绘工程,2016,25(9):50-54.ZHANG Xitong,LIU Huiyun,LI Yongqiang,et al.Streetlamp extraction and identification from mobile LiDAR point cloud scenes[J].Engineering of Surveying and Mapping,2016,25(9):50-54.
[16]李永强,董亚涵,张西童,等.车载LiDAR点云路灯提取方法[J].测绘学报,2018,47(2):247-259.LI Yongqiang,DONG Yahan,ZHANG Xitong,et al.Point cloud information extraction for streetlights with vehicle-borne LiDAR[J].Acta Geodaetica et Cartographica Sinica,2018,47(2):247-259.
[17]中华人民共和国行业标准.CJJ45-2006,城市道路照明设计标准[S].
[18]卢秀山,刘如飞,田茂义,等.利用改进的数学形态法进行车载激光点云地面滤波[J].武汉大学学报(信息科学版),2014,39(5):514-519.LU Xiushan,LIU Rufei,TIAN Maoyi,et al.Ground filtering of vehicle-borne laser point cloud based on adaptive mathematical morphology[J].Geomatics and Information Science of Wuhan University,2014,39(5):514-519.
[19]CHEN C S,HUNG Y P,CHENG J B.RANSAC-based DARCES:A new approach to fast automatic registration of partially overlapping range images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,21(11):1229-1234.
[20]中华人民共和国城镇建设行业标准.CJ/T 3016-1998,高杆照明设施技术条件[S].
[2]卢秀山,李清泉,冯文灏,等.车载式城市信息采集与三维建模系统[J].武汉大学学报(工学版),2003,36(3):76-80.LU Xiushan,LI Qingquan,FENG Wenhao,et al.Vehicle-borne urban information acquisition and 3D modeling system[J].Engineering Journal of Wuhan University,2003,36(3):76-80..
[3]EL-HALAWANY S,MOUSSA A,LICHTI D D,et al.Detection of road curb from mobile terrestrial laser scanner point cloud[C]//Proceedings of the ISPRS Workshop on Laser Scanning,Calgary,AB,Canada,Aug.29-31.2011.
[4]刘如飞,田茂义,许君一.车载激光扫描数据中高速公路路面点滤波[J].武汉大学学报(信息科学版),2015,40(6):751-755.LIU Rufei,TIAN Maoyi,XU Junyi.Expressway road surface point filtering for mobile laser scanning data[J].Geomatics and Information Science of Wuhan University,2015,40(6):751-755.
[5]魏征,杨必胜,李清泉.车载激光扫描点云中建筑物边界的快速提取[J].遥感学报,2012,16(2):286-296.WEI Zheng,YANG Bisheng,LI Qingquan.Automated extraction of building footprints from mobile LIDAR point clouds[J].Journal of Remote Sensing,2012,16(2):286-296.
[6]CABO C,ORDOEZ C,GARCA-CORTS S,et al.An algorithm for automatic detection of pole-like street furniture objects from mobile laser scanner point clouds[J].ISPRS Journal of Photogrammetry&Remote Sensing,2014,87(1):47-56.
[7]RODRGUEZ-CUENCA B,GARCA-CORTS S,ORDOEZ C,et al.Automatic detection and classification of pole-like objects in urban point cloud data using an anomaly detection algorithm[J].Remote Sensing,2015,7(10):12680-12703.
[8]GUAN H,YU Y,LI J,et al.Pole-like road object detection in mobile LiDAR data via supervoxel and bag-of-contextual-visual-words representation[J].IEEE Geoscience&Remote Sensing Letters,2016,13(4):520-524.
[9]LI D,OUDE ELBERINK S.Optimizing detection of road furniture(pole-like object)in Mobile Laser Scanner data[J/OL].ISPRS Annals of the Photogrammetry,Romote Sensing and Spatial Information Sciences,2013:276020296.
[10]ZAI D,CHEN Y,LI J,et al.Inventory of 3Dstreet lighting poles using mobile laser scanning point clouds[C]//Geoscience&Remote Sensing Symposium.IEEE,2015:573-576.
[11]LUO H,WANG C,WANG H,et al.Exploiting location information to detect light pole in mobile LiDAR point clouds[C]//Geoscience and Remote Sensing Symposium.IEEE,2016:453-456.
[12]YAN W Y,MORSY S,SHAKER A,et al.Automatic extraction of highway light poles and towers from mobile LiDAR data[J].Optics&Laser Technology,2016,77:162-168.
[13]YANG B,DONG Z,ZHAO G,et al.Hierarchical extraction of urban objects from mobile laser scanning data[J].Isprs Journal of Photogrammetry&Remote Sensing,2015,99:45-57.
[14]董震,杨必胜.车载激光扫描数据中多类目标的层次化提取方法[J].测绘学报,2015,44(9):980-987.DONG Zhen,YANG Bisheng.Hierarchical extraction of multiple objects from mobile laser scanning data[J].Acta Geodaetica et Cartographica Sinica,2015,44(9):980-987.
[15]张西童,刘会云,李永强,等.车载LiDAR场景中路灯的提取与识别[J].测绘工程,2016,25(9):50-54.ZHANG Xitong,LIU Huiyun,LI Yongqiang,et al.Streetlamp extraction and identification from mobile LiDAR point cloud scenes[J].Engineering of Surveying and Mapping,2016,25(9):50-54.
[16]李永强,董亚涵,张西童,等.车载LiDAR点云路灯提取方法[J].测绘学报,2018,47(2):247-259.LI Yongqiang,DONG Yahan,ZHANG Xitong,et al.Point cloud information extraction for streetlights with vehicle-borne LiDAR[J].Acta Geodaetica et Cartographica Sinica,2018,47(2):247-259.
[17]中华人民共和国行业标准.CJJ45-2006,城市道路照明设计标准[S].
[18]卢秀山,刘如飞,田茂义,等.利用改进的数学形态法进行车载激光点云地面滤波[J].武汉大学学报(信息科学版),2014,39(5):514-519.LU Xiushan,LIU Rufei,TIAN Maoyi,et al.Ground filtering of vehicle-borne laser point cloud based on adaptive mathematical morphology[J].Geomatics and Information Science of Wuhan University,2014,39(5):514-519.
[19]CHEN C S,HUNG Y P,CHENG J B.RANSAC-based DARCES:A new approach to fast automatic registration of partially overlapping range images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,21(11):1229-1234.
[20]中华人民共和国城镇建设行业标准.CJ/T 3016-1998,高杆照明设施技术条件[S].