基于车载LiDAR点云联合特征的道路边界提取研究
|
摘要
针对基于车载LiDAR点云数据的道路边界提取存在的问题,该文提出一种基于联合特征且能适应多种道路环境的道路边界提取方法。首先依据移动测量系统的航迹,按照设定宽度对道路数据进行分段,排除道路外侧无用数据;再对每段数据采用布料模拟滤波(CSF)算法分离地面点和非地面点,通过强度中值滤波去除地面点的椒盐噪声;然后计算点云局部邻域高差梯度和回波强度梯度构成的联合特征,依据设置阈值提取道路边界;最后通过欧氏距离聚类剔除部分非道路边缘点,细化道路边界,合并各段道路边界点云,得到完整的道路边界。选用代表性的城区道路、高速公路、乡村道路3种实验环境,验证了算法的鲁棒性。该研究对于扩展车载LiDAR在道路场景中的应用具有重要价值。
Aiming at the problems of multiple environmental road boundary extraction based on vehicle-borne mobile LiDAR point cloud data,a novel algorithm of road edge extraction adapted to various road environments was proposed in this paper.The principle of this algorithm is described as follows:firstly,according to the track of the mobile measurement system,the road data is segmented based on a certain width,and the peripheral data from the road are deleted to improve the efficiency of data processing.Secondly,cloth simulation filtering(CSF)algorithm is used to separate the surface points from the ground points,and the ground points are separated by intensity median filtering to remove the salt and pepper noise.Then,the conjunction feature of the local neighborhood elevation gradient and the echo intensity gradient of the point cloud is calculated,and the threshold is set up to extract the road edge.Finally,the Euclidean distance clustering is used to exclude some non-road edge points,refine the road sideline and merge the obtained road edges to get the complete road boundary.Experimental verification of the algorithm is carried out in three experimental environments of urban streets,highways and rural roads.The results show that the algorithm can extract various road boundaries effectively.The research is of great value to the application of the extended vehicle-borne LiDAR in the road scene.
Aiming at the problems of multiple environmental road boundary extraction based on vehicle-borne mobile LiDAR point cloud data,a novel algorithm of road edge extraction adapted to various road environments was proposed in this paper.The principle of this algorithm is described as follows:firstly,according to the track of the mobile measurement system,the road data is segmented based on a certain width,and the peripheral data from the road are deleted to improve the efficiency of data processing.Secondly,cloth simulation filtering(CSF)algorithm is used to separate the surface points from the ground points,and the ground points are separated by intensity median filtering to remove the salt and pepper noise.Then,the conjunction feature of the local neighborhood elevation gradient and the echo intensity gradient of the point cloud is calculated,and the threshold is set up to extract the road edge.Finally,the Euclidean distance clustering is used to exclude some non-road edge points,refine the road sideline and merge the obtained road edges to get the complete road boundary.Experimental verification of the algorithm is carried out in three experimental environments of urban streets,highways and rural roads.The results show that the algorithm can extract various road boundaries effectively.The research is of great value to the application of the extended vehicle-borne LiDAR in the road scene.
引文
[1] PUENTER I,GONZLEZ-JORGE H,MARTNEZ-SNCHEZ J,et al.Automatic detection of road tunnel luminaires using a mobile LiDAR system[J].Measurement,2014,47(1):569-575.
[2] TANG L,YANG X,DONG Z,et al.CLRIC:Collecting lanebased road information via crowdsourcing[J].IEEE Transactions on Intelligent Transportation Systems,2016,17(9):2552-2562.
[3] YANG B,DONG Z,LIU Y,et al.Computing multiple aggregation levels and contextual features for road facilities recognition using mobile laser scanning data[J].ISPRS Journal of Photogrammetry&Remote Sensing,2017,126:180-194.
[4] CHEN Y,ZHAO H J,SHIBASAKI R.A mobile system combining laster scanners and cameras for urban spatial objects extraction[A].Proceeding of the Sixth International Conference on Machine Learning and Cybernetics[C].2007.
[5] BARBER D,MILLS J,SMITH V S.Geometric validation of a ground base mobile laster scanning system[J].ISPRS Journal of Photogrammetry&Remote Sensing,2008,63(1):128-141.
[6]王果,崔希民,袁德宝,等.车载激光点云邻域比较的道路边线提取方法[J].测绘通报,2012,58(9):55-57.
[7]田茂义,李鹏飞,俞家勇,等.格网邻域滤波在车载激光点云道路边线提取中的方法研究[J].测绘与空间地理信息,2016,39(5):8-10.
[8] HERNNDEZ J,MARCOTEGUI B.Filtering of artifacts and pavement segmentation from mobile LiDAR data[A].ISPRS Workshop Laser Scanning[C].2009.
[9]李永强,王文越,郑艳慧,等.基于车载LiDAR数据的道路边界精细提取[J].河南理工大学学报(自然科学版),2014,34(4):458-462.
[10]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,2013,57(2):260-267.
[11]刘如飞,卢秀山,岳国伟,等.一种车载激光点云数据中道路自动提取方法[J].武汉大学学报(信息科学版),2017,61(2):250-256.
[12]李峰,崔希民,刘小阳,等.机载LiDAR点云提取城市道路网的半自动方法[J].测绘科学,2015,40(2):88-92.
[13]闫兆进,孟丽娜.基于直线特征检测的道路边线自动提取方法[J].测绘工程,2017,24(3):42-45.
[14]都伟冰,王双亭,王春来.基于机载LiDAR粗糙度指数和回波强度的道路提取[J].测绘科学技术学报,2013,30(1):63-67.
[15] KUMAR P,MCELHINNEY C P,LEWIS P,et al.Automated road markings extraction from mobile laser scanning data[J].International Journal of Applied Earth Observation and Geoinformation,2014,32(1):125-137.
[16]罗海峰,方莉娜,陈崇成.车载激光扫描数据路坎点云提取方法[J].地球信息科学学报,2017,22(7):861-871.
[17]张朋动,邓敏,赵玲,等.集成不同类型特征的城市道路选取方法研究[J].地理与地理信息科学,2011,27(5):16-20.
[18]张西童.车载LiDAR点云中路灯与行道树信息提取研究[D].焦作:河南理工大学,2017.
[19]隋立春,张熠斌,柳艳,等.基于改进的数学形态学算法的LiDAR点云数据滤波[J].测绘学报,2010,54(4):390-396.
[20]赵明波,何峻,田军生,等.基于改进的渐进多尺度数学形态学的激光雷达数据滤波方法[J].光学学报,2013,33(3):292-301.
[21]陈琳,范湘涛,杜小平.基于高程统计的机载LiDAR点云三角网渐进滤波方法[J].遥感信息,2014,29(3):19-23.
[22] ZHANG W,QI J,WAN P,et al.An easy-to-use airborne LiDAR data filtering method based on cloth simulation[J].Remote Sensing,2016,6(8):501.
[23]赖旭东,万幼川.一种针对激光雷达强度图像的滤波算法研究[J].武汉大学学报(信息科学版),2005,49(2):158-160.
[24]李益.基于光谱/空间联合特征的遥感影像地物提取技术研究[D].郑州:解放军信息工程大学,2012.
[25]何胜,柳益君,叶飞跃,等.基于F-measure的网络布局评测算法实现[J].计算机工程,2015,41(7):129-132.
[2] TANG L,YANG X,DONG Z,et al.CLRIC:Collecting lanebased road information via crowdsourcing[J].IEEE Transactions on Intelligent Transportation Systems,2016,17(9):2552-2562.
[3] YANG B,DONG Z,LIU Y,et al.Computing multiple aggregation levels and contextual features for road facilities recognition using mobile laser scanning data[J].ISPRS Journal of Photogrammetry&Remote Sensing,2017,126:180-194.
[4] CHEN Y,ZHAO H J,SHIBASAKI R.A mobile system combining laster scanners and cameras for urban spatial objects extraction[A].Proceeding of the Sixth International Conference on Machine Learning and Cybernetics[C].2007.
[5] BARBER D,MILLS J,SMITH V S.Geometric validation of a ground base mobile laster scanning system[J].ISPRS Journal of Photogrammetry&Remote Sensing,2008,63(1):128-141.
[6]王果,崔希民,袁德宝,等.车载激光点云邻域比较的道路边线提取方法[J].测绘通报,2012,58(9):55-57.
[7]田茂义,李鹏飞,俞家勇,等.格网邻域滤波在车载激光点云道路边线提取中的方法研究[J].测绘与空间地理信息,2016,39(5):8-10.
[8] HERNNDEZ J,MARCOTEGUI B.Filtering of artifacts and pavement segmentation from mobile LiDAR data[A].ISPRS Workshop Laser Scanning[C].2009.
[9]李永强,王文越,郑艳慧,等.基于车载LiDAR数据的道路边界精细提取[J].河南理工大学学报(自然科学版),2014,34(4):458-462.
[10]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,2013,57(2):260-267.
[11]刘如飞,卢秀山,岳国伟,等.一种车载激光点云数据中道路自动提取方法[J].武汉大学学报(信息科学版),2017,61(2):250-256.
[12]李峰,崔希民,刘小阳,等.机载LiDAR点云提取城市道路网的半自动方法[J].测绘科学,2015,40(2):88-92.
[13]闫兆进,孟丽娜.基于直线特征检测的道路边线自动提取方法[J].测绘工程,2017,24(3):42-45.
[14]都伟冰,王双亭,王春来.基于机载LiDAR粗糙度指数和回波强度的道路提取[J].测绘科学技术学报,2013,30(1):63-67.
[15] KUMAR P,MCELHINNEY C P,LEWIS P,et al.Automated road markings extraction from mobile laser scanning data[J].International Journal of Applied Earth Observation and Geoinformation,2014,32(1):125-137.
[16]罗海峰,方莉娜,陈崇成.车载激光扫描数据路坎点云提取方法[J].地球信息科学学报,2017,22(7):861-871.
[17]张朋动,邓敏,赵玲,等.集成不同类型特征的城市道路选取方法研究[J].地理与地理信息科学,2011,27(5):16-20.
[18]张西童.车载LiDAR点云中路灯与行道树信息提取研究[D].焦作:河南理工大学,2017.
[19]隋立春,张熠斌,柳艳,等.基于改进的数学形态学算法的LiDAR点云数据滤波[J].测绘学报,2010,54(4):390-396.
[20]赵明波,何峻,田军生,等.基于改进的渐进多尺度数学形态学的激光雷达数据滤波方法[J].光学学报,2013,33(3):292-301.
[21]陈琳,范湘涛,杜小平.基于高程统计的机载LiDAR点云三角网渐进滤波方法[J].遥感信息,2014,29(3):19-23.
[22] ZHANG W,QI J,WAN P,et al.An easy-to-use airborne LiDAR data filtering method based on cloth simulation[J].Remote Sensing,2016,6(8):501.
[23]赖旭东,万幼川.一种针对激光雷达强度图像的滤波算法研究[J].武汉大学学报(信息科学版),2005,49(2):158-160.
[24]李益.基于光谱/空间联合特征的遥感影像地物提取技术研究[D].郑州:解放军信息工程大学,2012.
[25]何胜,柳益君,叶飞跃,等.基于F-measure的网络布局评测算法实现[J].计算机工程,2015,41(7):129-132.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |