车载激光点云道路边界提取的Snake方法

doi:10.11947/j.AGCS.2020.20190370

测绘学报 ›› 2020, Vol. 49 ›› Issue (11): 1438-1450.doi: 10.11947/j.AGCS.2020.20190370

车载激光点云道路边界提取的Snake方法

方莉娜^1,2,3, 卢丽靖^1,2,3, 赵志远^1,2,3, 王昀昀⁴, 陈崇成^1,2,3

1. 福州大学地理空间信息技术国家地方联合工程研究中心, 福建福州 350002;
2. 空间数据挖掘与信息共享教育部重点实验室, 福建福州 350002;
3. 福州大学数字中国研究院, 福建福州 350002;
4. 福建省制图院, 福建福州 350001

收稿日期:2019-09-04 修回日期:2020-06-10 发布日期:2020-11-25
通讯作者: 赵志远 E-mail:zyzhao@fzu.edu.cn
作者简介:方莉娜(1983-),女,博士,助理研究员,研究方向为激光雷达数据处理与三维重建。E-mail:fangln@fzu.edu.cn
基金资助:
国家自然科学基金（42071446）；福建省自然科学基金（2017J01465）；中国博士后科学基金（2017M610391）

Road boundaries extraction from mobile laser scanning point clouds based on discrete point Snake

FANG Lina^1,2,3, LU Lijing^1,2,3, ZHAO Zhiyuan^1,2,3, WANG Yunyun⁴, CHEN Chongcheng^1,2,3

1. National Engineering Research Centre of Geospatial Information Technology, Fuzhou University, Fuzhou 350002, China;
2. Key Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education, Fuzhou University, Fuzhou 350002, China;
3. Academy of Digital China, Fuzhou University, Fuzhou 350002, China;
4. Fujian Mapping Institute, Fuzhou 350001, China

Received:2019-09-04 Revised:2020-06-10 Published:2020-11-25
Supported by:
The National Natural Science Foundation of China (No. 42071446);The National Natural Science Foundation of Fujian Province, China (No. 2017J01465);China Postdoctoral Science Foundation (No. 2017M610391)

摘要/Abstract

摘要： 针对车载激光点云中道路边界提取困难，自动化程度低的问题，提出一种基于离散点Snake的车载激光点云道路边界提取方法。不同于传统基于图像建立Snake，本文直接基于离散点建立Snake模型。先利用伪轨迹点数据，确定初始轮廓位置，参数化不同类型的道路边界初始轮廓；然后基于离散点构建适合多类型道路边界的Snake模型，定义模型内部、外部和约束能量，通过能量函数最小化推动轮廓曲线移动到显著道路边界特征点处，实现不同道路边界的精细提取。本文试验采用3份不同城市场景的车载激光点云数据验证本文方法的有效性，道路边界提取结果的准确率达到97.62%，召回率达到98.04%，F1-Measure值达到97.83%以上，且提取的道路边界结果与软件交互提取的结果有较好的吻合度。试验结果表明，本文方法能够修正噪声、断裂等数据质量对道路边界提取的影响，能够实现各类复杂城市环境中不同形状道路边界的提取，具有较强的稳健性和适用性。

关键词: 车载激光点云, 主动轮廓模型(Snake), 道路提取, 梯度, 能量函数

Abstract: Due to large volume of data, uneven spatial distribution of point densities, and complex scene, it is difficult to automatically extract and delineate road boundaries from mobile laser scanning (MLS) point clouds. This paper proposed a method for extracting road boundaries from MLS point clouds based on Snake. Different from the traditional Snake model defined within 2D image, we modified the Snake model directly based on 3D point clouds. Firstly, we developed a way of initializing Snake curves using pseudo-trajectory data to match multi-type road boundaries. Then, the Snake’s energy function was designed with internal, external and constrained energy terms derived from Snake curve points with their neighborhood points. Finally, the road boundaries were precisely extracted by minimizing the Snake’s energy function. Experiments were undertaken to evaluate the validities of the proposed algorithm with three different urban scene datasets acquired by different MLS system. Quantitative evaluations on the selected MLS datasets indicate that the Precision, Recall and F₁-Measure of road boundaries extraction results were over 97.62%, 98.04%, 97.83%, respectively, which validate that the proposed method proved a promising and robust solution for regular and irregular road boundaries extraction in complex urban environments.

Key words: mobile laser scanning point clouds, active contour model (Snake), road boundaries extraction, gradient vector, energy function

中图分类号:

P208

方莉娜, 卢丽靖, 赵志远, 王昀昀, 陈崇成. 车载激光点云道路边界提取的Snake方法[J]. 测绘学报, 2020, 49(11): 1438-1450.

FANG Lina, LU Lijing, ZHAO Zhiyuan, WANG Yunyun, CHEN Chongcheng. Road boundaries extraction from mobile laser scanning point clouds based on discrete point Snake[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(11): 1438-1450.

参考文献

[1] 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, 42(2):260-267. FANG Lina, YANG Bisheng. Automated extracting structural roads from mobile laser scanning point clouds[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(2):260-267.
[2] 王峰萍, 王卫星, 薛柏玉, 等. GVF Snake与显著特征相结合的高分辨率遥感图像道路提取[J]. 测绘学报, 2017, 46(12):1978-1985.DOI:10.11947/j.AGCS.2017.20170393. WANG Fengping, WANG Weixing, XUE Baiyu, et al. Road extraction from high-spatial-resolution remote sensing image by combining GVF snake with salient features[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(12):1978-1985. DOI:10.11947/j.AGCS.2017.20170393.
[3] 罗海峰, 方莉娜, 陈崇成, 等. 基于DBN的车载激光点云路侧多目标提取[J]. 测绘学报, 2018, 47(2):234-246.DOI:10.11947/j.AGCS.2018.20170524. LUO Haifeng, FANG Lina, CHEN Chongcheng, et al. Roadside multiple objects extraction from mobile laser scanning point cloud based on DBN[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(2):234-246. DOI:10.11947/j.AGCS.2018.20170524.
[4] 魏征. 车载LiDAR点云中建筑物的自动识别与立面几何重建[D]. 武汉:武汉大学, 2012. WEI Zheng. Automated extraction of buildings and facades reconstruction from mobile LiDAR point clouds[D]. Wuhan:Wuhan University, 2012.
[5] ZHOU Liang, VOSSELMAN G. Mapping curbstones in airborne and mobile laser scanning data[J]. International Journal of Applied Earth Observation and Geoinformation, 2012, 18:293-304.
[6] 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, 19(7):861-871. LUO Haifeng, FANG Lina, CHEN Chongcheng. Curb point clouds extraction from vehicle-borne laser scanning data[J]. Journal of Geo-Information Science, 2017, 19(7):861-871.
[7] YANG Bisheng, LIU Yuan, DONG Zhen, et al. 3D local feature BKD to extract road information from mobile laser scanning point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 130:329-343.
[8] 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, 33(4):458-462. LI Yongqiang, WANG Wenyue, ZHENG Yanhui, et al. Refining extraction of road boundary from vehicle LiDAR date[J]. Journal of Henan Polytechnic University(Natural Science), 2014, 33(4):458-462.
[9] ONIGA F, NEDEVSCHI S. Polynomial curb detection based on dense stereovision for driving assistance[C]//Proceedings of the 13th International IEEE Conference on Intelligent Transportation Systems.Funchal, Portugal:IEEE, 2010.
[10] JAAKKOLA A, HYYPPÄ J, HYYPPÄ H, et al. Retrieval algorithms for road surface modelling using laser-based mobile mapping[J]. Sensors, 2008, 8(9):5238-5249.
[11] 魏双全, 房华乐, 林祥国. 先验知识引导的车载激光扫描点云道路信息提取[J]. 测绘科学, 2014, 39(10):81-84. WEI Shuangquan, FANG Huale, LIN Xiangguo. Road information extraction from mobile laser scanning point cloud based on priori knowledge[J]. Science of Surveying and Mapping, 2014, 39(10):81-84.
[12] 杨必胜, 魏征, 李清泉, 等. 面向车载激光扫描点云快速分类的点云特征图像生成方法[J]. 测绘学报, 2010, 39(5):540-545. YANG Bisheng, WEI Zheng, LI Qingquan, et al. A classification-oriented method of feature image generation for vehicle-borne laser scanning point clouds[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(5):540-545.
[13] HATA A Y, OSÓRIO F S, WOLF D F. Robust curb detection and vehicle localization in urban environments[C]//Proceedings of 2014 IEEE Intelligent Vehicles Symposium Proceedings. Dearborn, USA:IEEE, 2014.
[14] MCELHINNEY C P, KUMAR P, CAHALANE C, et al. Initial results from European Road Safety Inspection (EURSI) mobile mapping project[J]. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2010, 38(5):440-445.
[15] 苏致远, 徐友春, 彭永胜, 等. 基于点云密度的结构化道路边界增强检测方法[J]. 汽车工程, 2017, 39(7):833-838. SU Zhiyuan, XU Youchun, PENG Yongsheng, et al. Enhanced detection method for structured road edge based on point clouds density[J]. Automotive Engineering, 2017, 39(7):833-838.
[16] SERNA A, MARCOTEGUI B. Urban accessibility diagnosis from mobile laser scanning data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 84:23-32.
[17] 李天庆, 张毅, 刘志, 等. Snake模型综述[J]. 计算机工程, 2005, 31(9):1-3. LI Tianqing, ZHANG Yi, LIU Zhi, et al. An overview on Snakes models[J]. Computer Engineering, 2005, 31(9):1-3.
[18] FUA P. Model-based optimization:accurate and consistent site modeling[C]//Proceedings of the 18th Congress,International Society for Photogrammetry and Remote Sensing. Vienna:ISPRS, 1996.
[19] KASS M, WITKIN A, TERZOPOULOS D. Snakes:active contour models[J]. International Journal of Computer Vision, 1987, 1(4):321-331.
[20] 孙金虎. 点云模型分割与融合关键技术研究[D]. 南京:南京航空航天大学, 2013. SUN Jinhu. Research on key technologies of point cloud segmentation and fusion[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2013.
[21] BOYKO A, FUNKHOUSER T. Extracting roads from dense point clouds in large scale urban environment[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(6):S2-S12.
[22] KUMAR P, MCELHINNEY C P, LEWIS P, et al. An automated algorithm for extracting road edges from terrestrial mobile LiDAR data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 85:44-55.
[23] COHEN L D.On active contour models and balloons[J]. CVGIP:Image Understanding, 1991, 53(2):211-218.
[24] XU Chenyang, PRINCE J L. Gradient vector flow:a new external force for snakes[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Juan, USA:IEEE, 1997.
[25] 韩婷, 杨必胜, 袁鹏飞, 等. OSM辅助的车载激光点云道路三维矢量边界提取[J]. 测绘科学技术, 2018, 6(2):128-140. HAN Ting, YANG Bisheng, YUAN Pengfei, et al. OSm-assisted extraction of 3D vector boundary from mobile laser scanning point cloud[J]. Geomatics Science and Technology, 2018, 6(2):128-140.
[26] 韩婷. OpenStreetMap辅助的车载激光点云道路几何特征提取[D]. 武汉:武汉大学, 2018. HAN Ting. OpenStreetmap-assisted extraction of road geometric feature from mobile laser scanning point clouds[D]. Wuhan:Wuhan University, 2018.
[27] LAPTEV I, MAYER H, LINDEBERG T, et al. Automatic extraction of roads from aerial images based on scale space and snakes[J]. Machine Vision and Applications, 2000, 12(1):23-31.

车载激光点云道路边界提取的Snake方法

Road boundaries extraction from mobile laser scanning point clouds based on discrete point Snake

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	潘娟霞, 邹贤才. GOCE引力梯度内部校准方法[J]. 测绘学报, 2022, 51(2): 192-200.
[2]	徐焕, 于锦海, 安邦, 万晓云. 利用垂直重力梯度异常反演海底地形的解析方法[J]. 测绘学报, 2022, 51(1): 53-62.
[3]	方莉娜, 王爽, 赵志远, 付化胜, 陈崇成. 车载激光点云中交通标线自动分类与矢量化[J]. 测绘学报, 2021, 50(9): 1251-1265.
[4]	范雕, 李姗姗, 欧阳永忠, 孟书宇, 陈成, 邢志斌, 张驰. 顾及海底地形非线性项的最小二乘配置反演方法[J]. 测绘学报, 2021, 50(7): 953-971.
[5]	石岩, 王达, 陈袁芳, 陈炳蓉, 赵冰冰, 邓敏. 流空间邻近关系约束下的流行病分布空间异常探测方法[J]. 测绘学报, 2021, 50(6): 777-788.
[6]	陈鑑华, 张兴福, 沈云中, 陈秋杰, 李伟超. GOCE卫星重力梯度观测值的时变重力场变化改正及影响分析[J]. 测绘学报, 2021, 50(3): 324-332.
[7]	樊仲藜, 张力, 王庆栋, 刘思婷, 叶沅鑫. SAR影像和光学影像梯度方向加权的快速匹配方法[J]. 测绘学报, 2021, 50(10): 1390-1403.
[8]	谢先明, 孙玉铮, 梁小星, 曾庆宁, 郑展恒. 相位解缠的CKF局部多项式系数递推估计法[J]. 测绘学报, 2020, 49(8): 1023-1031.
[9]	陆川伟, 孙群, 陈冰, 温伯威, 赵云鹏, 徐立. 车辆轨迹数据的道路学习提取法[J]. 测绘学报, 2020, 49(6): 692-702.
[10]	王舒洋, 慕晓冬, 贺浩, 杨东方, 马晨晖. 航拍图像跨数据域特征迁移道路提取方法[J]. 测绘学报, 2020, 49(5): 611-621.
[11]	范雕, 李姗姗, 杨军军, 孟书宇, 邢志斌, 张驰, 冯进凯. 利用多元回归分析反演西南印度洋区域海底地形[J]. 测绘学报, 2020, 49(2): 147-161.
[12]	辛明真, 阳凡林, 薛树强, 王振杰, 韩云峰. 顾及波束入射角的常梯度声线跟踪水下定位算法[J]. 测绘学报, 2020, 49(12): 1535-1542.
[13]	方莉娜, 黄志文, 罗海峰, 陈崇成. 车载激光扫描数据中实线型交通标线提取[J]. 测绘学报, 2019, 48(8): 960-974.
[14]	李佳田, 王聪聪, 贾成林, 牛一如, 王瑜, 张文靖, 吴华静, 李键. 大角度立体像对相对定向的混合共轭梯度算法[J]. 测绘学报, 2019, 48(3): 322-329.
[15]	贺浩, 王仕成, 杨东方, 王舒洋, 刘星. 基于Encoder-Decoder网络的遥感影像道路提取方法[J]. 测绘学报, 2019, 48(3): 330-338.