基于车载LiDAR的特征融合差分的车前道路提取方法

doi:10.13474/j.cnki.11-2246.2023.0352

测绘通报 ›› 2023, Vol. 0 ›› Issue (12): 13-18.doi: 10.13474/j.cnki.11-2246.2023.0352

基于车载LiDAR的特征融合差分的车前道路提取方法

何光明¹, 韩士元^1,2, 陈月辉^1,2, 周劲^1,2, 杨君³

1. 济南大学山东省网络环境智能计算重点实验室, 山东济南 250022;
2. 济南大学人工智能研究院, 山东济南 250022;
3. 山东交通学院汽车工程学院, 山东济南 250023

收稿日期:2023-06-14 发布日期:2024-01-08
通讯作者: 韩士元。E-mail:isehansy@ujn.edu.cn
作者简介:何光明(1996-),男,硕士,研究方向为点云的道路不平度。E-mail:heguangming12138@163.com
基金资助:
国家自然科学基金(62273164;62373164);山东省自然科学基金重点项目(ZR2020KF006)

Front-of-vehicle road extraction method based on feature fusion difference of vehicle LiDAR

HE Guangming¹, HAN Shiyuan^1,2, CHEN Yuehui^1,2, ZHOU Jin^1,2, YANG Jun³

1. Shandong Provincial Key Laboratory of Network Based Intelligent Computing, University of Jinan, Jinan 250022, China;
2. Institute of Artificial Intelligence, University of Jinan, Jinan 250022, China;
3. School of Automotive Engineering, Shandong Jiaotong University, Jinan 250023, China

Received:2023-06-14 Published:2024-01-08

摘要/Abstract

摘要： 为应对行驶中变化的道路环境,划分当前车前道路的可行驶区域,本文提出一种基于多特征融合差分的车前道路检测方法。该算法通过形态学滤波法对原始点云进行地面点云提取,统计归纳地面点云数据,进而界定运算域,在运算域内划分不同纵深的差分元尺寸和起点,在差分元内进行特征参数的融合,形成特征矩阵,求解差分矩阵后再进行阈值滤波,进而实现车前道路点云的提取。本文首先与相关道路点云的提取算法进行对比,表明其性能优良;然后针对所采数据不同纵深的道路提取效果进行对比,证明该算法的有效性。

关键词: 车载LiDAR, 点云, 车前道路提取, 特征融合, 差分

Abstract: In order to cope with the changing road environment during driving and divide the drivable area of the current road in front of the vehicle, this paper proposes a detection method for the road in front of the vehicle based on multi-feature fusion difference. This algorithm extracts the ground point cloud from the original point cloud by morphological filtering method, statistically summarizes the ground point cloud data to define the operation domain, divides the differential element size and starting point of different depths in the operation domain, fuses the characteristic parameters in the differential element, forms a feature matrix, solves the differential matrix, and performs threshold filtering, so as to realize the extraction of the point cloud in front of the vehicle. In this paper the extraction algorithm of the relevant road point cloud is compared to,which highlight its excellent performance and then the road extraction effect of different depths of the collected data is compared to prove the effectiveness of the algorithm.

Key words: in-vehicle LiDAR, point cloud, front-of-vehicle road extraction, feature fusion, differential

中图分类号:

P237

何光明, 韩士元, 陈月辉, 周劲, 杨君. 基于车载LiDAR的特征融合差分的车前道路提取方法[J]. 测绘通报, 2023, 0(12): 13-18.

HE Guangming, HAN Shiyuan, CHEN Yuehui, ZHOU Jin, YANG Jun. Front-of-vehicle road extraction method based on feature fusion difference of vehicle LiDAR[J]. Bulletin of Surveying and Mapping, 2023, 0(12): 13-18.

参考文献

[1] YUAN Xia,ZHAO Chunxia,ZHANG Haofeng. Road detection and corner extraction using high definition lidar[J]. Information Technology Journal,2010,9(5): 1022-1030.
[2] IBRAHIM S,LICHTI D. Curb-based street floor extraction from mobile terrestrial lidar point cloud[J]. ISPRS-International Archives of the Photogrammetry,Remote Sensing and Spatial Information Sciences,2012,B5(1): 193-198.
[3] YANG Bisheng,FANG Lina,LI J. Semi-automated extraction and delineation of 3D roads of street scene from mobile laser scanning point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2013,79: 80-93.
[4] WANG Hanyun,LUO Huan,WEN Chenglu,et al. Road boundaries detection based on local normal saliency from mobile laser scanning data[J]. IEEE Geoscience and Remote Sensing Letters,2015,12(10): 2085-2089.
[5] GUAN Haiyan,LI J,YU Yongtao,et al. Automated road information extraction from mobile laser scanning data[J]. IEEE Transactions on Intelligent Transportation Systems,2015,16(1): 194-205.
[6] ZAI D,GUO Yulan,LI J,et al. 3D road surface extraction from mobile laser scanning point clouds[C]//Proceedings of 2016 IEEE Inter National Geoscience and Remote Sensing Symposium(IGARSS),[S.l.]:IEEE,2016.
[7] 于子龙,胡友健. 基于机载LiDAR点云的初始道路提取[J]. 激光与光电子学进展,2021,58(24): 137-144.
[8] 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.
[9] 王勇,曾祥强. 集成注意力机制和扩张卷积的道路提取模型[J]. 中国图象图形学报,2022,27(10): 3102-3115.
[10] 刘国栋,刘佳,刘浪. 一种基于机载LiDAR数据的山区道路提取方法[J]. 激光技术,2022,46(4): 466-473.
[11] 肖信峰. 车载激光点云道路及标线提取[D].合肥:合肥工业大学,2022.
[12] 周建,沈长表,束蝉方. 基于车载激光点云的道路路面提取[J]. 现代测绘,2021,44(6): 8-12.
[13] 盛君,孙晨辉,王杰,等. 基于车载激光点云的城市道路提取方法研究[J]. 地理信息世界,2022,29(3): 114-118.
[14] 徐安帝,王会峰,余炳伟,等. 基于车载LiDAR点云的道路提取方法[J]. 光学技术,2023,49(1): 29-33.
[15] ZHANG Keqi,CHEN S C,WHITMAN D,et al. A progressive morphological filter for removing nonground measurements from airborne LIDAR data[J]. IEEE Transactions on Geoscience and Remote Sensing,2003,41(4): 872-882.
[16] QI C R,SU Hao,MO Kaichun,et al. PointNet: deep learning on point sets for 3D classification and segmentation[EB/OL]. [2023-06-01]. https://arxiv.org/abs/1612.00593.
[17] YOU Yurong,LUO K Z,CHEN Xiangyu,et al. Hindsight is 20/20: leveraging past traversals to aid 3D perception[EB/OL]. [2023-06-01]. https://arxiv.org/abs/2203.11405.
[18] DIAZ-RUIZ C A,XIA Youya,YOU Yurong,et al. Ithaca365: dataset and driving perception under repeated and challenging weather conditions[EB/OL]. [2023-06-01]. https://arxiv.org/abs/2208.01166.
[19] YOU Yurong,LUO K Z,PHOO C P,et al. Learning to detect mobile objects from LiDAR scans without labels[EB/OL]. [2023-06-01]. https://arxiv.org/abs/2203.15882.
[20] CLODE S,FRANZ R, PETER K,et al. Detection and vectorization of roads from lidar data[J]. Photogrammetric Engineering & Remote Sensing,2007,73(5): 517-535.
[21] WANG H,WANG C,CHEN Y,et al. Extracting Road Surface from Mobile Laser Scanning Point Clouds in Large Scale Urban Environment[C]//Proceedings of 17th International IEEE Conference on Intelligent Transportation SystemsⅡ.Yokohama:[s.n.],2014:673-678.

基于车载LiDAR的特征融合差分的车前道路提取方法

Front-of-vehicle road extraction method based on feature fusion difference of vehicle LiDAR

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]	戴志胜, 王鹏飞, 周光建. 基于摄影测量匹配点云估算建筑表面太阳辐照度[J]. 测绘通报, 2023, 0(9): 93-99.
[2]	赵奕文, 杨天然, 苗李莉, 马运涛. GPS+BDS与UWB组合定位的Helmert方差分量估计方法[J]. 测绘通报, 2023, 0(8): 91-96.
[3]	李捷斌, 王宁, 赵春晨. 三维激光扫描仪在建筑物精细重建中的应用[J]. 测绘通报, 2023, 0(8): 126-129.
[4]	王斌, 徐佳沅, 唐力明, 周立鹏. 小型斜坡隐患识别“空天地”图谱几何遥感方法[J]. 测绘通报, 2023, 0(8): 136-141.
[5]	于倩, 凌晓春, 赵明金, 隗伟, 刘洋. 空地融合的建筑物室内外一体化点云构建技术[J]. 测绘通报, 2023, 0(8): 146-150.
[6]	冯晓珂, 吕沛娴, 张卡, 沈华康, 叶龙杰, 赵娜, 杨盈. 面向滩涂DEM构建的机载LiDAR点云滤波方法[J]. 测绘通报, 2023, 0(7): 58-62.
[7]	赵丽凤, 王勇, 王晓静, 任传斌, 徐鹏宇. 改进U-Net模型支持下的高密度激光点云在沥青道路病害识别中的应用[J]. 测绘通报, 2023, 0(7): 136-141,159.
[8]	张清波, 严加栋. 融合自适应最优邻域和卷积神经网络的三维点云分类[J]. 测绘通报, 2023, 0(7): 177-182.
[9]	何荣, 白伟森, 代震, 翟慧鹏. UAV影像点云支持下的林地精细DEM建立方法[J]. 测绘通报, 2023, 0(6): 75-81.
[10]	张炎, 刘立龙, 何广焕, 徐勇, 蒙金龙. 改进哈里斯鹰优化算法在匹配地面点云孔洞修补中的应用[J]. 测绘通报, 2023, 0(6): 82-87.
[11]	孙森震, 荆留杰, 王力. 利用点云空间投影概率特征的隧道钢拱架检测与提取[J]. 测绘通报, 2023, 0(6): 129-133.
[12]	姚萌萌, 李晓明, 王伟玺, 谢林甫, 黄俊杰, 黄鸿盛, 汤圣君. 几何特征与神经网络联合优化的室内三维点云语义分割方法[J]. 测绘通报, 2023, 0(5): 56-61.
[13]	牛鹏涛, 曹毅, 张恩朝, 漆洋. 融合车载LiDAR点云和全景影像的道路标线自动提取方法[J]. 测绘通报, 2023, 0(5): 67-71,139.
[14]	朱赞, 姚钘, 王建琦, 李阳, 龙诗科. 三维激光扫描技术应用于机翼微变形检测[J]. 测绘通报, 2023, 0(5): 115-119.
[15]	黄桦, 葛为燎, 刘微微, 钱荣荣, 李杰. 利用倾斜影像重建点云的建筑物变化检测[J]. 测绘通报, 2023, 0(5): 125-129.