Efficient and robust lane marking extraction from mobile lidar point clouds

被引:66
作者
Jung, Jaehoon [1 ]
Che, Erzhuo [1 ]
Olsen, Michael J. [1 ]
Parrish, Christopher [1 ]
机构
[1] Oregon State Univ, Sch Civil & Construct Engn, 101 Kearney Hall, Corvallis, OR 97331 USA
基金
美国国家科学基金会;
关键词
Mobile laser scanning; Point cloud; Lane marking extraction; ROAD MARKINGS; AUTOMATED EXTRACTION; SEGMENTATION; INFORMATION; FEATURES; IMAGES; MODEL;
D O I
10.1016/j.isprsjprs.2018.11.012
中图分类号
P9 [自然地理学];
学科分类号
0705 ; 070501 ;
摘要
Surveys of roadways with Mobile Laser Scanning (MLS) are now being conducted on a regular basis by many transportation agencies to provide detailed geometric information to support a wide range of applications, including asset management. Most MLS systems provide intensity (return signal strength) data as a point attribute in georeferenced point clouds, which may be used to estimate retro-reflectivity of pavement markings for effective maintenance. Nevertheless, the extraction of pavement markings from mobile lidar data remains an open challenge, due to variable noise, degree of wear on the markings, and road conditions. This paper addresses these challenges, presenting a novel approach for efficient, reliable extraction of lane markings, including those that have been significantly worn. First, using the MLS trajectory information, the lidar data is discretized into smaller sections, and then transformed to the local coordinate system, such that the road surface is near-horizontal for reliable extraction on roads with significant grade. Subsequently, the road surface is extracted using the constrained Random Sampling and Consensus (RANSAC) algorithm and then rasterized into a 2D intensity image to apply image processing techniques, namely: image segmentation to separate the lane markings from the road pavement, and a morphological opening operation to remove small objects. However, the extracted lane markings are prone to over-segmentation, due to occlusions or worn portions caused by moving vehicles. To rectify this, topologically-similar lane markings are associated with each other by computing line parameters (i.e., orientation and distance from the origin), which enables the gaps to be filled among the associated lanes. Finally, the remaining incorrect lane markings are detected and removed through a noise filtering phase using Dip test statistics. Examples of the effectiveness and application of the methodology are shown for a variety of sites with stripes of variable condition to highlight the robustness of the approach. Using optimized parameter values, the algorithm achieved Fl scores of 89-97% when tested on a variety of datasets encompassing a wide range of road scene types.
引用
收藏
页码:1 / 18
页数:18
相关论文
共 44 条
[21]   The SSP-Tree: A Method for Distributed Processing of Range Monitoring Queries in Road Networks [J].
Jung, HaRim ;
Kim, Ung-Mo .
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2017, 6 (11)
[22]   Productive modeling for development of as-built BIM of existing indoor structures [J].
Jung, Jaehoon ;
Hong, Sungchul ;
Jeong, Seongsu ;
Kim, Sangmin ;
Cho, Hyoungsig ;
Hong, Seunghwan ;
Heo, Joon .
AUTOMATION IN CONSTRUCTION, 2014, 42 :68-77
[23]   A Review of LIDAR Radiometric Processing: From Ad Hoc Intensity Correction to Rigorous Radiometric Calibration [J].
Kashani, Alireza G. ;
Olsen, Michael J. ;
Parrish, Christopher E. ;
Wilson, Nicholas .
SENSORS, 2015, 15 (11) :28099-28128
[24]   Automated road markings extraction from mobile laser scanning data [J].
Kumar, Pankaj ;
McElhinney, Conor P. ;
Lewis, Paul ;
McCarthy, Timothy .
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2014, 32 :125-137
[25]  
Mechler F., 2002, HARTIGANS DIP STAT
[26]  
Mozos OM, 2007, SPRINGER TRAC ADV RO, V28, P453
[27]  
Olsen M.J., 2018, FHWAORRD1901 OR DEP, V1
[28]  
Olsen MJ, 2013, 748 TRB NCHRP
[29]  
Oregon DOT, 2011, TRAFFIC LINE MANUAL
[30]  
Pike A., 2013, Investigate the ability to determine pavement marking retroreflectivity-Evaluate the advanced mobile asset collection (AMAC) mobile pavement marking retroreflectivity measurement system