TY - JOUR
T1 - Detection and tracking of pedestrians and vehicles using roadside LiDAR sensors
AU - Zhao, Junxuan
AU - Xu, Hao
AU - Liu, Hongchao
AU - Wu, Jianqing
AU - Zheng, Yichen
AU - Wu, Dayong
N1 - Funding Information:
This work was supported by the SOLARIS Institute , a Tier 1 University Transportation Center (UTC) [Grant No. DTRT13-G-UTC55 ] and matching funds by the Nevada Department of Transportation (NDOT) [Grant No. P224-14-803/TO #13 ]. The authors gratefully acknowledge this financial support. This research was also supported by engineers with the Nevada Department of Transportation, the Regional Transportation Commission of Washoe County , Nevada, and the City of Reno . We are very thankful to the reviewers for their time and efforts, their comments and suggestions have greatly improved the quality of this paper.
Publisher Copyright:
© 2019 Elsevier Ltd
PY - 2019/3
Y1 - 2019/3
N2 - Light Detection and Ranging (LiDAR) is a remote sensing technology widely used in many areas ranging from making precise medical equipment to creating accurate elevation maps of farmlands. In transportation, although it has been used to assist some design and planning works, the application has been predominantly focused on autonomous vehicles, regardless of its great potential in precise detection and tracking of all road users if implemented in the field. This paper explores fundamental concepts, solution algorithms, and application guidance associated with using infrastructure-based LiDAR sensors to accurately detect and track pedestrians and vehicles at intersections. Based on LiDAR data collected in the field, investigations were conducted in the order of background filtering, object clustering, pedestrian and vehicle classification, and tracking. The results of the analysis include accurate and real-time information of the presence, position, velocity, and direction of pedestrians and vehicles. By studying the data from infrastructure-mounted LiDAR sensors at intersections, this paper offers insights into some critical techniques that are valuable to both researchers and practitioners toward field implementation of LiDAR sensors.
AB - Light Detection and Ranging (LiDAR) is a remote sensing technology widely used in many areas ranging from making precise medical equipment to creating accurate elevation maps of farmlands. In transportation, although it has been used to assist some design and planning works, the application has been predominantly focused on autonomous vehicles, regardless of its great potential in precise detection and tracking of all road users if implemented in the field. This paper explores fundamental concepts, solution algorithms, and application guidance associated with using infrastructure-based LiDAR sensors to accurately detect and track pedestrians and vehicles at intersections. Based on LiDAR data collected in the field, investigations were conducted in the order of background filtering, object clustering, pedestrian and vehicle classification, and tracking. The results of the analysis include accurate and real-time information of the presence, position, velocity, and direction of pedestrians and vehicles. By studying the data from infrastructure-mounted LiDAR sensors at intersections, this paper offers insights into some critical techniques that are valuable to both researchers and practitioners toward field implementation of LiDAR sensors.
KW - Classification
KW - Clustering
KW - Infrastructure-based LiDAR
KW - Pedestrians and Vehicles
KW - Trajectory Extraction
UR - http://www.scopus.com/inward/record.url?scp=85060079519&partnerID=8YFLogxK
U2 - 10.1016/j.trc.2019.01.007
DO - 10.1016/j.trc.2019.01.007
M3 - Article
AN - SCOPUS:85060079519
VL - 100
SP - 68
EP - 87
JO - Transportation Research Part C: Emerging Technologies
JF - Transportation Research Part C: Emerging Technologies
SN - 0968-090X
ER -