Extraction of road lane markings from mobile LiDAR data
Yükleniyor...
Dosyalar
Tarih
2021
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Sage Publications
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
This study presents a method for automatic extraction of road lane markings from mobile light detection and ranging (LiDAR) data. Road lanes and traffic signs on the road surface provide safe driving for drivers and aid traffic flow movement along the highway and street. Mobile LiDAR systems acquire massive datasets very quickly in a short time. To simplify the data structure and feature extraction, it is essential for traffic management personnel to apply the right methods. Road lanes must be visible and are a major factor in road safety for drivers. In this study, a methodology is devised and implemented for the extraction of features such as dashed lines, continuous lanes, and direction arrows on the pavement from point clouds. Point cloud data was collected from the Riegl VMX-450 mobile LiDAR system. The alpha shape algorithm is implemented on a point cloud and compared with the widespread use of edge detection techniques applied for intensity-based raster images. The proposed methodology directly extracts three-dimensional and two-dimensional road features to control the quality of road markings and spatial positions with the obtained marking boundaries. State-of-the-art results are obtained and compared with manually digitized reference markings. The standard deviations were evaluated and acquired for intensity imagebased and direct point cloud-based extractions, at 1.2 cm and 1.7 cm, respectively
Açıklama
Anahtar Kelimeler
Kaynak
Transportation Research Record
WoS Q Değeri
Q3
Scopus Q Değeri
Q2
Cilt
2675
Sayı
5
Künye
Zeybek, M. (2021). Extraction of Road Lane Markings from Mobile LiDAR Data. Transportation Research Record, 2675 (5), 30-47 0361198120981948.
