Citation

Martirena JB, Doncel MN, Vidal AC, Madurga OO, Esnal JF, Romay MG. IEEE Trans. Intel. Transp. Syst. 2022; 23(4): 3115-3125.

Copyright

(Copyright © 2022, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/TITS.2020.3031921

PMID

unavailable

Abstract

Lane markings are mymargin a key element for Autonomous Driving. The generation of high definition maps and ground-truth data require extensive manual labor. In this paper, we present an efficient and robust method for the offline annotation of lane markings, using low-density LIDAR point clouds and odometry information. The odometry is used to accumulate the scans and to process them using blocks following the trajectory of the vehicle. At each block, candidate lane marking points are detected by generating virtual scan-lines and applying a dynamically optimized filter function to the LIDAR intensity values. The lane markings are tracked block wise, and their width is estimated and classified as either solid or dashed. The results are lists of connected 3D points that represent the different lane markings. The accuracy of the proposed method was tested against manually labeled recordings. A novel evaluation methodology focused on the lateral precision of detections is presented. Moreover, a web user interface was used to load the produced annotations, achieving a reduction of 60% in the annotation time, as compared to a fully manual baseline.

Language: en

Keywords

annotation; Annotations; Autonomous driving; Image segmentation; lane detection; lane marking; lane sensing; Laser radar; laser scanning; Lasers; LIDAR; Manuals; point cloud; road marking; Roads; Three-dimensional displays