Abstract
The commercialization of automated driving vehicles promotes the development of safer and more efficient autonomous driving technologies including lane marking detection strategy, which is considered to be the most promising feature in environmental perception technology. To reduce the tradeoff between time consumption and detection precision, we propose a real-time lane marking detection method by using LiDAR point clouds directly. A constrained RANSAC algorithm is applied to select the regions of interest and filter the background data. Further, a road curb detection method based on the segment point density is also proposed to classify the road points and curb points. Finally, an adaptive threshold selection method is proposed to identify lane markings. In this investigation, five datasets are collected from different driving conditions that include the straight road, curved road, and uphill, to test the proposed method. The proposed method is evaluated under different performance metrics such as Precision, Recall, Dice, Jaccard as well as the average detection distance and computation time for the five datasets. The quantitative results show the efficiency and feasibility of this proposed method.
Highlights
Self-driving technologies have received much attention due to the several research activities of universityindustry collaboration financed by some reputed companies such as Waymo [1] and Hyundai [2]
We present a real-time lane marking detection method for structured roads with few obstructions based on a Light Detection and Ranging (LiDAR) sensor using point clouds
REGION-OF-INTEREST Fig. 8 shows the outcomes of the ROI selection approach that includes the results of the rough road data with marks of curb points as well as, the results using the curb filtering algorithm based on segment point density
Summary
Self-driving technologies have received much attention due to the several research activities of universityindustry collaboration financed by some reputed companies such as Waymo [1] and Hyundai [2]. The realization of autonomous driving technology is difficult. The most basic yet important function for an automated vehicle is environmental perception, because of its direct influence on both drivers and pedestrians. Various objects need to be recognized in the procedure of environmental perception, such as lane markings, pedestrians, and adjacent vehicles. Different sensing modalities are used to achieve autonomous driving, for example, visual and thermal cameras, radars, Light Detection and Ranging (LiDAR) sensors, and ultrasonic sensors.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
