English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the fast development of autonomous driving technologies, there is anincreasing demand for high-definition (HD) maps, which provide reliable androbust prior information about the static part of the traffic environments. Asone of the important elements in HD maps, road lane centerline is critical fordownstream tasks, such as prediction and planning. Manually annotatingcenterlines for road lanes in HD maps is labor-intensive, expensive andinefficient, severely restricting the wide applications of autonomous drivingsystems. Previous work seldom explores the lane centerline detection problemdue to the complicated topology and severe overlapping issues of lanecenterlines. In this paper, we propose a novel method named CenterLineDet todetect lane centerlines for automatic HD map generation. Our CenterLineDet istrained by imitation learning and can effectively detect the graph ofcenterlines with vehicle-mounted sensors (i.e., six cameras and one LiDAR)through iterations. Due to the use of the DETR-like transformer network,CenterLineDet can handle complicated graph topology, such as laneintersections. The proposed approach is evaluated on the large-scale publicdataset NuScenes. The superiority of our CenterLineDet is demonstrated by thecomparative results. Our code, supplementary materials, and videodemonstrations are available at\href{https://tonyxuqaq.github.io/projects/CenterLineDet/}{https://tonyxuqaq.github.io/projects/CenterLineDet/}.

CenterLineDet: CenterLine Graph Detection for Road Lanes with Vehicle-mounted Sensors by Transformer for HD Map Generation