LDTR: Transformer-based Lane Detection with Anchor-chain Representation

arXiv:2403.14354v1 Announce Type: new
Abstract: Despite recent advances in lane detection methods, scenarios with limited- or no-visual-clue of lanes due to factors such as lighting conditions and occlusion remain challenging and crucial for automated driving. Moreover, current lane representations require complex post-processing and struggle with specific instances. Inspired by the DETR architecture, we propose LDTR, a transformer-based model to address these issues. Lanes are modeled with a novel anchor-chain, regarding a lane as a whole from the beginning, which enables …

abstract advances anchor architecture arxiv automated cs.cv current detection detection methods detr driving instances lane detection lighting post-processing processing representation struggle transformer type visual