LDTR: Transformer-based Lane Detection with Anchor-chain Representation
This addresses a critical problem for automated driving systems by improving lane detection in difficult conditions, though it appears incremental as it builds on existing DETR architecture.
The paper tackles lane detection in challenging scenarios like poor lighting and occlusion for automated driving, proposing LDTR, a transformer-based model with a novel anchor-chain representation that achieves state-of-the-art performance on well-known datasets.
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 LDTR to handle special lanes inherently. To enhance lane instance perception, LDTR incorporates a novel multi-referenced deformable attention module to distribute attention around the object. Additionally, LDTR incorporates two line IoU algorithms to improve convergence efficiency and employs a Gaussian heatmap auxiliary branch to enhance model representation capability during training. To evaluate lane detection models, we rely on Frechet distance, parameterized F1-score, and additional synthetic metrics. Experimental results demonstrate that LDTR achieves state-of-the-art performance on well-known datasets.