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.Moreove...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 anchorchain,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 Fr´echet distance,parameterized F1-score,and additional synthetic metrics.Experimental results demonstrate that LDTR achieves state-of-the-art performance on well-known datasets.展开更多
基金supported by the National Natural Science Foundation of China(No.U23A6007).
文摘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 anchorchain,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 Fr´echet distance,parameterized F1-score,and additional synthetic metrics.Experimental results demonstrate that LDTR achieves state-of-the-art performance on well-known datasets.
