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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Zhongyu, Shen, Chen, Shao, Wei, Xing, Tengfei, Hu, Runbo, Xu, Pengfei, Chai, Hua, Xue, Ruini
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916170429366272
author Yang, Zhongyu
Shen, Chen
Shao, Wei
Xing, Tengfei
Hu, Runbo
Xu, Pengfei
Chai, Hua
Xue, Ruini
author_facet Yang, Zhongyu
Shen, Chen
Shao, Wei
Xing, Tengfei
Hu, Runbo
Xu, Pengfei
Chai, Hua
Xue, Ruini
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LDTR: Transformer-based Lane Detection with Anchor-chain Representation
Yang, Zhongyu
Shen, Chen
Shao, Wei
Xing, Tengfei
Hu, Runbo
Xu, Pengfei
Chai, Hua
Xue, Ruini
Computer Vision and Pattern Recognition
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.
title LDTR: Transformer-based Lane Detection with Anchor-chain Representation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.14354