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

• URL: http://arxiv.org/abs/2403.14354v1
• Date: Thu, 21 Mar 2024 12:29:26 GMT
• Title: LDTR: Transformer-based Lane Detection with Anchor-chain Representation
• Authors: Zhongyu Yang, Chen Shen, Wei Shao, Tengfei Xing, Runbo Hu, Pengfei Xu, Hua Chai, Ruini Xue,
• Abstract summary: Lane detection scenarios with limited- or no-visual-clue of lanes remain challenging and crucial for automated driving. Inspired by the DETR architecture, we propose LDTR, a transformer-based model to address these issues. Experimental results demonstrate that LDTR achieves state-of-the-art performance on well-known datasets.
• Score: 11.184960972042406
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 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.

Related papers

• LMT-Net: Lane Model Transformer Network for Automated HD Mapping from Sparse Vehicle Observations [11.395749549636868]
  Lane Model Transformer Network (LMT-Net) is an encoder-decoder neural network architecture that performs polyline encoding and predicts lane pairs and their connectivity. We evaluate the performance of LMT-Net on an internal dataset that consists of multiple vehicle observations as well as human annotations as Ground Truth (GT)
  arXiv  Detail & Related papers  (2024-09-19T02:14:35Z)
• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping [84.65114565766596]
  We present OpenLane-V2, the first dataset on topology reasoning for traffic scene structure. OpenLane-V2 consists of 2,000 annotated road scenes that describe traffic elements and their correlation to the lanes. We evaluate various state-of-the-art methods, and present their quantitative and qualitative results on OpenLane-V2 to indicate future avenues for investigating topology reasoning in traffic scenes.
  arXiv  Detail & Related papers  (2023-04-20T16:31:22Z)
• Repainting and Imitating Learning for Lane Detection [52.5220065495956]
  Current lane detection methods are struggling with the invisibility lane issue caused by heavy shadows. We propose a novel Repainting and Imitating Learning framework containing a pair of teacher and student. Our method introduces no extra time cost during inference and can be plug-and-play in various cutting-edge lane detection networks.
  arXiv  Detail & Related papers  (2022-10-11T02:26:39Z)
• Laneformer: Object-aware Row-Column Transformers for Lane Detection [96.62919884511287]
  Laneformer is a transformer-based architecture tailored for lane detection in autonomous driving. Inspired by recent advances of the transformer encoder-decoder architecture in various vision tasks, we move forwards to design a new end-to-end Laneformer architecture.
  arXiv  Detail & Related papers  (2022-03-18T10:14:35Z)
• RONELDv2: A faster, improved lane tracking method [1.3965477771846408]
  Lane detection is an integral part of control systems in autonomous vehicles and lane departure warning systems. This paper proposes an improved, lighter weight lane detection method, RONELDv2. Experiments using the proposed improvements show a consistent increase in lane detection accuracy results across different datasets and deep learning models.
  arXiv  Detail & Related papers  (2022-02-26T13:12:09Z)
• End-to-end Lane Shape Prediction with Transformers [13.103463647059634]
  Lane detection is widely used for lane departure warning and adaptive cruise control in autonomous vehicles. We propose an end-to-end method that directly outputs parameters of a lane shape model. The proposed method is validated on the TuSimple benchmark and shows state-of-the-art accuracy with the most lightweight model size and fastest speed.
  arXiv  Detail & Related papers  (2020-11-09T07:42:55Z)
• DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search [55.164053971213576]
  convolutional neural network has achieved great success in fulfilling computer vision tasks despite large computation overhead. Structured (channel) pruning is usually applied to reduce the model redundancy while preserving the network structure. Existing structured pruning methods require hand-crafted rules which may lead to tremendous pruning space.
  arXiv  Detail & Related papers  (2020-11-04T07:43:01Z)
• Lane Detection Model Based on Spatio-Temporal Network With Double Convolutional Gated Recurrent Units [11.968518335236787]
  Lane detection will remain an open problem for some time to come. A-temporal network with double Conal Gated Recurrent Units (ConvGRUs) proposed to address lane detection in challenging scenes. Our model can outperform the state-of-the-art lane detection models.
  arXiv  Detail & Related papers  (2020-08-10T06:50:48Z)
• CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending [102.98909328368481]
  CurveLane-NAS is a novel lane-sensitive architecture search framework. It captures both long-ranged coherent and accurate short-range curve information. It unifies both architecture search and post-processing on curve lane predictions via point blending.
  arXiv  Detail & Related papers  (2020-07-23T17:23:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.