Skip to main content
QUICK REVIEW

[论文解读] A Keypoint-based Global Association Network for Lane Detection

Jinsheng Wang, Yinchao Ma|arXiv (Cornell University)|Apr 15, 2022
Autonomous Vehicle Technology and Safety被引用 10
一句话总结

该论文提出了一种用于车道检测的全局关联网络(GANet),将关键点关联建模为对车道起点的直接回归,从而实现并行、高效且鲁棒的全局关联。通过引入一种车道感知特征聚合模块(LFA)以增强局部上下文,GANet在CULane数据集上达到79.63%的F1分数,在Tusimple数据集上达到97.71%的F1分数,同时保持了较高的推理速度。

ABSTRACT

Lane detection is a challenging task that requires predicting complex topology shapes of lane lines and distinguishing different types of lanes simultaneously. Earlier works follow a top-down roadmap to regress predefined anchors into various shapes of lane lines, which lacks enough flexibility to fit complex shapes of lanes due to the fixed anchor shapes. Lately, some works propose to formulate lane detection as a keypoint estimation problem to describe the shapes of lane lines more flexibly and gradually group adjacent keypoints belonging to the same lane line in a point-by-point manner, which is inefficient and time-consuming during postprocessing. In this paper, we propose a Global Association Network (GANet) to formulate the lane detection problem from a new perspective, where each keypoint is directly regressed to the starting point of the lane line instead of point-by-point extension. Concretely, the association of keypoints to their belonged lane line is conducted by predicting their offsets to the corresponding starting points of lanes globally without dependence on each other, which could be done in parallel to greatly improve efficiency. In addition, we further propose a Lane-aware Feature Aggregator (LFA), which adaptively captures the local correlations between adjacent keypoints to supplement local information to the global association. Extensive experiments on two popular lane detection benchmarks show that our method outperforms previous methods with F1 score of 79.63% on CULane and 97.71% on Tusimple dataset with high FPS. The code will be released at https://github.com/Wolfwjs/GANet.

研究动机与目标

  • 为解决现有基于关键点的车道检测方法中逐点关联带来的效率低下与误差累积问题。
  • 通过用可学习的关键点表示替代固定的锚框先验,提升对复杂车道形状建模的灵活性。
  • 通过直接回归到车道起点,实现关键点到车道的并行、全局关联。
  • 通过可学习的、车道感知的特征聚合模块,增强沿车道线的局部特征表示。
  • 在标准基准上同时实现高精度与高推理速度。

提出的方法

  • 将车道检测建模为从每个关键点预测到其对应车道线起点的偏移量,从而实现全局、独立的关联。
  • 引入一种车道感知特征聚合模块(LFA),通过预测的偏移量在车道线上相邻点处采样特征,使用可变形卷积实现。
  • 引入辅助损失,引导LFA模块聚焦于车道线上的相关局部特征。
  • 采用两阶段流程:先预测关键点置信度,再进行全局偏移回归与后处理分组。
  • 通过预测偏移量在车道对齐的局部区域内采样,对2D可变形卷积进行适配,以实现更优的特征聚合。
  • 在后处理中应用非极大值抑制(NMS)以优化最终的车道线预测结果。

实验结果

研究问题

  • RQ1直接回归到车道起点的全局关键点关联是否能相比逐点分组方式提升效率与鲁棒性?
  • RQ2通过车道感知模块引入局部特征聚合,对车道检测精度有何影响?
  • RQ3与自回归关键点扩展相比,全局关联机制是否能减少误差传播?
  • RQ4辅助监督对LFA模块捕捉局部车道结构能力有何影响?
  • RQ5在标准基准上,该方法与基于锚框和基于关键点的基线模型相比,在精度与速度方面表现如何?

主要发现

  • GANet在CULane基准上取得了79.63%的新SOTA F1分数,优于先前方法。
  • 在Tusimple数据集上,GANet-S以高推理速度实现97.71%的F1分数,超越了同等FPS的模型。
  • 消融实验表明,加入辅助损失的LFA模块相比基线使F1提升0.95个百分点(78.79 vs. 77.84)。
  • 可视化结果表明,LFA增强了特征表示,抑制了背景噪声,并在遮挡情况下保持了高精度。
  • 该方法在复杂场景中表现更优,尤其在Curve场景下,F1分数比ERF-E2E高出5%以上。
  • 全局关联机制支持并行后处理,相比顺序关键点分组,显著提升了推理效率。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。