Sketch and Refine：迈向快速且精准的车道检测
Sketch and Refine: Towards Fast and Accurate Lane Detection
AI总结：
针对现有车道检测方法在表示灵活性或后处理上的不足，提出融合两类方法优势的“勾勒-细化”范式与SRLane检测器，实现278 FPS高速运行且F1达78.9%。
摘要：
车道检测旨在确定道路上车道的精确位置与形状。尽管现有方法已做出诸多努力，但受真实场景复杂性影响，该任务仍具挑战性。现有方法无论是基于候选框（proposal-based）还是基于关键点（keypoint-based）的，都难以高效且有效地刻画车道。基于候选框的方法以 streamlined 自上而下的方式区分并回归一组候选框来检测车道，但在车道表示上灵活性不足。另一方面，基于关键点的方法从局部描述符灵活构建车道，通常需要复杂的后处理。\n本文提出一种“Sketch-and-Refine（勾勒-细化）”范式，融合了基于关键点与基于候选框方法的优势。其核心动机是：车道的局部方向在语义上简单清晰。在“Sketch（勾勒）”阶段，可通过快速卷积层轻松估计关键点的局部方向，随后据此构建一组精度适中的车道候选框。在“Refine（细化）”阶段，我们通过新颖的 Lane Segment Association Module（LSAM，车道段关联模块）进一步优化这些候选框，该模块支持自适应车道段调整。最后，我们提出多级特征融合，以更高效地丰富车道特征表示。\n基于所提出的“Sketch and Refine”范式，我们构建了一款快速且高效的车道检测器，命名为 SRLane。实验表明，我们的 SRLane 可实现 278 FPS 的高速运行，同时取得 78.9% 的 F1 分数。源代码可在以下链接获取：https://github.com/passerer/SRLane。
英文摘要：
Lane detection is to determine the precise location and shape of lanes on the road. Despite efforts made by current methods, it remains a challenging task due to the complexity of real-world scenarios. Existing approaches, whether proposal-based or keypoint-based, suffer from depicting lanes effectively and efficiently. Proposal-based methods detect lanes by distinguishing and regressing a collection of proposals in a streamlined top-down way, yet lack sufficient flexibility in lane representation. Keypoint-based methods, on the other hand, construct lanes flexibly from local descriptors, which typically entail complicated post-processing. In this paper, we present a "Sketch-and-Refine" paradigm that utilizes the merits of both keypoint-based and proposal-based methods. The motivation is that local directions of lanes are semantically simple and clear. At the "Sketch" stage, local directions of keypoints can be easily estimated by fast convolutional layers. Then we can build a set of lane proposals accordingly with moderate accuracy. At the "Refine" stage, we further optimize these proposals via a novel Lane Segment Association Module (LSAM), which allows adaptive lane segment adjustment. Last but not least, we propose multi-level feature integration to enrich lane feature representations more efficiently. Based on the proposed "Sketch and Refine" paradigm, we propose a fast yet effective lane detector dubbed "SRLane". Experiments show that our SRLane can run at a fast speed (i.e., 278 FPS) while yielding an F1 score of 78.9\%. The source code is available at: https://github.com/passerer/SRLane.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
