用于鲁棒车道检测的结构增强特征与质量感知动态锚点评分
Structure-Enhanced Features and Quality-Aware Dynamic Anchor Scoring for Robust Lane Detection
- RWTH Aachen University（亚琛工业大学）
- Delft University of Technology（代尔夫特理工大学）
- Chang’an University（长安大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
该研究针对车道检测中锚点检测器的结构连续性丢失与置信度-定位质量解耦问题，提出含GHVT模块与LQAS的框架，在ADNet基础上提升VIL-100等数据集的F1分数，计算开销极小。
中文摘要 AI 辅助
车道检测需要在复杂驾驶场景下恢复纤细、细长且常被遮挡的车道结构。尽管基于锚点的检测器能高效生成候选区域，但受两个耦合问题限制：骨干网络特征在部分可见车道上常丢失结构连续性，且分类置信度可能与线级定位质量解耦，导致不准确的锚点在非极大值抑制（NMS）前仍被保留。我们提出一种结构增强且质量感知的框架，在保留锚点分解网络（ADNet）推理流程的同时，改进车道表示与动态锚点评分。具体而言，门控水平-垂直令牌（GHVT）模块通过带可学习残差门的轻量方向令牌交互，增强中、高层骨干网络特征；同时，线质量感知动态锚点评分（LQAS）利用质量监督、难负样本抑制与成对排序校准现有分类逻辑，无需额外推理分支。在VIL-100数据集上，本方法将ADNet-R34在0.5交并比阈值下的F1分数（F1@50）从89.97提升至91.28，同时降低了误检与漏检。在CULane、TuSimple数据集上的额外实验、广泛的 ablation 研究、分数分布诊断及运行时间分析，均证实了结构与排序改进的互补性，且计算开销极小。
英文摘要
Lane detection requires recovering thin, elongated, and frequently occluded lane structures under challenging driving conditions. While anchor-based detectors provide efficient candidate generation, their performance is limited by two coupled issues: backbone features often lose structural continuity along partially visible lanes, and classification confidence may decouple from line-level localization quality, allowing inaccurate anchors to persist before non-maximum suppression (NMS). We propose a structure-enhanced and quality-aware framework that improves lane representation and dynamic-anchor scoring while preserving the inference pipeline of the Anchor Decomposition Network (ADNet). Specifically, a Gated Horizontal-Vertical Token (GHVT) module enhances mid- and high-level backbone features via lightweight directional token interactions with a learnable residual gate. In parallel, Line-Quality-Aware Dynamic Anchor Scoring (LQAS) calibrates existing classification logits using quality supervision, hard-negative suppression, and pairwise ranking without adding inference branches. On the VIL-100 dataset, our method improves ADNet-R34 from 89.97 to 91.28 in F1 score at the 0.5 intersection-over-union threshold (F1@50), reducing both false positives and false negatives. Additional experiments on CULane and TuSimple datasets, extensive ablations, score-distribution diagnostics, and runtime analysis confirm complementary structural and ranking improvements with minimal computational overhead.
