统一建模车道与拓扑关系，提升自动驾驶场景理解能力
Unified Modeling of Lane and Lane Topology for Driving Scene Reasoning
- 将车道与拓扑关系统一为连通车道表示，直接从图像特征中感知
- 在OpenLane-V2上达到30.1%和31.8%的TOP_ll指标，优于T²SG方法
- 适用于需要精确车道逻辑关系的自动驾驶感知系统
自动驾驶车辆不仅需感知车道线、交通灯等物理元素，还需理解车道中心线及其拓扑关系等逻辑信息。现有方法多采用先检测后推理的范式，依赖检测结果推导拓扑关系。本文提出统一建模车道与车道拓扑（UniTopo）方法，将车道间拓扑关系表示为连通车道，包括前驱、后继及连接关系。该统一表示使我们能在共享感知流程中同步获取车道位置与拓扑信息，建立从原始图像特征直接感知车道拓扑的新范式。我们在基于Argoverse2和nuScenes构建的OpenLane-V2基准上验证方法，两个子集上的TOP_ll分别达30.1%和31.8%，显著超越现有最优方法T²SG的6.0%和8.6%。
原文摘要 · Abstract (English)
Autonomous vehicles need to perceive not only physical elements in the driving scene, such as lane lines and traffic lights, but also logical elements like lane centerlines and their topology. Existing lane topology reasoning methods typically follow a reasoning-by-detection paradigm, where lane topological relationships are primarily derived from lane detection results. In this paper, we propose an innovative method called Unified Modeling of Lane and Lane Topology (UniTopo), which represents the topological relationships between lanes as connected lanes, encompassing predecessor lanes, successor lanes, and their interconnections. This unified representation of lanes and lane topology allows us to simultaneously obtain both the positions and topological information of lanes within a shared perception pipeline, establishing a new paradigm for directly perceiving lane topology from original image features. We validate our method on the driving scene reasoning benchmark OpenLane-V2, which consists of two subsets, built based on Argoverse2 and nuScenes, respectively. Our method achieves TOP_ll of 30.1% and 31.8% on the two subsets, significantly surpassing the existing state-of-the-art method T^2SG by 6.0% and 8.6%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。