用卫星图做先验，提升自动驾驶高精地图构建精度
SatMap: Revisiting Satellite Maps as Prior for Online HD Map Construction
- 结合卫星图与多视角摄像头，直接生成矢量高精地图
- 在nuScenes上比纯摄像头方法高34.8%地图识别准确率
- 适用于长距离和恶劣天气，对遮挡和深度模糊有强鲁棒性
在线高精（HD）地图构建是安全可靠端到端自动驾驶系统的关键环节。基于车载摄像头的方法受限于深度感知能力，且易受遮挡影响导致精度下降。本文提出SatMap，一种将卫星地图与多视角相机观测融合的在线矢量化高精地图估计方法，可直接输出下游预测与规划模块可用的矢量地图。该方法利用鸟瞰视角卫星影像提供的车道级语义与纹理作为全局先验，有效缓解深度模糊与遮挡问题。在nuScenes数据集上的实验表明，SatMap相比纯摄像头基线提升34.8% mAP，相比摄像头-激光雷达融合基线提升8.5% mAP。此外，我们在长距离及恶劣天气条件下评估模型，验证了卫星先验地图的优势。源代码将公开于https://iv.ee.hm.edu/satmap/。
原文摘要 · Abstract (English)
Online high-definition (HD) map construction is an essential part of a safe and robust end-to-end autonomous driving (AD) pipeline. Onboard camera-based approaches suffer from limited depth perception and degraded accuracy due to occlusion. In this work, we propose SatMap, an online vectorized HD map estimation method that integrates satellite maps with multi-view camera observations and directly predicts a vectorized HD map for downstream prediction and planning modules. Our method leverages lane-level semantics and texture from satellite imagery captured from a Bird's Eye View (BEV) perspective as a global prior, effectively mitigating depth ambiguity and occlusion. In our experiments on the nuScenes dataset, SatMap achieves 34.8% mAP performance improvement over the camera-only baseline and 8.5% mAP improvement over the camera-LiDAR fusion baseline. Moreover, we evaluate our model in long-range and adverse weather conditions to demonstrate the advantages of using a satellite prior map. Source code will be available at https://iv.ee.hm.edu/satmap/.
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。