AI 中文总结
研究高速赛车场景下的3D车道检测问题，通过新数据集比较多种方法，提出改进措施，利用多摄像头集成及里程计等提升性能，相比其他方法提高了F1分数并降低误差，在车辆部署中取得良好指标。
AI 中文摘要
车道边界检测是自动驾驶系统的关键组成部分，在常规驾驶场景中已得到深入研究。然而，在赛车领域，汽车以更高速度行驶且道路几何形状更极端，对此研究较少。为研究此问题，我们引入了一个用于赛车3D车道检测的新数据集，包含来自多个摄像头的超25万张图像以及雷克萨斯LC 500在封闭赛道上行驶时的惯性测量数据。利用该数据集，我们比较了各种3D车道检测方法，并提出改进措施，能以近300Hz的速率处理帧，同时在赛车应用中保持高预测性能。这促进了一种在硬件上得到验证的多摄像头集成方法。我们表明，像惯性测量这样的传感模态可用于预积分，以在摄像头和时间上回归道路几何形状，从而改善关键指标。与BevLaneDet等方法相比，添加里程计和集成预测可将F1分数提高3分，并将车辆附近的平均绝对误差降低超30%。在车辆部署中，我们展示了F1分数大于\(0.9\)且横向平均绝对误差小于\(0.18\)米。
英文摘要
Lane boundary detection is a critical component in autonomous driving systems and has been rigorously studied in regular driving scenarios. However, it is less explored in vehicle racing, where the car moves at higher speeds across more extreme road geometries. To study this problem, we introduce a new dataset for 3D lane detection in racing, featuring >$250$k images from multiple camera feeds and inertial measurements taken with a Lexus LC 500 driving on a closed circuit. With this dataset, we compare various approaches to 3D lane detection and propose modifications that permit frames to be processed at rates of almost 300Hz while retaining high predictive performance in the racing application. This facilitates a multi-camera ensemble approach that is validated on hardware. We show that sensing modalities such as inertial measurements can be leveraged for pre-integration to regress road geometries over both cameras and time, yielding improvements in key metrics. Compared to methods such as BevLaneDet, adding odometry and ensemble predictions improves the F1 score by 3 points and reduces near-vehicle mean absolute errors (MAEs) by $>30 \%$. We show F1 scores $>$0.9 and lateral MAEs of $<$0.18m in vehicle deployments.
Comments14 pages, IROS paper, includes extended abstract
