用交通级刚性运动建模雷达点云，提升自动驾驶运动感知精度
TARS: Traffic-Aware Radar Scene Flow Estimation
- 在交通层级利用刚性运动假设，融合目标检测特征增强雷达场景流理解
- 在自研数据集和View-of-Delft上分别提升23%和15%的性能基准
- 适合做雷达感知、自动驾驶场景流任务的研究者与工程师参考
场景流为自动驾驶提供关键运动信息。现有激光雷达场景流模型在实例层级采用刚性运动假设，但该方法不适用于稀疏雷达点云。本文提出一种新型交通级雷达场景流（TARS）估计方法，将刚性运动假设提升至交通层级。通过联合进行目标检测与场景流估计，并利用检测器生成的特征图（以检测损失训练）来增强雷达场景流对环境与道路使用者的感知能力。基于此，在特征空间构建交通向量场（TVF），实现场景流分支中全局交通级理解。在估计场景流时，同时考虑点邻域的点级运动线索与空间内交通级刚性运动一致性。TARS在自研数据集和View-of-Delft数据集上均优于现有最优方法，性能分别提升23%和15%。
原文摘要 · Abstract (English)
Scene flow provides crucial motion information for autonomous driving. Recent LiDAR scene flow models utilize the rigid-motion assumption at the instance level, assuming objects are rigid bodies. However, these instance-level methods are not suitable for sparse radar point clouds. In this work, we present a novel Traffic-Aware Radar Scene-Flow (TARS) estimation method, which utilizes motion rigidity at the traffic level. To address the challenges in radar scene flow, we perform object detection and scene flow jointly and boost the latter. We incorporate the feature map from the object detector, trained with detection losses, to make radar scene flow aware of the environment and road users. From this, we construct a Traffic Vector Field (TVF) in the feature space to achieve holistic traffic-level scene understanding in our scene flow branch. When estimating the scene flow, we consider both point-level motion cues from point neighbors and traffic-level consistency of rigid motion within the space. TARS outperforms the state of the art on a proprietary dataset and the View-of-Delft dataset, improving the benchmarks by 23% and 15%, respectively.
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。