arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.10863cs.CVcs.RO
收藏

RV-FuseNet:基于距离视图的时间序列LiDAR数据融合三维目标检测和运动预测

RV-FuseNet: Range View Based Fusion of Time-Series LiDAR Data for Joint 3D Object Detection and Motion Forecasting

Aurora Innovation(奥罗拉创新公司);Uber Advanced Technologies Group(优步先进技术集团);Motional(动势公司)

Ankit Laddha, Shivam Gautam, Gregory P. Meyer, Carlos Vallespi-Gonzalez, Carl K. Wellington

摘要:

强大的实时检测和交通参与者的运动预测是必要的自动驾驶汽车安全地在城市环境中导航。在本文中,我们提出了RV-FuseNet,这是一种新的端到端方法,用于直接从时间序列LiDAR数据进行联合检测和轨迹估计。代替广泛使用的鸟瞰图(BEV)表示,我们利用本地范围视图(RV)表示的激光雷达数据。RV通过避免BEV中使用的体素化来保持传感器的全分辨率。此外,由于RV的紧凑性,可以有效地处理RV。以前的方法将时间序列数据投影到一个共同的视点进行时间融合,并且这个视点通常与捕获它的位置不同。这对于BEV方法是足够的,但是对于RV方法,这可能导致信息丢失和数据失真,这对性能具有不利影响。为了解决这一挑战,我们提出了一个简单而有效的新架构,\textit{Incremental Fusion},最大限度地减少信息损失的顺序投影到下一个扫描的角度每个RV扫描的时间。我们表明,我们的方法显着提高了运动预测性能超过现有的国家的最先进的。此外,我们证明了我们的顺序融合方法优于其他RV基于融合方法的多个数据集。

英文摘要:

Robust real-time detection and motion forecasting of traffic participants is necessary for autonomous vehicles to safely navigate urban environments. In this paper, we present RV-FuseNet, a novel end-to-end approach for joint detection and trajectory estimation directly from time-series LiDAR data. Instead of the widely used bird's eye view (BEV) representation, we utilize the native range view (RV) representation of LiDAR data. The RV preserves the full resolution of the sensor by avoiding the voxelization used in the BEV. Furthermore, RV can be processed efficiently due to its compactness. Previous approaches project time-series data to a common viewpoint for temporal fusion, and often this viewpoint is different from where it was captured. This is sufficient for BEV methods, but for RV methods, this can lead to loss of information and data distortion which has an adverse impact on performance. To address this challenge we propose a simple yet effective novel architecture, \textit{Incremental Fusion}, that minimizes the information loss by sequentially projecting each RV sweep into the viewpoint of the next sweep in time. We show that our approach significantly improves motion forecasting performance over the existing state-of-the-art. Furthermore, we demonstrate that our sequential fusion approach is superior to alternative RV based fusion methods on multiple datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑