arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.11901cs.CVcs.LG
收藏

传感器数据的多视图融合,以改善自动驾驶中的感知和预测

Multi-View Fusion of Sensor Data for Improved Perception and Prediction in Autonomous Driving

Aurora Innovation;Uber ATG

Sudeep Fadadu, Shreyash Pandey, Darshan Hegde, Yi Shi, Fang-Chieh Chou, Nemanja Djuric, Carlos Vallespi-Gonzalez

摘要:

我们提出了一种端到端的方法,利用激光雷达返回和相机图像的多视图表示的目标检测和轨迹预测。在这项工作中,我们认识到不同的视图表示的优点和缺点,我们提出了一个有效的和通用的融合方法,从所有的意见汇总的好处。我们的模型建立在最先进的鸟瞰图(BEV)网络上,该网络融合了历史LiDAR数据序列中的体素化特征以及栅格化的高清地图,以执行检测和预测任务。我们扩展了这个模型与额外的激光雷达范围视图(RV)功能,使用其原生的,非量化表示的原始激光雷达信息。将RV特征图投影到BEV中,并与LiDAR和高清地图计算的BEV特征融合。然后,融合的特征被进一步处理,以在单个端到端可训练网络内输出最终检测和轨迹。此外,RV融合的LiDAR和相机是在一个简单的和计算效率的方式使用这个框架。所提出的多视图融合方法改进了由自动驾驶车辆车队收集的专有大规模真实世界数据以及公共nuScenes数据集的最新技术,同时计算成本的增加最小。

英文摘要:

We present an end-to-end method for object detection and trajectory prediction utilizing multi-view representations of LiDAR returns and camera images. In this work, we recognize the strengths and weaknesses of different view representations, and we propose an efficient and generic fusing method that aggregates benefits from all views. Our model builds on a state-of-the-art Bird's-Eye View (BEV) network that fuses voxelized features from a sequence of historical LiDAR data as well as rasterized high-definition map to perform detection and prediction tasks. We extend this model with additional LiDAR Range-View (RV) features that use the raw LiDAR information in its native, non-quantized representation. The RV feature map is projected into BEV and fused with the BEV features computed from LiDAR and high-definition map. The fused features are then further processed to output the final detections and trajectories, within a single end-to-end trainable network. In addition, the RV fusion of LiDAR and camera is performed in a straightforward and computationally efficient manner using this framework. The proposed multi-view fusion approach improves the state-of-the-art on proprietary large-scale real-world data collected by a fleet of self-driving vehicles, as well as on the public nuScenes data set with minimal increases on the computational cost.

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。

↑