GeeNet:用于自动驾驶汽车地面高程估计的稳健快速点云补全
GeeNet:robust and fast point cloud completion for ground elevation estimation towards autonomous vehicles
刘沥文 1杨卫东 2费奔1
作者信息
- 1. 复旦大学计算机学院数据科学上海重点实验室,中国 上海市,200433
- 2. 复旦大学计算机学院数据科学上海重点实验室,中国 上海市,200433;珠海复旦创新研究院,中国珠海市,519000
- 折叠
摘要
地面高程估计对于无人驾驶汽车和智能机器人的许多应用至关重要,包括三维物体检测、导航空间检测、用于定位的点云匹配和用于建图的配准.然而,现有大多数工作将地面视为没有高度信息的平面,导致这些应用中出现不准确的操作.本文提出一种端到端的轻量级方法GeeNet,可几乎实时地补全地面,同时在基于网格的表示中估计地面高程.GeeNet利用二维/三维卷积的混合来保留轻量级架构,以回归网格每个单元格的地面高程信息.GeeNet首次实现了语义场景补全的地面高程估计.使用SemanticKITTI和SemanticPOSS数据集对GeeNet进行验证,展示了其在地面高程估计和点云语义场景补全方面的定性和定量性能.此外,其跨数据集泛化能力也得到实验证明.相比文献方法,GeeNet取得更好性能,并以0.88 ms运行时实现地面高程估计和地面补全.
Abstract
Ground elevation estimation is vital for numerous applications in autonomous vehicles and intelligent robotics including three-dimensional object detection,navigable space detection,point cloud matching for localiza-tion,and registration for mapping.However,most works regard the ground as a plane without height information,which causes inaccurate manipulation in these applications.In this work,we propose GeeNet,a novel end-to-end,lightweight method that completes the ground in nearly real time and simultaneously estimates the ground elevation in a grid-based representation.GeeNet leverages the mixing of two-and three-dimensional convolutions to preserve a lightweight architecture to regress ground elevation information for each cell of the grid.For the first time,GeeNet has fulfilled ground elevation estimation from semantic scene completion.We use the SemanticKITTI and Seman-ticPOSS datasets to validate the proposed GeeNet,demonstrating the qualitative and quantitative performances of GeeNet on ground elevation estimation and semantic scene completion of the point cloud.Moreover,the cross-dataset generalization capability of GeeNet is experimentally proven.GeeNet achieves state-of-the-art performance in terms of point cloud completion and ground elevation estimation,with a runtime of 0.88 ms.
关键词
点云补全/地面高程估计/实时/自动驾驶车辆Key words
Point cloud completion/Ground elevation estimation/Real-time/Autonomous vehicles引用本文复制引用
基金项目
National Natural Science Foundation of China(U2033209)
出版年
2024
NETL
NSTL
万方数据