GeeNet:robust and fast point cloud completion for ground elevation estimation towards autonomous vehicles

作     者：Liwen LIU Weidong YANG Ben FEI Liwen LIU;Weidong YANG;Ben FEI

作者机构：Shanghai Key Laboratory of Data ScienceSchool of Computer ScienceFudan UniversityShanghai 200433China Zhuhai Fudan Innovation InstituteZhuhai 519000China 

出 版 物：《Frontiers of Information Technology & Electronic Engineering》 (信息与电子工程前沿（英文版）)

年 卷 期：2024年第25卷第7期

页      面：938-950页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the National Natural Science Foundation of China(No.U2033209) 

主　　题：Point cloud completion Ground elevation estimation Real-time Autonomous vehicles 

摘      要：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 localization,and registration for ***,most works regard the ground as a plane without height information,which causes inaccurate manipulation in these *** 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 *** leverages the mixing of two-and three-dimensional convolutions to preserve a lightweight architecture to regress ground elevation information for each cell of the *** the first time,GeeNet has fulfilled ground elevation estimation from semantic scene *** use the SemanticKITTI and SemanticPOSS 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 ***,the crossdataset generalization capability of GeeNet is experimentally *** achieves state-of-the-art performance in terms of point cloud completion and ground elevation estimation,with a runtime of 0.88 ms.