Affiliation(s):
Shanghai Key Laboratory of Data Science, the School of Computer Science, Fudan University, Shanghai, 200433, China Zhuhai Fudan Innovation Institute, Hengqin New Area, Zhuhai, Guangdong, 519000, China
Liwen Liu, Weidong Yang, Ben Fei. GeeNet: Robust and Fast Point Cloud Completion for Ground Elevation Estimation towards Autonomous Vehicles[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2300388
@article{title="GeeNet: Robust and Fast Point Cloud Completion for Ground Elevation Estimation towards Autonomous Vehicles", author="Liwen Liu, Weidong Yang, Ben Fei", journal="Frontiers of Information Technology & Electronic Engineering", year="in press", publisher="Zhejiang University Press & Springer", doi="https://doi.org/10.1631/FITEE.2300388" }
%0 Journal Article %T GeeNet: Robust and Fast Point Cloud Completion for Ground Elevation Estimation towards Autonomous Vehicles %A Liwen Liu %A Weidong Yang %A Ben Fei %J Frontiers of Information Technology & Electronic Engineering %P %@ 2095-9184 %D in press %I Zhejiang University Press & Springer doi="https://doi.org/10.1631/FITEE.2300388"
TY - JOUR T1 - GeeNet: Robust and Fast Point Cloud Completion for Ground Elevation Estimation towards Autonomous Vehicles A1 - Liwen Liu A1 - Weidong Yang A1 - Ben Fei J0 - Frontiers of Information Technology & Electronic Engineering SP - EP - %@ 2095-9184 Y1 - in press PB - Zhejiang University Press & Springer ER - doi="https://doi.org/10.1631/FITEE.2300388"
Abstract: Ground elevation estimation is vital for numerous applications in autonomous vehicles and intelligent robotics including 3D object detection, navigable space detection, point cloud matching for localization and registration for mapping. However, most works regard the ground as a plane without height information, which causes inaccurate manipulation in these applications. Therefore, 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 2D/3D convolutions to preserve lightweight architecture to regress ground elevation information for each cell of the grid. For the first time, GeeNet fulfills ground elevation estimation from semantic scene completion. We utilize the SemanticKITTI and SemanticPOSS datasets to validate the proposed GeeNet. It is demonstrated the qualitative and quantitative performance of GeeNet on ground elevation estimation and semantic scene completion of the point cloud. Moreover, the cross-dataset generalization capability of GeeNet is also experimentally proven. GeeNet achieves state-of-the-art performance and fulfills a run-time of 220 Hz for ground elevation estimation and ground completion.
Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article
Reference
Open peer comments: Debate/Discuss/Question/Opinion
Open peer comments: Debate/Discuss/Question/Opinion
<1>