Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/111843
PIRA download icon_1.1View/Download Full Text
Title: An end-to-end geometric characterization-aware semantic instance segmentation network for ALS point clouds
Authors: Wang, J 
Yao, W 
Issue Date: 2024
Source: International archives of the photogrammetry, remote sensing and spatial information sciences, 2024, v. XLVIII-2-2024, p. 435-442
Abstract: Semantic instance segmentation from scenes, serving as a crucial role for 3D modelling and scene understanding. Conducting semantic segmentation before grouping instances is adopted by the existing state-of-the-art methods. However, without additional refinement, semantic errors will fully propagate into the grouping stage, resulting in low overlap with the ground truth instance. Furthermore, the proposed methods focused on indoor level scenes, which are limited when directly applied to large-scale outdoor Airborne Laser Scanning (ALS) point clouds. Numerous instances, significant object density and scale variations make ALS point clouds distinct from indoor data. In order to address the problems, we proposed a geometric characterization-aware semantic instance segmentation network, which utilized both semantic and objectness score to select potential points for grouping. And in point cloud feature learning stage, hand-craft geometry features are taken as input for geometric characterization awareness. Moreover, to address errors propagated from previous modules after grouping, we have additionally designed a per-instance refinement module. To assess semantic instance segmentation, we conducted experiments on an open-source dataset. Additionally, we performed semantic segmentation experiments to evaluate the performance of our proposed point cloud feature learning method.
Keywords: Airborne Laser Scanning (ALS)
Deep learning
Geometric characterization
Point clouds
Semantic instance segmentation
Publisher: Copernicus GmbH
Journal: International archives of the photogrammetry, remote sensing and spatial information sciences 
ISSN: 1682-1750
EISSN: 2194-9034
DOI: 10.5194/isprs-archives-XLVIII-2-2024-435-2024
Rights: © Author(s) 2024. This work is distributed under the Creative Commons Attribution 4.0 License (https://creativecommons.org/licenses/by/4.0/).
The following publication Wang, J. and Yao, W.: An End-to-End Geometric Characterization-aware Semantic Instance Segmentation Network for ALS Point Clouds, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-2-2024, 435–442 is available at https://doi.org/10.5194/isprs-archives-XLVIII-2-2024-435-2024.
Appears in Collections:Conference Paper

Files in This Item:
File Description SizeFormat 
isprs-archives-XLVIII-2-2024-435-2024.pdf1.47 MBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

4
Citations as of Apr 1, 2025

Downloads

2
Citations as of Apr 1, 2025

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.