Li, Q. and Zhao, Q. (2023) Weakly-Supervised Semantic Segmentation of Airborne LiDAR Point Clouds in Hong Kong Urban Areas. In: 2023 Joint Urban Remote Sensing Event (JURSE), Heraklion, Greece, 17-19 May 2023, ISBN 9781665493734 (doi: 10.1109/JURSE57346.2023.10144215)
![]() |
Text
300530.pdf - Accepted Version Available under License Creative Commons Attribution. 530kB |
Abstract
Semantic segmentation of airborne LiDAR point clouds of urban areas is an essential process prior to applying LiDAR data to further applications such as 3D city modeling. Large-scale point cloud semantic segmentation is challenging in practical applications due to the massive data size and time-consuming point-wise annotation. This paper applied weakly-supervised Semantic Query Network and sparse points annotation pipeline to practical airborne LiDAR datasets for urban scene semantic segmentation in Hong Kong. The experiment result obtained the overall accuracy over 84% and the mean intersect over union over 75%. The capacity of intensity and return attributes of LiDAR data to classify the vegetation and construction was explored and discussed. This work demonstrates an efficient workflow of large-scale airborne LiDAR point cloud semantic segmentation in practice.
Item Type: | Conference Proceedings |
---|---|
Additional Information: | This work is supported by the ESRC to the Urban Big Data Centre [ES/L011921/1 and ES/ S007105/1] and is also funded by the Glasgow City Council. |
Status: | Published |
Refereed: | Yes |
Glasgow Author(s) Enlighten ID: | Zhao, Dr Qunshan and Li, Dr Qiaosi |
Authors: | Li, Q., and Zhao, Q. |
College/School: | College of Social Sciences > School of Social and Political Sciences > Urban Studies |
ISSN: | 2642-9535 |
ISBN: | 9781665493734 |
Copyright Holders: | Copyright © 2023 IEEE |
First Published: | First published in Proceedings of the 2023 Joint Urban Remote Sensing Event (JURSE) |
Publisher Policy: | Reproduced in accordance with the copyright policy of the publisher |
University Staff: Request a correction | Enlighten Editors: Update this record