Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/19393
Title: | Deep learning model for accurate vegetation classification using RGB image only | Authors: | Ayhan, Bulent Kwan, Chiman Larkin, Jude Kwan, Liyun Skarlatos, Dimitrios Vlachos, Marinos |
Major Field of Science: | Natural Sciences | Field Category: | Computer and Information Sciences | Keywords: | Deep Learning;DSM;DTM;Image inpainting;Vegetation extraction | Issue Date: | 21-Apr-2020 | Source: | Geospatial Informatics X, 27 April - 8 May 2020, United States | Conference: | Geospatial Informatics | Abstract: | The objective of this paper is to detect the type of vegetation so that a more accurate Digital Terrain Model (DTM) can be generated by excluding the vegetation from the Digital Surface Model (DSM) based on the vegetation type (such as trees). This way, many different inpainting methods can be applied subsequently to restore the terrain information from the removed vegetation pixels from DSM and obtain a more accurate DTM. We trained three DeepLabV3+ models with three different datasets that are collected at different resolutions. Among the three DeepLabV3+ models, the model trained with the dataset that has an image resolution close to the test data images provided the best performance and the semantic segmentation results with this model looked highly promising. | URI: | https://hdl.handle.net/20.500.14279/19393 | ISBN: | 978-151063573-9 | DOI: | 10.1117/12.2557833 | Rights: | © SPIE Attribution-NonCommercial-NoDerivatives 4.0 International |
Type: | Conference Papers | Affiliation : | Applied Research LLC Cyprus University of Technology |
Publication Type: | Peer Reviewed |
Appears in Collections: | Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation |
CORE Recommender
SCOPUSTM
Citations
5
checked on Nov 6, 2023
Page view(s)
300
Last Week
0
0
Last month
2
2
checked on Dec 24, 2024
Google ScholarTM
Check
Altmetric
This item is licensed under a Creative Commons License