Vegetation land segmentation with multi-modal and multi-temporal remote sensing images: a temporal learning approach and a new dataset

In recent years, remote sensing analysis has gained significant attention in visual analysis applications, particularly in segmenting and recognizing remote sensing images. However, the existing research has predominantly focused on single-period RGB image analysis, thus overlooking the complexities...

Full description

Saved in:
Bibliographic Details
Main Authors: Qu, Fang, Sun, Youqiang, Zhou, Man, Liu, Liu, Yang, Huamin, Zhang, Junqing, Huang, He, Hong, Danfeng
Other Authors: College of Computing and Data Science
Format: Article
Language:English
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10356/178519
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-178519
record_format dspace
spelling sg-ntu-dr.10356-1785192024-06-25T03:00:20Z Vegetation land segmentation with multi-modal and multi-temporal remote sensing images: a temporal learning approach and a new dataset Qu, Fang Sun, Youqiang Zhou, Man Liu, Liu Yang, Huamin Zhang, Junqing Huang, He Hong, Danfeng College of Computing and Data Science S-Lab Computer and Information Science Multi-temporal VRSFormer In recent years, remote sensing analysis has gained significant attention in visual analysis applications, particularly in segmenting and recognizing remote sensing images. However, the existing research has predominantly focused on single-period RGB image analysis, thus overlooking the complexities of remote sensing image capture, especially in highly vegetated land parcels. In this paper, we provide a large-scale vegetation remote sensing (VRS) dataset and introduce the VRS-Seg task for multi-modal and multi-temporal vegetation segmentation. The VRS dataset incorporates diverse modalities and temporal variations, and its annotations are organized using the Vegetation Knowledge Graph (VKG), thereby providing detailed object attribute information. To address the VRS-Seg task, we introduce VRSFormer, a critical pipeline that integrates multi-temporal and multi-modal data fusion, geometric contour refinement, and category-level classification inference. The experimental results demonstrate the effectiveness and generalization capability of our approach. The availability of VRS and the VRS-Seg task paves the way for further research in multi-modal and multi-temporal vegetation segmentation in remote sensing imagery. Published version This research was funded by the National Key Research and Development Program of China (grant number 2021YFD200060102), the Strategic Priority Research Program of the Chinese Academy of Sciences (grant number XDA28120402), and the HFIPS Director’s Fund (grant number 2023YZGH04). 2024-06-25T03:00:20Z 2024-06-25T03:00:20Z 2024 Journal Article Qu, F., Sun, Y., Zhou, M., Liu, L., Yang, H., Zhang, J., Huang, H. & Hong, D. (2024). Vegetation land segmentation with multi-modal and multi-temporal remote sensing images: a temporal learning approach and a new dataset. Remote Sensing, 16(1), 3-. https://dx.doi.org/10.3390/rs16010003 2072-4292 https://hdl.handle.net/10356/178519 10.3390/rs16010003 2-s2.0-85181943542 1 16 3 en Remote Sensing © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
Multi-temporal
VRSFormer
spellingShingle Computer and Information Science
Multi-temporal
VRSFormer
Qu, Fang
Sun, Youqiang
Zhou, Man
Liu, Liu
Yang, Huamin
Zhang, Junqing
Huang, He
Hong, Danfeng
Vegetation land segmentation with multi-modal and multi-temporal remote sensing images: a temporal learning approach and a new dataset
description In recent years, remote sensing analysis has gained significant attention in visual analysis applications, particularly in segmenting and recognizing remote sensing images. However, the existing research has predominantly focused on single-period RGB image analysis, thus overlooking the complexities of remote sensing image capture, especially in highly vegetated land parcels. In this paper, we provide a large-scale vegetation remote sensing (VRS) dataset and introduce the VRS-Seg task for multi-modal and multi-temporal vegetation segmentation. The VRS dataset incorporates diverse modalities and temporal variations, and its annotations are organized using the Vegetation Knowledge Graph (VKG), thereby providing detailed object attribute information. To address the VRS-Seg task, we introduce VRSFormer, a critical pipeline that integrates multi-temporal and multi-modal data fusion, geometric contour refinement, and category-level classification inference. The experimental results demonstrate the effectiveness and generalization capability of our approach. The availability of VRS and the VRS-Seg task paves the way for further research in multi-modal and multi-temporal vegetation segmentation in remote sensing imagery.
author2 College of Computing and Data Science
author_facet College of Computing and Data Science
Qu, Fang
Sun, Youqiang
Zhou, Man
Liu, Liu
Yang, Huamin
Zhang, Junqing
Huang, He
Hong, Danfeng
format Article
author Qu, Fang
Sun, Youqiang
Zhou, Man
Liu, Liu
Yang, Huamin
Zhang, Junqing
Huang, He
Hong, Danfeng
author_sort Qu, Fang
title Vegetation land segmentation with multi-modal and multi-temporal remote sensing images: a temporal learning approach and a new dataset
title_short Vegetation land segmentation with multi-modal and multi-temporal remote sensing images: a temporal learning approach and a new dataset
title_full Vegetation land segmentation with multi-modal and multi-temporal remote sensing images: a temporal learning approach and a new dataset
title_fullStr Vegetation land segmentation with multi-modal and multi-temporal remote sensing images: a temporal learning approach and a new dataset
title_full_unstemmed Vegetation land segmentation with multi-modal and multi-temporal remote sensing images: a temporal learning approach and a new dataset
title_sort vegetation land segmentation with multi-modal and multi-temporal remote sensing images: a temporal learning approach and a new dataset
publishDate 2024
url https://hdl.handle.net/10356/178519
_version_ 1814047071742722048