A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images
It is very significant for rural planning to accurately count the number and area of rural homesteads by means of automation. The development of deep learning makes it possible to achieve this goal. At present, many effective works have been conducted to extract building objects from VHR images usin...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/7/3643 |
_version_ | 1797607009871200256 |
---|---|
author | Ren Wei Beilei Fan Yuting Wang Rongchao Yang |
author_facet | Ren Wei Beilei Fan Yuting Wang Rongchao Yang |
author_sort | Ren Wei |
collection | DOAJ |
description | It is very significant for rural planning to accurately count the number and area of rural homesteads by means of automation. The development of deep learning makes it possible to achieve this goal. At present, many effective works have been conducted to extract building objects from VHR images using semantic segmentation technology, but they do not extract instance objects and do not work for densely distributed and overlapping rural homesteads. Most of the existing mainstream instance segmentation frameworks are based on the top-down structure. The model is complex and requires a large number of manually set thresholds. In order to solve the above difficult problems, we designed a simple query-based instance segmentation framework, QueryFormer, which includes an encoder and a decoder. A multi-scale deformable attention mechanism is incorporated into the encoder, resulting in significant computational savings, while also achieving effective results. In the decoder, we designed multiple groups, and used a Many-to-One label assignment method to make the image feature region be queried faster. Experiments show that our method achieves better performance (52.8AP) than the other most advanced models (+0.8AP) in the task of extracting rural homesteads in dense regions. This study shows that query-based instance segmentation framework has strong application potential in remote sensing images. |
first_indexed | 2024-03-11T05:25:16Z |
format | Article |
id | doaj.art-e192fc0e69c049f79dcb4cc0baacf319 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T05:25:16Z |
publishDate | 2023-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-e192fc0e69c049f79dcb4cc0baacf3192023-11-17T17:35:35ZengMDPI AGSensors1424-82202023-03-01237364310.3390/s23073643A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing ImagesRen Wei0Beilei Fan1Yuting Wang2Rongchao Yang3Institute of Agricultural Information, Chinese Academy of Agricultural Sciences, Beijing 100876, ChinaInstitute of Agricultural Information, Chinese Academy of Agricultural Sciences, Beijing 100876, ChinaInstitute of Agricultural Information, Chinese Academy of Agricultural Sciences, Beijing 100876, ChinaInstitute of Agricultural Information, Chinese Academy of Agricultural Sciences, Beijing 100876, ChinaIt is very significant for rural planning to accurately count the number and area of rural homesteads by means of automation. The development of deep learning makes it possible to achieve this goal. At present, many effective works have been conducted to extract building objects from VHR images using semantic segmentation technology, but they do not extract instance objects and do not work for densely distributed and overlapping rural homesteads. Most of the existing mainstream instance segmentation frameworks are based on the top-down structure. The model is complex and requires a large number of manually set thresholds. In order to solve the above difficult problems, we designed a simple query-based instance segmentation framework, QueryFormer, which includes an encoder and a decoder. A multi-scale deformable attention mechanism is incorporated into the encoder, resulting in significant computational savings, while also achieving effective results. In the decoder, we designed multiple groups, and used a Many-to-One label assignment method to make the image feature region be queried faster. Experiments show that our method achieves better performance (52.8AP) than the other most advanced models (+0.8AP) in the task of extracting rural homesteads in dense regions. This study shows that query-based instance segmentation framework has strong application potential in remote sensing images.https://www.mdpi.com/1424-8220/23/7/3643VHR remote sensing imagesrural homesteadinstance segmentationquery-basedmulti-scale deformable attentiongroup queries |
spellingShingle | Ren Wei Beilei Fan Yuting Wang Rongchao Yang A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images Sensors VHR remote sensing images rural homestead instance segmentation query-based multi-scale deformable attention group queries |
title | A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images |
title_full | A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images |
title_fullStr | A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images |
title_full_unstemmed | A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images |
title_short | A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images |
title_sort | query based network for rural homestead extraction from vhr remote sensing images |
topic | VHR remote sensing images rural homestead instance segmentation query-based multi-scale deformable attention group queries |
url | https://www.mdpi.com/1424-8220/23/7/3643 |
work_keys_str_mv | AT renwei aquerybasednetworkforruralhomesteadextractionfromvhrremotesensingimages AT beileifan aquerybasednetworkforruralhomesteadextractionfromvhrremotesensingimages AT yutingwang aquerybasednetworkforruralhomesteadextractionfromvhrremotesensingimages AT rongchaoyang aquerybasednetworkforruralhomesteadextractionfromvhrremotesensingimages AT renwei querybasednetworkforruralhomesteadextractionfromvhrremotesensingimages AT beileifan querybasednetworkforruralhomesteadextractionfromvhrremotesensingimages AT yutingwang querybasednetworkforruralhomesteadextractionfromvhrremotesensingimages AT rongchaoyang querybasednetworkforruralhomesteadextractionfromvhrremotesensingimages |