Built-Up Area Change Detection Using Multi-Task Network with Object-Level Refinement
The detection and monitoring of changes in urban buildings, as a major place for human activities, have been considered profoundly in the field of remote sensing. In recent years, comparing with other traditional methods, the deep learning-based methods have become the mainstream methods for urban b...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-02-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/4/957 |
_version_ | 1797476833993687040 |
---|---|
author | Song Gao Wangbin Li Kaimin Sun Jinjiang Wei Yepei Chen Xuan Wang |
author_facet | Song Gao Wangbin Li Kaimin Sun Jinjiang Wei Yepei Chen Xuan Wang |
author_sort | Song Gao |
collection | DOAJ |
description | The detection and monitoring of changes in urban buildings, as a major place for human activities, have been considered profoundly in the field of remote sensing. In recent years, comparing with other traditional methods, the deep learning-based methods have become the mainstream methods for urban building change detection due to their strong learning ability and robustness. Unfortunately, often, it is difficult and costly to obtain sufficient samples for the change detection method development. As a result, the application of the deep learning-based building change detection methods is limited in practice. In our work, we proposed a novel multi-task network based on the idea of transfer learning, which is less dependent on change detection samples by appropriately selecting high-dimensional features for sharing and a unique decoding module. Different from other multi-task change detection networks, with the help of a high-accuracy building mask, our network can fully utilize the prior information from building detection branches and further improve the change detection result through the proposed object-level refinement algorithm. To evaluate the proposed method, experiments on the publicly available WHU Building Change Dataset were conducted. The experimental results show that the proposed method achieves F1 values of 0.8939, 0.9037, and 0.9212, respectively, when 10%, 25%, and 50% of change detection training samples are used for network training under the same conditions, thus, outperforming other methods. |
first_indexed | 2024-03-09T21:08:22Z |
format | Article |
id | doaj.art-9d742cd2d18b4550802f6c74be8b4e56 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-09T21:08:22Z |
publishDate | 2022-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-9d742cd2d18b4550802f6c74be8b4e562023-11-23T21:54:45ZengMDPI AGRemote Sensing2072-42922022-02-0114495710.3390/rs14040957Built-Up Area Change Detection Using Multi-Task Network with Object-Level RefinementSong Gao0Wangbin Li1Kaimin Sun2Jinjiang Wei3Yepei Chen4Xuan Wang5State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan 430079, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, ChinaThe detection and monitoring of changes in urban buildings, as a major place for human activities, have been considered profoundly in the field of remote sensing. In recent years, comparing with other traditional methods, the deep learning-based methods have become the mainstream methods for urban building change detection due to their strong learning ability and robustness. Unfortunately, often, it is difficult and costly to obtain sufficient samples for the change detection method development. As a result, the application of the deep learning-based building change detection methods is limited in practice. In our work, we proposed a novel multi-task network based on the idea of transfer learning, which is less dependent on change detection samples by appropriately selecting high-dimensional features for sharing and a unique decoding module. Different from other multi-task change detection networks, with the help of a high-accuracy building mask, our network can fully utilize the prior information from building detection branches and further improve the change detection result through the proposed object-level refinement algorithm. To evaluate the proposed method, experiments on the publicly available WHU Building Change Dataset were conducted. The experimental results show that the proposed method achieves F1 values of 0.8939, 0.9037, and 0.9212, respectively, when 10%, 25%, and 50% of change detection training samples are used for network training under the same conditions, thus, outperforming other methods.https://www.mdpi.com/2072-4292/14/4/957change detectionmulti-task change detection networkremote sensingobject-level refinement algorithm |
spellingShingle | Song Gao Wangbin Li Kaimin Sun Jinjiang Wei Yepei Chen Xuan Wang Built-Up Area Change Detection Using Multi-Task Network with Object-Level Refinement Remote Sensing change detection multi-task change detection network remote sensing object-level refinement algorithm |
title | Built-Up Area Change Detection Using Multi-Task Network with Object-Level Refinement |
title_full | Built-Up Area Change Detection Using Multi-Task Network with Object-Level Refinement |
title_fullStr | Built-Up Area Change Detection Using Multi-Task Network with Object-Level Refinement |
title_full_unstemmed | Built-Up Area Change Detection Using Multi-Task Network with Object-Level Refinement |
title_short | Built-Up Area Change Detection Using Multi-Task Network with Object-Level Refinement |
title_sort | built up area change detection using multi task network with object level refinement |
topic | change detection multi-task change detection network remote sensing object-level refinement algorithm |
url | https://www.mdpi.com/2072-4292/14/4/957 |
work_keys_str_mv | AT songgao builtupareachangedetectionusingmultitasknetworkwithobjectlevelrefinement AT wangbinli builtupareachangedetectionusingmultitasknetworkwithobjectlevelrefinement AT kaiminsun builtupareachangedetectionusingmultitasknetworkwithobjectlevelrefinement AT jinjiangwei builtupareachangedetectionusingmultitasknetworkwithobjectlevelrefinement AT yepeichen builtupareachangedetectionusingmultitasknetworkwithobjectlevelrefinement AT xuanwang builtupareachangedetectionusingmultitasknetworkwithobjectlevelrefinement |