Network and Dataset for Multiscale Remote Sensing Image Change Detection
Remote sensing image change detection (RSCD) aims to identify differences between remote sensing images of the same location at different times. However, due to the significant variations in the size and appearance of objects in real-world scenes, existing RSCD algorithms often lack strong capabilit...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10813409/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841542581855453184 |
|---|---|
| author | Shenbo Liu Dongxue Zhao Yuheng Zhou Ying Tan Huang He Zhao Zhang Lijun Tang |
| author_facet | Shenbo Liu Dongxue Zhao Yuheng Zhou Ying Tan Huang He Zhao Zhang Lijun Tang |
| author_sort | Shenbo Liu |
| collection | DOAJ |
| description | Remote sensing image change detection (RSCD) aims to identify differences between remote sensing images of the same location at different times. However, due to the significant variations in the size and appearance of objects in real-world scenes, existing RSCD algorithms often lack strong capabilities in extracting multiscale features, thereby failing to fully capture the characteristics of changes. To address this issue, a multiscale remote sensing change detection network (MSNet) and a multiscale RSCD dataset (MSRS-CD) are proposed. A multiscale convolution module (MSCM) is investigated, and combined with MSCM, an encoder capable of capturing features of different sizes is designed to efficiently extract multiscale semantic change features. A global multiscale feature fusion module is designed to achieve global multiscale feature fusion and obtain multiscale high-level semantic change features. As existing RSCD datasets lack rich scale information and often focus on change targets of specific sizes, a new dataset, MSRS-CD, is constructed. This dataset consists of 842 pairs of images with a resolution of 1024 × 1024 pixels, featuring uniformly distributed change detection target sizes. Comparative experiments are conducted with 10 other state-of-the-art algorithms on the MSRS-CD dataset and another public dataset, LEVIR-CD. Experimental results demonstrate that MSNet achieves the best performance on both datasets, with an <italic>F</italic>1 score of 75.74% on the MSRS-CD dataset and 91.41% on the LEVIR-CD dataset. |
| format | Article |
| id | doaj-art-ccb6ad0b9caa4d3ba3f5d5fe3f867391 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-ccb6ad0b9caa4d3ba3f5d5fe3f8673912025-01-14T00:00:50ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01182851286610.1109/JSTARS.2024.352213510813409Network and Dataset for Multiscale Remote Sensing Image Change DetectionShenbo Liu0https://orcid.org/0000-0003-2257-8615Dongxue Zhao1Yuheng Zhou2Ying Tan3Huang He4Zhao Zhang5Lijun Tang6https://orcid.org/0009-0006-2264-1660School of Physics and Electronic Science, Changsha University of Science and Technology, Changsha, ChinaSchool of Physics and Electronic Science, Changsha University of Science and Technology, Changsha, ChinaSchool of Physics and Electronic Science, Changsha University of Science and Technology, Changsha, ChinaSchool of Physics and Electronic Science, Changsha University of Science and Technology, Changsha, ChinaSchool of Physics and Electronic Science, Changsha University of Science and Technology, Changsha, ChinaSchool of Physics and Electronic Science, Changsha University of Science and Technology, Changsha, ChinaSchool of Physics and Electronic Science, Changsha University of Science and Technology, Changsha, ChinaRemote sensing image change detection (RSCD) aims to identify differences between remote sensing images of the same location at different times. However, due to the significant variations in the size and appearance of objects in real-world scenes, existing RSCD algorithms often lack strong capabilities in extracting multiscale features, thereby failing to fully capture the characteristics of changes. To address this issue, a multiscale remote sensing change detection network (MSNet) and a multiscale RSCD dataset (MSRS-CD) are proposed. A multiscale convolution module (MSCM) is investigated, and combined with MSCM, an encoder capable of capturing features of different sizes is designed to efficiently extract multiscale semantic change features. A global multiscale feature fusion module is designed to achieve global multiscale feature fusion and obtain multiscale high-level semantic change features. As existing RSCD datasets lack rich scale information and often focus on change targets of specific sizes, a new dataset, MSRS-CD, is constructed. This dataset consists of 842 pairs of images with a resolution of 1024 × 1024 pixels, featuring uniformly distributed change detection target sizes. Comparative experiments are conducted with 10 other state-of-the-art algorithms on the MSRS-CD dataset and another public dataset, LEVIR-CD. Experimental results demonstrate that MSNet achieves the best performance on both datasets, with an <italic>F</italic>1 score of 75.74% on the MSRS-CD dataset and 91.41% on the LEVIR-CD dataset.https://ieeexplore.ieee.org/document/10813409/Attention mechanismchange detection dataset (CDD)feature pyramidmultiscale change detectionremote sensing images |
| spellingShingle | Shenbo Liu Dongxue Zhao Yuheng Zhou Ying Tan Huang He Zhao Zhang Lijun Tang Network and Dataset for Multiscale Remote Sensing Image Change Detection IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention mechanism change detection dataset (CDD) feature pyramid multiscale change detection remote sensing images |
| title | Network and Dataset for Multiscale Remote Sensing Image Change Detection |
| title_full | Network and Dataset for Multiscale Remote Sensing Image Change Detection |
| title_fullStr | Network and Dataset for Multiscale Remote Sensing Image Change Detection |
| title_full_unstemmed | Network and Dataset for Multiscale Remote Sensing Image Change Detection |
| title_short | Network and Dataset for Multiscale Remote Sensing Image Change Detection |
| title_sort | network and dataset for multiscale remote sensing image change detection |
| topic | Attention mechanism change detection dataset (CDD) feature pyramid multiscale change detection remote sensing images |
| url | https://ieeexplore.ieee.org/document/10813409/ |
| work_keys_str_mv | AT shenboliu networkanddatasetformultiscaleremotesensingimagechangedetection AT dongxuezhao networkanddatasetformultiscaleremotesensingimagechangedetection AT yuhengzhou networkanddatasetformultiscaleremotesensingimagechangedetection AT yingtan networkanddatasetformultiscaleremotesensingimagechangedetection AT huanghe networkanddatasetformultiscaleremotesensingimagechangedetection AT zhaozhang networkanddatasetformultiscaleremotesensingimagechangedetection AT lijuntang networkanddatasetformultiscaleremotesensingimagechangedetection |