A Remote Sensing Image Change Detection Method Integrating Layer-Exchange and Channel-Spatial Differences
Change detection in remote sensing imagery is a crucial technique for Earth observation, primarily focusing on pixel-level segmentation of change regions between bitemporal images. The core of pixel-level change detection lies in determining whether corresponding pixels in bitemporal images have und...
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/11024553/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849706080497565696 |
|---|---|
| author | Sijun Dong Fangcheng Zuo Geng Chen Siming Fu Xiaoliang Meng |
| author_facet | Sijun Dong Fangcheng Zuo Geng Chen Siming Fu Xiaoliang Meng |
| author_sort | Sijun Dong |
| collection | DOAJ |
| description | Change detection in remote sensing imagery is a crucial technique for Earth observation, primarily focusing on pixel-level segmentation of change regions between bitemporal images. The core of pixel-level change detection lies in determining whether corresponding pixels in bitemporal images have undergone changes. In deep learning, the spatial and channel dimensions of feature maps represent distinct types of information derived from the original images. In this study, we discovered that in change detection tasks, difference information can be computed not only from the spatial dimension of bitemporal features but also from the channel dimension. Based on this insight, we designed the channel-spatial difference weighting module, which serves as an aggregation-distribution mechanism for bitemporal features in change detection. This module enhances the sensitivity of the change detection model to difference features, thereby improving its overall performance. Furthermore, bitemporal images share the same geographic location and exhibit strong interimage correlations. To effectively capture and utilize these correlations, we designed a decoding structure based on the layer-exchange method, which enhances the interaction of bitemporal features. This approach allows the model to better leverage the temporal dependencies between the images, leading to more accurate change detection. To validate the effectiveness of our proposed method, we conducted comprehensive experiments on four widely used datasets: CLCD, PX-CLCD, LEVIR-CD, and S2Looking. The experimental results demonstrate that the proposed LENet model significantly outperforms existing methods in terms of change detection accuracy. |
| format | Article |
| id | doaj-art-11fea629c70549c2bcb3ed984c0d83d3 |
| institution | DOAJ |
| 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-11fea629c70549c2bcb3ed984c0d83d32025-08-20T03:16:18ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118148041481910.1109/JSTARS.2025.357683111024553A Remote Sensing Image Change Detection Method Integrating Layer-Exchange and Channel-Spatial DifferencesSijun Dong0https://orcid.org/0000-0003-4218-6790Fangcheng Zuo1Geng Chen2https://orcid.org/0009-0008-1824-7593Siming Fu3Xiaoliang Meng4https://orcid.org/0000-0002-3271-9314School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaGuangxi Water & Power Design Institute CO., Ltd., Nanning, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaChange detection in remote sensing imagery is a crucial technique for Earth observation, primarily focusing on pixel-level segmentation of change regions between bitemporal images. The core of pixel-level change detection lies in determining whether corresponding pixels in bitemporal images have undergone changes. In deep learning, the spatial and channel dimensions of feature maps represent distinct types of information derived from the original images. In this study, we discovered that in change detection tasks, difference information can be computed not only from the spatial dimension of bitemporal features but also from the channel dimension. Based on this insight, we designed the channel-spatial difference weighting module, which serves as an aggregation-distribution mechanism for bitemporal features in change detection. This module enhances the sensitivity of the change detection model to difference features, thereby improving its overall performance. Furthermore, bitemporal images share the same geographic location and exhibit strong interimage correlations. To effectively capture and utilize these correlations, we designed a decoding structure based on the layer-exchange method, which enhances the interaction of bitemporal features. This approach allows the model to better leverage the temporal dependencies between the images, leading to more accurate change detection. To validate the effectiveness of our proposed method, we conducted comprehensive experiments on four widely used datasets: CLCD, PX-CLCD, LEVIR-CD, and S2Looking. The experimental results demonstrate that the proposed LENet model significantly outperforms existing methods in terms of change detection accuracy.https://ieeexplore.ieee.org/document/11024553/Change detectionchannel-spatial differencelayer-exchange (LE) |
| spellingShingle | Sijun Dong Fangcheng Zuo Geng Chen Siming Fu Xiaoliang Meng A Remote Sensing Image Change Detection Method Integrating Layer-Exchange and Channel-Spatial Differences IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Change detection channel-spatial difference layer-exchange (LE) |
| title | A Remote Sensing Image Change Detection Method Integrating Layer-Exchange and Channel-Spatial Differences |
| title_full | A Remote Sensing Image Change Detection Method Integrating Layer-Exchange and Channel-Spatial Differences |
| title_fullStr | A Remote Sensing Image Change Detection Method Integrating Layer-Exchange and Channel-Spatial Differences |
| title_full_unstemmed | A Remote Sensing Image Change Detection Method Integrating Layer-Exchange and Channel-Spatial Differences |
| title_short | A Remote Sensing Image Change Detection Method Integrating Layer-Exchange and Channel-Spatial Differences |
| title_sort | remote sensing image change detection method integrating layer exchange and channel spatial differences |
| topic | Change detection channel-spatial difference layer-exchange (LE) |
| url | https://ieeexplore.ieee.org/document/11024553/ |
| work_keys_str_mv | AT sijundong aremotesensingimagechangedetectionmethodintegratinglayerexchangeandchannelspatialdifferences AT fangchengzuo aremotesensingimagechangedetectionmethodintegratinglayerexchangeandchannelspatialdifferences AT gengchen aremotesensingimagechangedetectionmethodintegratinglayerexchangeandchannelspatialdifferences AT simingfu aremotesensingimagechangedetectionmethodintegratinglayerexchangeandchannelspatialdifferences AT xiaoliangmeng aremotesensingimagechangedetectionmethodintegratinglayerexchangeandchannelspatialdifferences AT sijundong remotesensingimagechangedetectionmethodintegratinglayerexchangeandchannelspatialdifferences AT fangchengzuo remotesensingimagechangedetectionmethodintegratinglayerexchangeandchannelspatialdifferences AT gengchen remotesensingimagechangedetectionmethodintegratinglayerexchangeandchannelspatialdifferences AT simingfu remotesensingimagechangedetectionmethodintegratinglayerexchangeandchannelspatialdifferences AT xiaoliangmeng remotesensingimagechangedetectionmethodintegratinglayerexchangeandchannelspatialdifferences |