Difference Perception Fusion Network for Remote Sensing Image Change Detection
Deep-learning-based methods have achieved promising results in the field of remote sensing image change detection. However, they have deficiencies in generating and utilizing difference features, which leads to inaccurate detection of changed regions with fine structures. To address the aforemention...
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/11060832/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839622607467446272 |
|---|---|
| author | Lijing Wang Ying Xie Zhongda Lu Shipeng Tian |
| author_facet | Lijing Wang Ying Xie Zhongda Lu Shipeng Tian |
| author_sort | Lijing Wang |
| collection | DOAJ |
| description | Deep-learning-based methods have achieved promising results in the field of remote sensing image change detection. However, they have deficiencies in generating and utilizing difference features, which leads to inaccurate detection of changed regions with fine structures. To address the aforementioned problems, this article proposes a difference perception fusion network. First, multilevel bitemporal features are extracted through the Siamese backbone network. To generate discriminative difference features utilizing the extracted multilevel bitemporal features, the difference perception module is designed, which consists of an adaptive denoising module (ADM) and an edge enhancement module (EEM). Specifically, ADM relies on frequency filters with learnable parameters to suppress the noise produced during difference generation and EEM uses pooled subtraction to extract edge information for maintaining the fine contours of changed regions. The hybrid attention difference fusion module is constructed to realize the interaction between multilevel difference features, enriching the edge details and internal integrity of changed regions. In addition, the refinement representation module is developed to realize the sophisticated representation of difference features and enhance the detection effect of changed regions. The effectiveness of the proposed DPFNet is verified by extensive experiments on three RSCD datasets (WHU-CD, CDD-CD, and SYSU-CD), and DPFNet has fewer false detections and missed detections compared to other state-of-the-art methods. |
| format | Article |
| id | doaj-art-cb0bd0d09b8b4be794bccca51fc18a95 |
| institution | Matheson Library |
| 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-cb0bd0d09b8b4be794bccca51fc18a952025-07-21T23:00:14ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118169661698210.1109/JSTARS.2025.358475811060832Difference Perception Fusion Network for Remote Sensing Image Change DetectionLijing Wang0https://orcid.org/0000-0003-4157-8477Ying Xie1https://orcid.org/0000-0003-4291-8090Zhongda Lu2https://orcid.org/0000-0003-2842-0245Shipeng Tian3https://orcid.org/0009-0005-1968-0223School of Electrical and Electronic Engineering, Harbin University of Science and Technology, Harbin, ChinaSchool of Electrical and Electronic Engineering, Harbin University of Science and Technology, Harbin, ChinaCollaborative Innovation Center of Intelligent Manufacturing Equipment Industrialization of Heilongjiang, Qiqihar University, Qiqihar, ChinaCollaborative Innovation Center of Intelligent Manufacturing Equipment Industrialization of Heilongjiang, Qiqihar University, Qiqihar, ChinaDeep-learning-based methods have achieved promising results in the field of remote sensing image change detection. However, they have deficiencies in generating and utilizing difference features, which leads to inaccurate detection of changed regions with fine structures. To address the aforementioned problems, this article proposes a difference perception fusion network. First, multilevel bitemporal features are extracted through the Siamese backbone network. To generate discriminative difference features utilizing the extracted multilevel bitemporal features, the difference perception module is designed, which consists of an adaptive denoising module (ADM) and an edge enhancement module (EEM). Specifically, ADM relies on frequency filters with learnable parameters to suppress the noise produced during difference generation and EEM uses pooled subtraction to extract edge information for maintaining the fine contours of changed regions. The hybrid attention difference fusion module is constructed to realize the interaction between multilevel difference features, enriching the edge details and internal integrity of changed regions. In addition, the refinement representation module is developed to realize the sophisticated representation of difference features and enhance the detection effect of changed regions. The effectiveness of the proposed DPFNet is verified by extensive experiments on three RSCD datasets (WHU-CD, CDD-CD, and SYSU-CD), and DPFNet has fewer false detections and missed detections compared to other state-of-the-art methods.https://ieeexplore.ieee.org/document/11060832/Change detection (CD)difference fusiondifference perceptionremote sensing (RS) |
| spellingShingle | Lijing Wang Ying Xie Zhongda Lu Shipeng Tian Difference Perception Fusion Network for Remote Sensing Image Change Detection IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Change detection (CD) difference fusion difference perception remote sensing (RS) |
| title | Difference Perception Fusion Network for Remote Sensing Image Change Detection |
| title_full | Difference Perception Fusion Network for Remote Sensing Image Change Detection |
| title_fullStr | Difference Perception Fusion Network for Remote Sensing Image Change Detection |
| title_full_unstemmed | Difference Perception Fusion Network for Remote Sensing Image Change Detection |
| title_short | Difference Perception Fusion Network for Remote Sensing Image Change Detection |
| title_sort | difference perception fusion network for remote sensing image change detection |
| topic | Change detection (CD) difference fusion difference perception remote sensing (RS) |
| url | https://ieeexplore.ieee.org/document/11060832/ |
| work_keys_str_mv | AT lijingwang differenceperceptionfusionnetworkforremotesensingimagechangedetection AT yingxie differenceperceptionfusionnetworkforremotesensingimagechangedetection AT zhongdalu differenceperceptionfusionnetworkforremotesensingimagechangedetection AT shipengtian differenceperceptionfusionnetworkforremotesensingimagechangedetection |