MFINet: Multi-Scale Feature Interaction Network for Change Detection of High-Resolution Remote Sensing Images

Change detection is widely used in the field of building monitoring. In recent years, the progress of remote sensing image technology has provided high-resolution data. However, unlike other tasks, change detection focuses on the difference between dual-input images, so the interaction between bi-te...

Full description

Saved in:
Bibliographic Details
Published inRemote sensing (Basel, Switzerland) Vol. 16; no. 7; p. 1269
Main Authors Ren, Wuxu, Wang, Zhongchen, Xia, Min, Lin, Haifeng
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.04.2024
Subjects
Accuracy
Artificial intelligence
Change detection
CNN
Comparative analysis
Computer networks
Decoding
Deep learning
High resolution
Image processing
Image resolution
Machine learning
Methods
Morphology
Neural networks
Remote sensing
remote sensing images
Satellites
self-attention mechanism
Semantics
Support vector machines
Technology application
Temporal variations
transformer
China
Online AccessGet full text

Cover

More Information
Summary:Change detection is widely used in the field of building monitoring. In recent years, the progress of remote sensing image technology has provided high-resolution data. However, unlike other tasks, change detection focuses on the difference between dual-input images, so the interaction between bi-temporal features is crucial. However, the existing methods have not fully tapped the potential of multi-scale bi-temporal features to interact layer by layer. Therefore, this paper proposes a multi-scale feature interaction network (MFINet). The network realizes the information interaction of multi-temporal images by inserting a bi-temporal feature interaction layer (BFIL) between backbone networks at the same level, guides the attention to focus on the difference region, and suppresses the interference. At the same time, a double temporal feature fusion layer (BFFL) is used at the end of the coding layer to extract subtle difference features. By introducing the transformer decoding layer and improving the recovery effect of the feature size, the ability of the network to accurately capture the details and contour information of the building is further improved. The F1 of our model on the public dataset LEVIR-CD reaches 90.12%, which shows better accuracy and generalization performance than many state-of-the-art change detection models.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs16071269