Siam-EMNet: A Siamese EfficientNet–MANet Network for Building Change Detection in Very High Resolution Images

As well as very high resolution (VHR) remote sensing technology and deep learning, methods for detecting changes in buildings have made great progress. Despite this, there are still some problems with the incomplete detection of change regions and rough edges. To this end, a change detection network...

Full description

Saved in:
Bibliographic Details
Published inRemote sensing (Basel, Switzerland) Vol. 15; no. 16; p. 3972
Main Authors Huang, Liang, Tian, Qiuyuan, Tang, Bo-Hui, Le, Weipeng, Wang, Min, Ma, Xianguang
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.08.2023
Subjects
Accuracy
attention mechanism
building
Buildings
Change detection
Classification
Coders
Deep learning
Feature extraction
High resolution
Image resolution
Maintenance and repair
Neural networks
Remote sensing
Support vector machines
VHR remote sensing images
China
Siam
Online AccessGet full text

Cover

More Information
Summary:As well as very high resolution (VHR) remote sensing technology and deep learning, methods for detecting changes in buildings have made great progress. Despite this, there are still some problems with the incomplete detection of change regions and rough edges. To this end, a change detection network for building VHR remote sensing images based on Siamese EfficientNet B4-MANet (Siam-EMNet) is proposed. First, a bi-branches pretrained EfficientNet B4 encoder structure is constructed to enhance the performance of feature extraction and the rich shallow and deep information is obtained; then, the semantic information of the building is input into the MANet decoder integrated by the dual attention mechanism through the skip connection. The position-wise attention block (PAB) and multi-scale fusion attention block (MFAB) capture spatial relationships between pixels in the global view and channel relationships between layers. The integration of dual attention mechanisms ensures that the building contour is fully detected. The proposed method was evaluated on the LEVIR-CD dataset, and its precision, recall, accuracy, and F1-score were 92.00%, 88.51%, 95.71%, and 90.21%, respectively, which represented the best overall performance compared to the BIT, CDNet, DSIFN, L-Unet, P2V-CD, and SNUNet methods. Verification of the efficacy of the suggested approach was then conducted.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs15163972