This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
A CNN- and Transformer-Based Dual-Branch Network for Change Detection with Cross-Layer Feature Fusion and Edge Constraints
by
Xiaofeng Wang
Xiaofeng Wang
,
Zhongyu Guo
Zhongyu Guo and
Ruyi Feng
Ruyi Feng *
School of Computer, China University of Geosciences, Wuhan 430074, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2024, 16(14), 2573; https://doi.org/10.3390/rs16142573 (registering DOI)
Submission received: 6 June 2024
/
Revised: 4 July 2024
/
Accepted: 11 July 2024
/
Published: 13 July 2024
Abstract
Change detection aims to identify the difference between dual-temporal images and has garnered considerable attention over the past decade. Recently, deep learning methods have shown robust feature extraction capabilities and have achieved improved detection results; however, they exhibit limitations in preserving clear boundaries for the identified regions, which is attributed to the inadequate contextual information aggregation capabilities of feature extraction, and fail to adequately constrain the delineation of boundaries. To address this issue, a novel dual-branch feature interaction backbone network integrating the CNN and Transformer architectures to extract pixel-level change information was developed. With our method, contextual feature aggregation can be achieved by using a cross-layer feature fusion module, and a dual-branch upsampling module is employed to incorporate both spatial and channel information, enhancing the precision of the identified change areas. In addition, a boundary constraint is incorporated, leveraging an MLP module to consolidate fragmented edge information, which increases the boundary constraints within the change areas and minimizes boundary blurring effectively. Quantitative and qualitative experiments were conducted on three benchmarks, including LEVIR-CD, WHU Building, and the xBD natural disaster dataset. The comprehensive results show the superiority of the proposed method compared with previous approaches.
Share and Cite
MDPI and ACS Style
Wang, X.; Guo, Z.; Feng, R.
A CNN- and Transformer-Based Dual-Branch Network for Change Detection with Cross-Layer Feature Fusion and Edge Constraints. Remote Sens. 2024, 16, 2573.
https://doi.org/10.3390/rs16142573
AMA Style
Wang X, Guo Z, Feng R.
A CNN- and Transformer-Based Dual-Branch Network for Change Detection with Cross-Layer Feature Fusion and Edge Constraints. Remote Sensing. 2024; 16(14):2573.
https://doi.org/10.3390/rs16142573
Chicago/Turabian Style
Wang, Xiaofeng, Zhongyu Guo, and Ruyi Feng.
2024. "A CNN- and Transformer-Based Dual-Branch Network for Change Detection with Cross-Layer Feature Fusion and Edge Constraints" Remote Sensing 16, no. 14: 2573.
https://doi.org/10.3390/rs16142573
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.