D2Former: Dual-Domain Transformer for Change Detection in VHR Remote Sensing Images
Electronics · 05.06.2024 · 13 (11) · 2204
DOI: 10.3390/electronics13112204 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 05.06.2024. Verfasst von Huanhuan Zheng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yulin Science and Technology Bureau Industry University Research Project, National Natural Science Foundation Regional Fund Project.
Abstract (Originalsprache)
Computational intelligence technologies have been extensively applied for the interpretation of remote sensing imagery. Recently, the computational-intelligence-based Transformer change detection (CD) approach has attracted increasing attention. However, the current Transformer-based CD method can better capture global features, but there is no good solution for the loss of local detail information. For this reason, introducing semantic and frequency information from the perspective of a dual-domain can be beneficial for improving the representation of detailed features to improve CD performance. To overcome this limitation, a dual-domain Transformer (D2Former) is proposed for CD. Firstly, we adopt a semantic tokenizer to capture the semantic information, which promotes the enrichment and refinement of semantic change information in the Transformer. Secondly, a frequency tokenizer is introduced to acquire the frequency information of the features, which offers the proposed D2Former another aspect and dimension to enhance the ability to detect change information. Therefore, the proposed D2Former employs dual-domain tokenizers to acquire and fuse the feature representation with rich semantic and frequency information, which can refine the features to acquire more fine-grained CD ability. Extensive experiments on three CD benchmark datasets demonstrate that the proposed D2Former obviously outperforms some other existing approaches. The results present the competitive performance of our method on the WHU-CD, LEVIR-CD, and GZ-CD datasets, for which it achieved F1-Score metrics of 92.85%, 90.60%, and 87.02%, respectively.
Förderung
- Yulin Science and Technology Bureau Industry University Research Project
- National Natural Science Foundation Regional Fund Project
Zitieren
APA
Zheng, H., Liu, H., Lu, L., Li, S., & Lin, J. (2024). D2Former: Dual-Domain Transformer for Change Detection in VHR Remote Sensing Images. Electronics, 13(11), 2204. https://doi.org/10.3390/electronics13112204
Vancouver
Zheng H, Liu H, Lu L, Li S, Lin J. D2Former: Dual-Domain Transformer for Change Detection in VHR Remote Sensing Images. Electronics. 2024;13(11):2204. doi:10.3390/electronics13112204
BibTeX
@article{Zheng2024,
author = {Zheng, Huanhuan and Liu, Hui and Lu, Lei and Li, Shiyin and Lin, Jiyan},
title = {D2Former: Dual-Domain Transformer for Change Detection in VHR Remote Sensing Images},
journal = {Electronics},
year = {2024},
volume = {13},
number = {11},
pages = {2204},
doi = {10.3390/electronics13112204}
}
EUVIMED