EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Spatial-Frequency Decoupling Alignment Encoding for Remote Sensing Change Detection

Xu Zhang iD, Yue Du, Weiran Zhou iD, Kaihua Zhang iD

Sensors · 21.03.2026 · 26 (6) · 1979

DOI: 10.3390/s26061979 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.03.2026. Verfasst von Xu Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronics and Information Engineering, Suzhou Polytechnic University, Suzhou 215104, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Seventh Batch of Science and Technology Development Plan (Agriculture) Project, Jiangsu Higher Vocational College Teachers’ Visiting Study Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing remote sensing change detection methods often struggle to accurately capture the contours of complex change targets and subtle textural differences. This makes it difficult to effectively distinguish between the boundaries of change targets and the background. To address this challenge, we propose a novel method called spatial-frequency decoupling alignment encoding (SDA-Encoding), which is designed to fully leverage information from both the spatial and frequency domains. Specifically, we first use a Transformer encoder to extract bi-temporal features. Next, we apply wavelet transform to decouple these features into low-frequency and high-frequency components. In the multi-scale high-frequency interaction (MHI) module, we combine local spatial enhancement using spatial pyramid pooling with cross-scale dependency supplementation via the dual-domain alignment fusion (DAF) module. Meanwhile, in the position-aware low-frequency enhancement (PLE) module, spatial position sensitivity is restored using coordinate attention, and region-level contextual dependencies are captured through the selective fusion attention (SFA) module. Finally, the two frequency-domain branches are complementarily fused within the spatial domain to achieve unified detection of both fine-grained and structural changes. Experimental results on three benchmark datasets demonstrate the significant performance improvements of SDA-Encoding.

Schlagwörter

Stichwörter der Autor:innen

dual-domain alignment fusionmulti-scale high-frequency interactionposition-aware low-frequency enhancementremote sensing change detectionselective fusion attention

Autor:innen und Institutionen

  • School of Electronics and Information Engineering, Suzhou Polytechnic University, Suzhou 215104, China.
  • Information Center, Suzhou Polytechnic University, Suzhou 215104, China.
  • School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, China.

ORCID-Profile: Xu Zhang, Weiran Zhou, Kaihua Zhang

Förderung

  • Seventh Batch of Science and Technology Development Plan (Agriculture) Project
  • Jiangsu Higher Vocational College Teachers’ Visiting Study Program

Zitieren

APA

Zhang, X., Du, Y., Zhou, W., & Zhang, K. (2026). Spatial-Frequency Decoupling Alignment Encoding for Remote Sensing Change Detection. Sensors, 26(6), 1979. https://doi.org/10.3390/s26061979

Vancouver

Zhang X, Du Y, Zhou W, Zhang K. Spatial-Frequency Decoupling Alignment Encoding for Remote Sensing Change Detection. Sensors. 2026;26(6):1979. doi:10.3390/s26061979

BibTeX
@article{Zhang2026,
  author = {Zhang, Xu and Du, Yue and Zhou, Weiran and Zhang, Kaihua},
  title = {Spatial-Frequency Decoupling Alignment Encoding for Remote Sensing Change Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {6},
  pages = {1979},
  doi = {10.3390/s26061979}
}
Kostenlos starten →