EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust Hyperspectral Anomaly Detection via Unsupervised Multiscale Feature Fusion

Yihan Wang, Zhenhua Mu, Hanyu Zhang, Chuanming Song, Xianghai Wang

Remote Sensing · 13.05.2026 · 18 (10) · 1554

DOI: 10.3390/rs18101554 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 13.05.2026. Verfasst von Yihan Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Scientific Research Project of Liaoning Provincial Education Department.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In hyperspectral image (HSI) anomaly detection (AD) methods, detecting small targets or anomalies remains challenging. This difficulty arises because targets or anomalies may vary significantly in size, shape, and texture, causing them to be obscured by larger-scale background features. To address the above issue, this paper proposes an unsupervised multi-scale feature fusion network (UMF2Net) for HSI-AD. Firstly, central difference convolution analyzes the image at multiple scales to capture fine-to-coarse details and structural information. Additionally, three-dimensional (3D) convolution is employed to generate feature weights for the multi-scale features, assigning different weights to features with different contributions so that the model dynamically emphasizes features that have a greater impact on the AD results. Finally, by using the two proposed multi-scale feature fusion modules, the model effectively integrates features at different scales, thereby enhancing its ability to detect anomalies of varying sizes. Compared with several classical HSI-AD algorithms on real hyperspectral datasets from four scenarios, UMF2Net achieved competitive detection results, verifying the effectiveness of our algorithm.

Förderung

  • Key Scientific Research Project of Liaoning Provincial Education Department

Zitieren

APA

Wang, Y., Mu, Z., Zhang, H., Song, C., & Wang, X. (2026). Robust Hyperspectral Anomaly Detection via Unsupervised Multiscale Feature Fusion. Remote Sensing, 18(10), 1554. https://doi.org/10.3390/rs18101554

Vancouver

Wang Y, Mu Z, Zhang H, Song C, Wang X. Robust Hyperspectral Anomaly Detection via Unsupervised Multiscale Feature Fusion. Remote Sensing. 2026;18(10):1554. doi:10.3390/rs18101554

BibTeX
@article{Wang2026,
  author = {Wang, Yihan and Mu, Zhenhua and Zhang, Hanyu and Song, Chuanming and Wang, Xianghai},
  title = {Robust Hyperspectral Anomaly Detection via Unsupervised Multiscale Feature Fusion},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {10},
  pages = {1554},
  doi = {10.3390/rs18101554}
}
Kostenlos starten →