The Spectrum Difference Enhanced Network for Hyperspectral Anomaly Detection
Remote Sensing · 02.12.2024 · 16 (23) · 4518
DOI: 10.3390/rs16234518 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 02.12.2024. Verfasst von Shaohua Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China General Program, Shaanxi Provincial Key Research and Develop Programme General Project.
Abstract (Originalsprache)
Most deep learning-based hyperspectral anomaly detection (HAD) methods focus on modeling or reconstructing the hyperspectral background to obtain residual maps from the original hyperspectral images. However, these methods typically do not pay enough attention to the spectral similarity in the complex environment, resulting in inadequate distinction between background and anomalies. Moreover, some anomalies and background are different objects, but they are sometimes recognized as the objects with the same spectrum. To address the issues mentioned above, this paper proposes a Spectrum Difference Enhanced Network (SDENet) for HAD, which employs variational mapping and Transformer to amplify spectrum differences. The proposed network is based on the encoder–decoder structure, which contains a CSWin-Transformer encoder, Variational Mapping Module (VMModule), and CSWin-Transformer decoder. First, the CSWin-Transformer encoder and decoder are designed to supplement image information by extracting deep and semantic features, where a cross-shaped window self-attention mechanism is designed to provide strong modeling capability with minimal computational cost. Second, in order to enhance the spectral difference characteristics between anomalies and background, a randomly sampling VMModule is presented for feature space transformation. Finally, all fully connected mapping operations are replaced with convolutional layers to reduce the model parameters and computational load. The effectiveness of the proposed SDENet is verified on three datasets, and experimental results show that it achieves better detection accuracy and lower model complexity compared with existing methods.
Förderung
- National Natural Science Foundation of China General Program
- Shaanxi Provincial Key Research and Develop Programme General Project
Zitieren
APA
Liu, S., Guo, H., Gao, S., & Zhang, W. (2024). The Spectrum Difference Enhanced Network for Hyperspectral Anomaly Detection. Remote Sensing, 16(23), 4518. https://doi.org/10.3390/rs16234518
Vancouver
Liu S, Guo H, Gao S, Zhang W. The Spectrum Difference Enhanced Network for Hyperspectral Anomaly Detection. Remote Sensing. 2024;16(23):4518. doi:10.3390/rs16234518
BibTeX
@article{Liu2024,
author = {Liu, Shaohua and Guo, Huibo and Gao, Shiwen and Zhang, Wuxia},
title = {The Spectrum Difference Enhanced Network for Hyperspectral Anomaly Detection},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {23},
pages = {4518},
doi = {10.3390/rs16234518}
}
EUVIMED