Abstract

The accuracy of anomaly detection in hyperspectral images (HSIs) faces great challenges due to the high dimensionality, redundancy of data, and correlation of spectral bands. In this paper, to further improve the detection accuracy, we propose a novel anomaly detection method based on texture feature extraction and a graph dictionary-based low rank decomposition (LRD). First, instead of using traditional clustering methods for the dictionary, the proposed method employs the graph theory and designs a graph Laplacian matrix-based dictionary for LRD. The robust information of the background matrix in the LRD model is retained, and both the low rank matrix and the sparse matrix are well separated while preserving the correlation of background pixels. To further improve the detection performance, we explore and extract texture features from HSIs and integrate with the low-rank model to obtain the sparse components by decomposition. The detection results from feature maps are generated in order to suppress background components similar to anomalies in the sparse matrix and increase the strength of real anomalies. Experiments were run on one synthetic dataset and three real datasets to evaluate the performance. The results show that the performance of the proposed method yields competitive results in terms of average area under the curve (AUC) for receiver operating characteristic (ROC), i.e., 0.9845, 0.9962, 0.9699, and 0.9900 for different datasets, respectively. Compared with seven other state-of-the-art algorithms, our method yielded the highest average AUC for ROC in all datasets.

Highlights

  • Hyperspectral images (HSIs) have hundreds of approximately continuous spectral bands, carrying more information of data characteristics than traditional two-dimensional images

  • We propose a novel hyperspectral anomaly detection algorithm called GLRD_TFE

  • The HSI can be decomposed into the reconstruction background part and the initial anomaly part by utilizing the multiple subspace low rank decomposition (LRD)

Read more

Summary

Introduction

Hyperspectral images (HSIs) have hundreds of approximately continuous spectral bands, carrying more information of data characteristics than traditional two-dimensional images. By exploiting this feature information, we can achieve the objective of target detection . In practice, it is not simple to directly acquire the prior knowledge of targets such as shapes, sizes, or spectrum. Anomalies usually refer to a few pixels or even a single pixel that has differences on spectrum or intensity from their surrounding background components. The algorithms which are capable to accurately detect anomalies have extremely high application values. Anomaly detection in HSI plays important roles in a variety of applications [3,4]

Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call