File(s) under permanent embargo
Reason: The file associated with this record is under embargo until publication, in accordance with the publisher's self-archiving policy. The full text may be available through the publisher links provided above.
Hyperspectral Anomaly Detection Based on Low- Rank and Sparse Representation with Data-Driven Projection and Dictionary Construction
Hyperspectral image anomaly detection is an increasingly important research topic in remote sensing images understanding and interpretation. Recently, low-rank representation-based methods have attracted extensive attentions and achieved promising performances in hyperspectral anomaly detection. These methods assume that the hyperspectral data can be decomposed into two parts: the low-rank component representing the background and the residual part indicating the anomaly. More recently, sparse representation has been introduced to support the development of low-rank representation (LRR) models, which considers the sparsity of the representation. In order to improve the separability of the background and anomaly, we propose a novel hyperspectral anomaly detection based on low-rank and sparse representation with dictionary construction and data-driven projection. To construct a robust dictionary that contains all categories of the background objects whilst excluding the anomaly’s influence, we adopt a superpixel-based tensor low-rank decomposition method to generate a comprehensive and pure background dictionary. Considering the spectral redundancy in the hyperspectral data, data-driven projection is introduced to the low-rank representation to project the original data to a low-dimensional feature space to better separate the anomaly and the background. Experimental results on four real hyperspectral datasets show that the proposed anomaly detection method outperforms the other anomaly detectors.
History
Citation
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2020) In PressVersion
- AM (Accepted Manuscript)