Hyperspectral Anomaly Detection with Auto-Encoder and Independent Target

• Published in: Remote sensing (Basel, Switzerland) Vol. 15; no. 22; p. 5266
• Main Authors: Chen, Shuhan, Li, Xiaorun, Yan, Yunfeng
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.11.2023
• Subjects: Algorithms; Anomalies; Artificial intelligence; auto-encoder; Coders; Collaboration; Comparative analysis; Construction; Decomposition; detectors; Dictionaries; Image processing; independent target subspace (ITS); low rank and sparse decomposition (LRaSMD); Methods; Multispectral photography; Neural networks; neurons; Normal distribution; Reconstruction; remote sensing; Sensors; Sparse matrices; sparsity cardinality (SC); Technology application; unsupervised independent target; China

As an unsupervised data representation neural network, auto-encoder (AE) has shown great potential in denoising, dimensionality reduction, and data reconstruction. Many AE-based background (BKG) modeling methods have been developed for hyperspectral anomaly detection (HAD). However, their performanc...