Spectral Distribution-Aware Estimation Network for Hyperspectral Anomaly Detection
| Autor: | Qian Du, Shuran Fan, Wu Xianyun, Jiahui Qu, Weiying Xie, Yanli Lu |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
business.industry
Computer science Deep learning Dimensionality reduction Feature extraction Hyperspectral imaging Markov chain Monte Carlo Pattern recognition Mixture model symbols.namesake symbols General Earth and Planetary Sciences Anomaly detection Artificial intelligence Electrical and Electronic Engineering Anomaly (physics) business |
| Zdroj: | IEEE Transactions on Geoscience and Remote Sensing. 60:1-12 |
| ISSN: | 1558-0644 0196-2892 |
| DOI: | 10.1109/tgrs.2021.3089711 |
| Popis: | Recently developed deep learning-based hyperspectral anomaly detection (HAD) methods typically include two steps where the deep feature extraction is not designed specifically for the HAD task. In this article, we propose a spectral distribution-aware estimation network (SDEN) that does not conduct feature extraction and anomaly detection in two separate steps but instead learns both jointly to estimate anomalies directly in an end-to-end manner without postprocessing. The unified framework can ensure that the extracted features serve better for anomaly detection. To preserve the distribution of hyperspectral images (HSIs) during dimensionality reduction, the SDEN introduces a spectral distribution (SD)-aware module imposed with a local-invariant constraint. More specifically, we adopt Markov chain Monte Carlo (MCMC) that enables the SD module to better estimate the distribution of the complex HSIs. Considering the powerful representation capability of Gaussian mixture model (GMM), the SDEN leverages it to establish an estimation module in the deep latent space where the anomaly resides in low density while the background not. We demonstrate that the SDEN yields competitive and highly promising results in comparison with the anomaly detection benchmarks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|