Deep Autoencoders With Multitask Learning for Bilinear Hyperspectral Unmixing
| Autor: | Paolo Gamba, Jun Li, Yuanchao Su, Xiang Xu, Hairong Qi, Antonio Plaza |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Endmember
business.industry Computer science 0211 other engineering and technologies Multi-task learning Bilinear interpolation Hyperspectral imaging Pattern recognition 02 engineering and technology Mixture model Autoencoder Subpixel rendering Statistics::Machine Learning Nonlinear system Computer Science::Computer Vision and Pattern Recognition General Earth and Planetary Sciences Artificial intelligence Electrical and Electronic Engineering business 021101 geological & geomatics engineering |
| Zdroj: | IEEE Transactions on Geoscience and Remote Sensing. 59:8615-8629 |
| ISSN: | 1558-0644 0196-2892 |
| DOI: | 10.1109/tgrs.2020.3041157 |
| Popis: | Hyperspectral unmixing is an important problem for remotely sensed data interpretation. It amounts at estimating the spectral signatures of the pure spectral constituents in the scene (endmembers) and their corresponding subpixel fractional abundances. Although the unmixing problem is inherently nonlinear (due to multiple scattering), the nonlinear unmixing of hyperspectral data has been a very challenging problem. This is because nonlinear models require detailed knowledge about the physical interactions between the sunlight scattered by multiple materials. In turn, bilinear mixture models (BMMs) can reach good accuracy with a relatively simple model for scattering. In this article, we develop a new BMM and a corresponding unsupervised unmixing approach which consists of two main steps. In the first step, a deep autoencoder is used to linearly estimate the endmember signatures and their associated abundance fractions. The second step refines the initial (linear) estimates using a bilinear model, in which another deep autoencoder (with a low-rank assumption) is adapted to model second-order scattering interactions. It should be noted that in our developed BMM model, the two deep autoencoders are trained in a mutually interdependent manner under the multitask learning framework, and the relative reconstruction error is used as the stopping criterion. The effectiveness of the proposed method is evaluated using both synthetic and real hyperspectral data sets. Our experimental results indicate that the proposed approach can reasonably estimate the nature of nonlinear interactions in real scenarios. Compared with other state-of-the-art unmixing algorithms, the proposed approach demonstrates very competitive performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|