Learning-Based Approach for Atmospheric Compensation of VNIR Hyperspectral Data
| Autor: | Nicola Acito, Marco Diani, Giovanni Corsini |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Pixel
Computer science 0211 other engineering and technologies Hyperspectral imaging 02 engineering and technology Atmospheric model Atmospheric compensation (AC) hyperspectral imagery learning-based (LB) approach machine learning Synthetic data VNIR hyperspectral imagery machine learning Radiance General Earth and Planetary Sciences Atmospheric compensation (AC) Electrical and Electronic Engineering Visibility learning-based (LB) approach 021101 geological & geomatics engineering Parametric statistics Remote sensing |
| Zdroj: | IEEE Transactions on Geoscience and Remote Sensing. 59:4218-4232 |
| ISSN: | 1558-0644 0196-2892 |
| DOI: | 10.1109/tgrs.2020.3016094 |
| Popis: | In this work, we deal with the problem of atmospheric compensation (AC) of hyperspectral data collected in the visible and near-infrared (VNIR) spectral range. We propose the “learning-based” approach which uses artificial intelligence algorithms to directly estimate the spectral reflectance from the observed at-sensor radiance image. It uses a parametric regressor whose parameters are learned by means of a strategy based on synthetic data. Such data are generated taking into account 1) the radiative transfer in the atmosphere; 2) the variability of the surface spectral reflectance; and 3) the effects of signal-dependent random noise and spectral miscalibration errors. According to this general framework, we propose a specific multilinear regressor that starting from the knowledge of the atmospheric visibility compensates the water absorption and provides the spectral reflectance of each pixel of the analyzed image. Furthermore, a specific image-based procedure is presented for visibility estimation. The experiment over simulated data is presented and discussed. The test on simulated data aims at showing the effectiveness of the proposed strategy in a completely controlled environment. Experiments are also carried out on three real hyperspectral images acquired by two hyperspectral sensors. The obtained results confirm the effectiveness of the proposed approach by comparing the retrieved reflectance spectra with in-situ measurements or with those obtained by using a well-known commercial AC software. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|