Depth feature extraction for mineral mixed spectrum analysis based hyperspectral data

2021 ◽  
Author(s):  
Kai Qin ◽  
Zhao yingjun ◽  
Ling ZHU ◽  
YUECHAO YANG ◽  
XIN CUI
Keyword(s):  
Feature Extraction ◽  
Spectrum Analysis ◽  
Hyperspectral Data ◽  
Mixed Spectrum ◽  
Depth Feature

scholarly journals Unsupervised Multi-Level Feature Extraction for Improvement of Hyperspectral Classification

2021 ◽  
Vol 13 (8) ◽  
pp. 1602
Author(s):  
Qiaoqiao Sun ◽  
Xuefeng Liu ◽  
Salah Bourennane
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Spatial Information ◽  
Hyperspectral Data ◽  
Great Promise ◽  
Learning Models ◽  
Single Level ◽  
Multiple Networks ◽  
Multi Level ◽  
Hyperspectral Classification

Deep learning models have strong abilities in learning features and they have been successfully applied in hyperspectral images (HSIs). However, the training of most deep learning models requires labeled samples and the collection of labeled samples are labor-consuming in HSI. In addition, single-level features from a single layer are usually considered, which may result in the loss of some important information. Using multiple networks to obtain multi-level features is a solution, but at the cost of longer training time and computational complexity. To solve these problems, a novel unsupervised multi-level feature extraction framework that is based on a three dimensional convolutional autoencoder (3D-CAE) is proposed in this paper. The designed 3D-CAE is stacked by fully 3D convolutional layers and 3D deconvolutional layers, which allows for the spectral-spatial information of targets to be mined simultaneously. Besides, the 3D-CAE can be trained in an unsupervised way without involving labeled samples. Moreover, the multi-level features are directly obtained from the encoded layers with different scales and resolutions, which is more efficient than using multiple networks to get them. The effectiveness of the proposed multi-level features is verified on two hyperspectral data sets. The results demonstrate that the proposed method has great promise in unsupervised feature learning and can help us to further improve the hyperspectral classification when compared with single-level features.

scholarly journals Feature Extraction Approach in Hyperspectral Data

2021 ◽  
Author(s):  
Munkh-Erdene Altangerel ◽  
Amarsaikhan Damdinsuren ◽  
Enkhjargal Damdinsuren ◽  
Odontuya Gendaram ◽  
Jargaldalai Enkhtuya
Keyword(s):  
Feature Extraction ◽  
Hyperspectral Data

Feature Extraction Techniques for Airborne Hyperspectral Images – Implication for Mineral Exploration

2021 ◽  
Author(s):  
Rupsa Chakraborty ◽  
Gabor Kereszturi ◽  
Reddy Pullanagari ◽  
Patricia Durance ◽  
Salman Ashraf ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Total Variation ◽  
Spatial Resolution ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Total Variation Regularization ◽  
Elemental Distribution ◽  
Ground Truth Data ◽  
Resolution Data ◽  
Mineral Prospecting

<p>Geochemical mineral prospecting approaches are mostly point-based surveys which then rely on statistical spatial extrapolation methods to cover larger areas of interest. This leads to a trade-off between increasing sampling density and associated attributes (e.g., elemental distribution). Airborne hyperspectral data is typically high-resolution data, whilst being spatially continuous, and spectrally contiguous, providing a versatile baseline to complement ground-based prospecting approaches and monitoring. In this study, we benchmark various shallow and deep feature extraction algorithms, on airborne hyperspectral data at three different spatial resolutions, 0.8 m, 2 m and 3 m. Spatial resolution is a key factor to detailed scale-dependent mineral prospecting and geological mapping. Airborne hyperspectral data has potential to advance our understanding for delineating new mineral deposits. This approach can be further extended to large areas using forthcoming spaceborne hyperspectral platforms, where procuring finer spatial resolution data is highly challenging. The study area is located along the Rise and Shine Shear Zone (RSSZ) within the Otago schist, in the South Island (New Zealand). The RSSZ contains gold and associated hydrothermal sulphides and carbonate minerals that are disseminated through sheared upper green schist facies rocks on the 10-metre scale, as well as localized (metre-scale) quartz-rich zones. Soil and rock samples from 63 locations were collected, scattered around known mineralised and unmineralized zones, providing ground truth data for benchmarking. The separability between the mineralized and the non-mineralised samples through laboratory based spectral datasets was analysed by applying Partial least squares discriminant analysis (PLS-DA) on the XRF spectra and laboratory based hyperspectral data separately. The preliminary results indicate that even in partially vegetated zones mineralised regions can be mapped out relatively accurately from airborne hyperspectral images using orthogonal total variation component analysis (OTVCA). This focuses on feature extraction by optimising a cost function that best fits the hyperspectral data in a lower dimensional feature space while monitoring the spatial smoothness of the features by applying total variation regularization.</p>

Feature Extraction Based on Multifractal Spectrum for Hyperspectral Data

2009 ◽  
Vol 29 (3) ◽  
pp. 844-847 ◽  
Author(s):  
刘小刚 Liu Xiaogang ◽  
赵慧洁 Zhao Huijie ◽  
李娜 Li Na
Keyword(s):  
Feature Extraction ◽  
Multifractal Spectrum ◽  
Hyperspectral Data
Sign in / Sign up

Export Citation Format

Share Document