scholarly journals CLASSIFICATION OF HYPERSPECTRAL DATA BASED ON GUIDED FILTERING AND RANDOM FOREST

2017 ◽  
Vol XLII-2/W7 ◽  
pp. 821-824
Author(s):  
H. Ma ◽  
W. Feng ◽  
X. Cao ◽  
L. Wang
Keyword(s):  
Random Forest ◽  
Infrared Imaging ◽  
Image Filtering ◽  
Hyperspectral Data ◽  
Spectral Information ◽  
Data Set ◽  
Imaging Spectrometer ◽  
Guided Image Filter ◽  
Spectral Bands ◽  
Guided Image Filtering

Hyperspectral images usually consist of more than one hundred spectral bands, which have potentials to provide rich spatial and spectral information. However, the application of hyperspectral data is still challengeable due to “the curse of dimensionality”. In this context, many techniques, which aim to make full use of both the spatial and spectral information, are investigated. In order to preserve the geometrical information, meanwhile, with less spectral bands, we propose a novel method, which combines principal components analysis (PCA), guided image filtering and the random forest classifier (RF). In detail, PCA is firstly employed to reduce the dimension of spectral bands. Secondly, the guided image filtering technique is introduced to smooth land object, meanwhile preserving the edge of objects. Finally, the features are fed into RF classifier. To illustrate the effectiveness of the method, we carry out experiments over the popular Indian Pines data set, which is collected by Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) sensor. By comparing the proposed method with the method of only using PCA or guided image filter, we find that effect of the proposed method is better.

scholarly journals Comparison and Evaluation of Dimensionality Reduction Techniques for Hyperspectral Data Analysis

Proceedings ◽  
2019 ◽  
Vol 24 (1) ◽  
pp. 6 ◽  
Author(s):  
K Nivedita Priyadarshini ◽  
V Sivashankari ◽  
Sulochana Shekhar ◽  
K Balasubramani
Keyword(s):  
Dimensionality Reduction ◽  
Infrared Imaging ◽  
Principal Component ◽  
Original Data ◽  
Hyperspectral Data ◽  
Imaging Spectrometer ◽  
Reduction Techniques ◽  
Spectral Bands ◽  
Dimensionality Reduction Techniques ◽  
Highly Correlated

Hyperspectral datasets provide explicit ground covers with hundreds of bands. Filtering contiguous hyperspectral datasets potentially discriminates surface features. Therefore, in this study, a number of spectral bands are minimized without losing original information through a process known as dimensionality reduction (DR). Redundant bands portray the fact that neighboring bands are highly correlated, sharing similar information. The benefits of utilizing dimensionality reduction include the ability to slacken the complexity of data during processing and transform original data to remove the correlation among bands. In this paper, two DR methods, principal component analysis (PCA) and minimum noise fraction (MNF), are applied to the Airborne Visible/Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG) dataset of Kalaburagi for discussion.

scholarly journals Regularization Destriping of Remote Sensing Imagery

2016 ◽  
Author(s):  
Ranil Basnayake ◽  
Erik Bollt ◽  
Nicholas Tufillaro ◽  
Jie Sun ◽  
Michelle Gierach
Keyword(s):  
Infrared Imaging ◽  
Lagrange Equations ◽  
Data Set ◽  
Imaging Spectrometer ◽  
Remote Imaging ◽  
Benchmark Data ◽  
Data Gaps ◽  
Technical Details ◽  
Data Fidelity ◽  
Explicit Finite Difference

Abstract. We illustrate the utility of variational destriping for ocean color images from both mulitspectral and hyperspectral sensors. In particular, we examine data from a filter spectrometer, the Visible Infrared Imaging Radiometer Suite (VIIRS) on the Suomi National Polar Partnership (NPP) orbiter, and an airborne grating spectrometer, the Jet Population Laboratory's (JPL) hyperspectral Portable Remote Imaging Spectrometer (PRISM) sensor. We solve the destriping problem using a variational regularization method by giving weights spatially to preserve the other features of the image during the destriping process. The target functional penalizes `the neighborhood of stripes' (strictly, directionally uniform features) while promoting data fidelity, and the functional is minimized by solving the Euler-Lagrange equations with an explicit finite difference scheme. We show the accuracy of our method from a benchmark data set which represents the Sea Surface Temperature off the Coast of Oregon, USA. Technical details, such as how to impose continuity across data gaps using inpainting, are also described.

scholarly journals What Can Multifractal Analysis Tell Us about Hyperspectral Imagery?

2020 ◽  
Vol 12 (24) ◽  
pp. 4077
Author(s):  
Michał Krupiński ◽  
Anna Wawrzaszek ◽  
Wojciech Drzewiecki ◽  
Małgorzata Jenerowicz ◽  
Sebastian Aleksandrowicz
Keyword(s):  
Infrared Imaging ◽  
Atmospheric Correction ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
High Spectral Resolution ◽  
Absorption Bands ◽  
Landscape Type ◽  
Spectral Bands ◽  
Before And After ◽  
Additional Value

Hyperspectral images provide complex information about the Earth’s surface due to their very high spectral resolution (hundreds of spectral bands per pixel). Effective processing of such a large amount of data requires dedicated analysis methods. Therefore, this research applies, for the first time, the degree of multifractality to the global description of all spectral bands of Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) data. Subsets of four hyperspectral images, presenting four landscape types, are analysed. In particular, we verify whether multifractality can be detected in all spectral bands. Furthermore, we analyse variability in multifractality as a function of wavelength, for data before and after atmospheric correction. We try to identify absorption bands and discuss whether multifractal parameters provide additional value or can help in the problem of dimensionality reduction in hyperspectral data or landscape type classification.

scholarly journals A Bidirectional Deep-Learning-Based Spectral Attention Mechanism for Hyperspectral Data Classification

2022 ◽  
Vol 14 (1) ◽  
pp. 217
Author(s):  
Bishwas Praveen ◽  
Vineetha Menon
Keyword(s):  
Deep Learning ◽  
Data Analysis ◽  
Short Term Memory ◽  
Data Classification ◽  
Hyperspectral Data ◽  
Attention Mechanism ◽  
Spectral Information ◽  
Analysis Model ◽  
Analysis Techniques ◽  
Spectral Bands

Hyperspectral remote sensing presents a unique big data research paradigm through its rich information captured across hundreds of spectral bands, which embodies vital spatial and temporal information about the underlying land cover. Deep-learning-based hyperspectral data analysis methodologies have made significant advancements over the past few years. Despite their success, most deep learning frameworks for hyperspectral data classification tend to suffer in terms of computational and classification efficacy as the data size increases. This is largely due to their equal emphasis criteria on the rich spectral information present in the data, albeit all of the spectral information not being essential for hyperspectral data analysis. On the contrary, this redundant information present in the spectral bands can deter the performance of hyperspectral data analysis techniques. Therefore, in this work, we propose a novel bidirectional spectral attention mechanism, which is computationally efficient and capable of adaptive spectral information diversification through selective emphasis on spectral bands that comprise more information and suppress the ones with lesser information. The concept of 3D-convolutions in tandem with bidirectional long short-term memory (LSTM) is used in the proposed architecture as spectral attention mechanism. A feedforward neural network (FNN)-based supervised classification is then performed to validate the performance of our proposed approach. Experimental results reveal that the proposed hyperspectral data analysis model with spectral attention mechanism outperforms other spatial- and spectral-information-extraction-based hyperspectral data analysis techniques compared.

scholarly journals EXTRACTION OF OPTIMAL SPECTRAL BANDS USING HIERARCHICAL BAND MERGING OUT OF HYPERSPECTRAL DATA

2015 ◽  
Vol XL-3/W3 ◽  
pp. 459-465 ◽  
Author(s):  
A. Le Bris ◽  
N. Chehata ◽  
X. Briottet ◽  
N. Paparoditis
Keyword(s):  
Feature Selection ◽  
Hyperspectral Data ◽  
Band Selection ◽  
Data Set ◽  
Spectral Bands ◽  
Relevance Criterion ◽  
Spectral Optimization ◽  
The One ◽  
Selection Algorithms ◽  
Different Levels

Spectral optimization consists in identifying the most relevant band subset for a specific application. It is a way to reduce hyperspectral data huge dimensionality and can be applied to design specific superspectral sensors dedicated to specific land cover applications. Spectral optimization includes both band selection and band extraction. On the one hand, band selection aims at selecting an optimal band subset (according to a relevance criterion) among the bands of a hyperspectral data set, using automatic feature selection algorithms. On the other hand, band extraction defines the most relevant spectral bands optimizing both their position along the spectrum and their width. The approach presented in this paper first builds a hierarchy of groups of adjacent bands, according to a relevance criterion to decide which adjacent bands must be merged. Then, band selection is performed at the different levels of this hierarchy. Two approaches were proposed to achieve this task : a greedy one and a new adaptation of an incremental feature selection algorithm to this hierarchy of merged bands.

scholarly journals The Instrument Design of the DLR Earth Sensing Imaging Spectrometer (DESIS)

Sensors ◽  
2019 ◽  
Vol 19 (7) ◽  
pp. 1622 ◽  
Author(s):  
David Krutz ◽  
Rupert Müller ◽  
Uwe Knodt ◽  
Burghardt Günther ◽  
Ingo Walter ◽  
...  
Keyword(s):  
International Space Station ◽  
Near Infrared ◽  
Space Station ◽  
Hyperspectral Data ◽  
Imaging Spectrometer ◽  
International Space ◽  
Spectral Bands ◽  
Sampling Distance ◽  
Characterization Of Materials ◽  
German Aerospace

Whether for identification and characterization of materials or for monitoring of theenvironment, space-based hyperspectral instruments are very useful. Hyperspectral instrumentsmeasure several dozens up to hundreds of spectral bands. These data help to reconstruct the spectralproperties like reflectance or emission of Earth surface or the absorption of the atmosphere, and toidentify constituents on land, water, and in the atmosphere. There are a lot of possible applications,from vegetation and water quality up to greenhouse gas monitoring. But the actual number ofhyperspectral space-based missions or hyperspectral space-based data is limited. This will be changedin the next years by different missions. The German Aerospace Center (DLR) Earth Sensing ImagingSpectrometer (DESIS) is one of the new currently existing space-based hyperspectral instruments,launched in 2018 and ready to reduce the gap of space-born hyperspectral data. The instrument isoperating onboard the International Space Station, using the Multi-User System for Earth Sensing(MUSES) platform. The instrument has 235 spectral bands in the wavelength range from visible(400 nm) to near-infrared (1000 nm), which results in a 2.5 nm spectral sampling distance and aground sampling distance of 30 m from 400 km orbit of the International Space Station. In this article,the design of the instrument will be described.

scholarly journals Estimation of Noise in the In Situ Hyperspectral Data Acquired by Chang’E-4 and Its Effects on Spectral Analysis of Regolith

2020 ◽  
Vol 12 (10) ◽  
pp. 1603
Author(s):  
Honglei Lin ◽  
Yangting Lin ◽  
Yong Wei ◽  
Rui Xu ◽  
Yang Liu ◽  
...  
Keyword(s):  
Spectral Analysis ◽  
Lunar Surface ◽  
Near Infrared ◽  
Infrared Imaging ◽  
Hyperspectral Data ◽  
Repeated Measurements ◽  
Imaging Spectrometer ◽  
Low Snr ◽  
Spectral Interpretation ◽  
Geologic Interpretation

The Chang’E-4 (CE-4) spacecraft landed successfully on the far side of the Moon on 3 January 2019, and the rover Yutu-2 has explored the lunar surface since then. The visible and near-infrared imaging spectrometer (VNIS) onboard the rover has acquired numerous spectra, providing unprecedented insight into the composition of the lunar surface. However, the noise in these spectral data and its effects on spectral interpretation are not yet assessed. Here we analyzed repeated measurements over the same area at the lunar surface to estimate the signal–noise ratio (SNR) of the VNIS spectra. Using the results, we assessed the effects of noise on the estimation of band centers, band depths, FeO content, optical maturity (OMAT), mineral abundances, and submicroscopic metallic iron (SMFe). The data observed at solar altitudes <20° exhibit low SNR (25 dB), whereas the data acquired at 20°–35° exhibit higher SNR (35–37 dB). We found differences in band centers due to noise to be ~6.2 and up to 28.6 nm for 1 and 2 μm absorption, respectively. We also found that mineral abundances derived using the Hapke model are affected by noise, with maximum standard deviations of 6.3%, 2.4%, and 7.0% for plagioclase, pyroxene, and olivine, respectively. Our results suggest that noise has significant impacts on the CE-4 spectra, which should be considered in the spectral analysis and geologic interpretation of lunar exploration data.

scholarly journals Multilayered autoencoders in problems of hyperspectral image analysis and processing

2021 ◽  
pp. 1-21
Author(s):  
Margarita Georgievna Kuzmina
Keyword(s):  
Image Analysis ◽  
Hyperspectral Image ◽  
Spectral Curve ◽  
Image Data ◽  
Image Features ◽  
Hyperspectral Data ◽  
Spectral Information ◽  
Data Set ◽  
Hyperspectral Image Analysis ◽  
Deep Image

A model of five-layered autoencoder (stacked autoencoder, SAE) is suggested for deep image features extraction and deriving compressed hyperspectral data set specifying the image. Spectral cost function, dependent on spectral curve forms of hyperspectral image, has been used for the autoencoder tuning. At the first step the autoencoder capabilities will be tested based on using pure spectral information contained in image data. The images from well known and widely used hyperspectral databases (Indian Pines, Pavia University и KSC) are planned to be used for the model testing.

Sign in / Sign up

Export Citation Format

Share Document