scholarly journals Compressed Sensing Technology for Spectral Reconstruction Based on Maximum Entropy Criterion

2021 ◽  
Author(s):  
Shoubo Zhao ◽  
Mengyu Yang ◽  
Yang Wang ◽  
Jianying Fan
Keyword(s):  
Compressed Sensing ◽  
Maximum Entropy ◽  
Spectral Reflectance ◽  
Spectral Curve ◽  
Hyperspectral Data ◽  
Threshold Method ◽  
Data Set ◽  
Spectral Curves ◽  
Sensing Technology ◽  
Entropy Criterion

Abstract In order to choose the related sampling ratio in the information-poor and information-rich spectral fragments, this paper attempts to recover the spectral reflectance by compressed sensing technology based on maximum entropy criterion. The maximum entropy threshold method is the criterion that the optimal threshold is determined to segment the information content of spectral curves. The spectral reflectance in each sub-spectral fragment is reconstructed by compressed sensing. The wavelet orthogonal matrix performs a sparse representation of each segmented spectral curve. Undersampling spectral curve be collected by random gaussian measurement matrix. The orthogonal matching pursuit algorithm recovers sparse original signals from undersampling observed signals. In this paper, the four standard color blocks of Munsell and the spectral curves of five types of ground objects in the hyperspectral data set are used as the exper-imental objects. The reconstructed results are evaluated by spectral curve reconstruction, root mean square error and information entropy difference. The experimental results show that our approach improves the reconstruction accuracy of spectral reflectance effectively, compared with the traditional method.

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.

An Algorithm for Red Tides Species’ Identification Based on Spectral Characteristics and Wavelet Analysis

2015 ◽  
Vol 719-720 ◽  
pp. 1063-1067
Author(s):  
Juan Zhang ◽  
Bing Wang ◽  
He Meng Yang
Keyword(s):  
Wavelet Analysis ◽  
Spectral Reflectance ◽  
Wavelet Decomposition ◽  
Red Tide ◽  
Spectral Characteristics ◽  
Red Tides ◽  
Spectral Curves ◽  
Remote Sensing Technology ◽  
Sensing Technology ◽  
False Recognitions

Hyperspectral remote sensing technology provides a new way to identify red tides types, but many existing methods can’t take full advantage of the spectral reflectance characteristics and often yield false recognitions. So, on the premise of perfect spectral curves library of red tides to be referred, this paper proposes an algorithm based on spectral reflectance characteristics and wavelet decomposition for red tides recognition. The algorithm identify the red tide species by applying wavelet analysis to a certain wavelength range limited by the spectral features. To compare and prove the effect of this algorithm, do simulate experiments with both the proposed method and the traditional SAM method. The results show that, compared with SAM method, the algorithm put forward in this paper can better indentify the species of red tides.

scholarly journals Spectral curves are transcendental

2021 ◽  
Vol 111 (1) ◽  
Author(s):  
H. W. Braden
Keyword(s):  
Spectral Curve ◽  
Spectral Curves ◽  
Arithmetic Properties ◽  
A Charge

AbstractSome arithmetic properties of spectral curves are discussed: the spectral curve, for example, of a charge $$n\ge 2$$ n ≥ 2 Euclidean BPS monopole is not defined over $$\overline{\mathbb {Q}}$$ Q ¯ if smooth.

Constructing the Seismograms of Future Earthquakes in Yunnan, China, Using Compressed Sensing

2020 ◽  
Vol 92 (1) ◽  
pp. 261-274
Author(s):  
Jie Zhang ◽  
Huiyu Zhu ◽  
Siwei Yu ◽  
Jianwei Ma
Keyword(s):  
Compressed Sensing ◽  
Active Fault ◽  
Regional Scale ◽  
Focal Mechanism Solution ◽  
Total Output ◽  
Detailed Knowledge ◽  
Large Dataset ◽  
Sensing Technology ◽  
Data Driven Approach ◽  
Using Data

Abstract The ability to calculate the seismogram of an earthquake at a local or regional scale is critical but challenging for many seismological studies because detailed knowledge about the 3D heterogeneities in the Earth’s subsurface, although essential, is often insufficient. Here, we present an application of compressed sensing technology that can help predict the seismograms of earthquakes at any position using data from past events randomly distributed in the same area in Jinggu County, Yunnan, China. This first data-driven approach for calculating seismograms generates a large dataset in 3D with a volume encompassing an active fault zone. The input number of earthquakes comprises only 1.27% of the total output events. We use the output data to create a database intended to find the best-matching waveform of a new event by applying an earthquake search engine, which instantly reveals the hypocenter and focal-mechanism solution.

A New Index for Steel Framed Roof Information Extraction Based on Remote Sensing

2013 ◽  
Vol 726-731 ◽  
pp. 4682-4685 ◽  
Author(s):  
Jie Ying Xiao ◽  
Na Ji ◽  
Xing Li
Keyword(s):  
Remote Sensing ◽  
Satellite Images ◽  
Spectral Characteristics ◽  
Threshold Method ◽  
Rapid Urbanization ◽  
Surface Information ◽  
Remote Sensing Technology ◽  
Economic Significance ◽  
Tm Image ◽  
Sensing Technology

There are a great number of index methods used to extract impervious surface from satellite images. However, these indices are not robust enough to detect steel framed roof due to the diversity of impervious materials. The extraction of steel framed roof information by remote sensing technology is becoming increasingly important because of its environmental and socio-economic significance. A new index, Normalized Difference Steel framed roof Index (NDSI) is proposed to extract steel framed roof surface information from TM images. The NDSI was created based on its spectral characteristics of TM image and the steel framed roof information can be extracted fast by NDSI threshold method. Additionally, Shijiazhuang city, which has experienced rapid urbanization, was chosen as the study area. And the classification results show that the new index NDSI can effectively extract steel framed roof information with higher accuracy.

scholarly journals A Maximum-Entropy Method to Estimate Discrete Distributions from Samples Ensuring Nonzero Probabilities

Entropy ◽  
2018 ◽  
Vol 20 (8) ◽  
pp. 601 ◽  
Author(s):  
Paul Darscheid ◽  
Anneli Guthke ◽  
Uwe Ehret
Keyword(s):  
Maximum Entropy ◽  
Multinomial Distribution ◽  
Entropy Method ◽  
Small Sample ◽  
Discrete Distributions ◽  
Occupation Probability ◽  
Small Samples ◽  
Data Set ◽  
Sample Distribution ◽  
Leibler Divergence

When constructing discrete (binned) distributions from samples of a data set, applications exist where it is desirable to assure that all bins of the sample distribution have nonzero probability. For example, if the sample distribution is part of a predictive model for which we require returning a response for the entire codomain, or if we use Kullback–Leibler divergence to measure the (dis-)agreement of the sample distribution and the original distribution of the variable, which, in the described case, is inconveniently infinite. Several sample-based distribution estimators exist which assure nonzero bin probability, such as adding one counter to each zero-probability bin of the sample histogram, adding a small probability to the sample pdf, smoothing methods such as Kernel-density smoothing, or Bayesian approaches based on the Dirichlet and Multinomial distribution. Here, we suggest and test an approach based on the Clopper–Pearson method, which makes use of the binominal distribution. Based on the sample distribution, confidence intervals for bin-occupation probability are calculated. The mean of each confidence interval is a strictly positive estimator of the true bin-occupation probability and is convergent with increasing sample size. For small samples, it converges towards a uniform distribution, i.e., the method effectively applies a maximum entropy approach. We apply this nonzero method and four alternative sample-based distribution estimators to a range of typical distributions (uniform, Dirac, normal, multimodal, and irregular) and measure the effect with Kullback–Leibler divergence. While the performance of each method strongly depends on the distribution type it is applied to, on average, and especially for small sample sizes, the nonzero, the simple “add one counter”, and the Bayesian Dirichlet-multinomial model show very similar behavior and perform best. We conclude that, when estimating distributions without an a priori idea of their shape, applying one of these methods is favorable.

scholarly journals Ordinal classification for efficient plant stress prediction in hyperspectral data

2014 ◽  
Vol XL-7 ◽  
pp. 29-36 ◽  
Author(s):  
J. Behmann ◽  
P. Schmitter ◽  
J. Steinrücken ◽  
L. Plümer
Keyword(s):  
Linear Models ◽  
Plant Stress ◽  
Crop Protection ◽  
Local Stress ◽  
Prediction Performance ◽  
Hyperspectral Data ◽  
Hyperspectral Images ◽  
Support Vector ◽  
Data Set ◽  
High Prediction

Detection of crop stress from hyperspectral images is of high importance for breeding and precision crop protection. However, the continuous monitoring of stress in phenotyping facilities by hyperspectral imagers produces huge amounts of uninterpreted data. In order to derive a stress description from the images, interpreting algorithms with high prediction performance are required. Based on a static model, the local stress state of each pixel has to be predicted. Due to the low computational complexity, linear models are preferable. <br><br> In this paper, we focus on drought-induced stress which is represented by discrete stages of ordinal order. We present and compare five methods which are able to derive stress levels from hyperspectral images: One-vs.-one Support Vector Machine (SVM), one-vs.-all SVM, Support Vector Regression (SVR), Support Vector Ordinal Regression (SVORIM) and Linear Ordinal SVM classification. The methods are applied on two data sets - a real world set of drought stress in single barley plants and a simulated data set. It is shown, that Linear Ordinal SVM is a powerful tool for applications which require high prediction performance under limited resources. It is significantly more efficient than the one-vs.-one SVM and even more efficient than the less accurate one-vs.-all SVM. Compared to the very compact SVORIM model, it represents the senescence process much more accurate.

scholarly journals FUSION OF HYPERSPECTRAL, MULTISPECTRAL, COLOR AND 3D POINT CLOUD INFORMATION FOR THE SEMANTIC INTERPRETATION OF URBAN ENVIRONMENTS

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 1899-1906 ◽  
Author(s):  
M. Weinmann ◽  
M. Weinmann
Keyword(s):  
3D Structure ◽  
Urban Environments ◽  
Hyperspectral Data ◽  
Semantic Interpretation ◽  
Lidar Data ◽  
Data Set ◽  
Feature Sets ◽  
Sensor Platforms ◽  
The Given ◽  
Color Imagery

<p><strong>Abstract.</strong> In this paper, we address the semantic interpretation of urban environments on the basis of multi-modal data in the form of RGB color imagery, hyperspectral data and LiDAR data acquired from aerial sensor platforms. We extract radiometric features based on the given RGB color imagery and the given hyperspectral data, and we also consider different transformations to potentially better data representations. For the RGB color imagery, these are achieved via color invariants, normalization procedures or specific assumptions about the scene. For the hyperspectral data, we involve techniques for dimensionality reduction and feature selection as well as a transformation to multispectral Sentinel-2-like data of the same spatial resolution. Furthermore, we extract geometric features describing the local 3D structure from the given LiDAR data. The defined feature sets are provided separately and in different combinations as input to a Random Forest classifier. To assess the potential of the different feature sets and their combination, we present results achieved for the MUUFL Gulfport Hyperspectral and LiDAR Airborne Data Set.</p>

Sign in / Sign up

Export Citation Format

Share Document