A neural network technique for atmospheric compensation and temperature/emissivity separation using LWIR/MWIR hyperspectral data

2004 ◽  
Author(s):  
William J. Blackwell
Keyword(s):  
Neural Network ◽  
Hyperspectral Data ◽  
Atmospheric Compensation

Estimating nitrogen contents of apple leaves based on hyperspectral parameter models at different phenophases

2016 ◽  
Vol 6 (2) ◽  
pp. 942-952
Author(s):  
Xicun ZHU ◽  
Zhuoyuan WANG ◽  
Lulu GAO ◽  
Gengxing ZHAO ◽  
Ling WANG
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Shoot Growth ◽  
Hyperspectral Data ◽  
Estimation Model ◽  
Apple Leaves ◽  
Bp Neural Network Model ◽  
Nitrogen Contents

The objective of the paper is to explore the best phenophase for estimating the nitrogen contents of apple leaves, to establish the best estimation model of the hyperspectral data at different phenophases. It is to improve the apple trees precise fertilization and production management. The experiments were done in 20 orchards in the field, measured hyperspectral data and nitrogen contents of apple leaves at three phenophases in two years, which were shoot growth phenophase, spring shoots pause growth phenophase, autumn shoots pause growth phenophase. The study analyzed the nitrogen contents of apple leaves with its original spectral and first derivative, screened sensitive wavelengths of each phenophase. The hyperspectral parameters were built with the sensitive wavelengths. Multiple stepwise regressions, partial least squares and BP neural network model were adopted in the study. The results showed that 551 nm, 716 nm, 530 nm, 703 nm; 543 nm, 705 nm, 699 nm, 756 nm and 545 nm, 702 nm, 695 nm, 746 nm were sensitive wavelengths of three phenophases. R551+R716, R551*R716, FDR530+FDR703, FDR530*FDR703; R543+R705, R543*R705, FDR699+FDR756, FDR699*FDR756and R545+R702, R545*R702, FDR695+FDR746, FDR695*FDR746 were the best hyperspectral parameters of each phenophase. Of all the estimation models, the estimated effect of shoot growth phenophase was better than other two phenophases, so shoot growth phenophase was the best phenophase to estimate the nitrogen contents of apple leaves based on hyperspectral models. In the three models, the 4-3-1 BP neural network model of shoot growth phenophase was the best estimation model. The R2 of estimated value and measured value was 0.6307, RE% was 23.37, RMSE was 0.6274.

scholarly journals Atmospheric Compensation of PRISMA Data by Means of a Learning Based Approach

2021 ◽  
Vol 13 (15) ◽  
pp. 2967
Author(s):  
Nicola Acito ◽  
Marco Diani ◽  
Gregorio Procissi ◽  
Giovanni Corsini
Keyword(s):  
Spectral Range ◽  
Near Infrared ◽  
Random Noise ◽  
Synthetic Data ◽  
Regression Function ◽  
Short Wave ◽  
Hyperspectral Data ◽  
Electromagnetic Spectrum ◽  
Great Opportunity ◽  
Atmospheric Compensation

Atmospheric compensation (AC) allows the retrieval of the reflectance from the measured at-sensor radiance and is a fundamental and critical task for the quantitative exploitation of hyperspectral data. Recently, a learning-based (LB) approach, named LBAC, has been proposed for the AC of airborne hyperspectral data in the visible and near-infrared (VNIR) spectral range. LBAC makes use of a parametric regression function whose parameters are learned by a strategy based on synthetic data that accounts for (1) a physics-based model for the radiative transfer, (2) the variability of the surface reflectance spectra, and (3) the effects of random noise and spectral miscalibration errors. In this work we extend LBAC with respect to two different aspects: (1) the platform for data acquisition and (2) the spectral range covered by the sensor. Particularly, we propose the extension of LBAC to spaceborne hyperspectral sensors operating in the VNIR and short-wave infrared (SWIR) portion of the electromagnetic spectrum. We specifically refer to the sensor of the PRISMA (PRecursore IperSpettrale della Missione Applicativa) mission, and the recent Earth Observation mission of the Italian Space Agency that offers a great opportunity to improve the knowledge on the scientific and commercial applications of spaceborne hyperspectral data. In addition, we introduce a curve fitting-based procedure for the estimation of column water vapor content of the atmosphere that directly exploits the reflectance data provided by LBAC. Results obtained on four different PRISMA hyperspectral images are presented and discussed.

scholarly journals Early Detection of Plant Viral Disease Using Hyperspectral Imaging and Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 742
Author(s):  
Canh Nguyen ◽  
Vasit Sagan ◽  
Matthew Maimaitiyiming ◽  
Maitiniyazi Maimaitijiang ◽  
Sourav Bhadra ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Early Detection ◽  
Convolutional Neural Network ◽  
Near Infrared ◽  
Hyperspectral Data ◽  
Viral Diseases ◽  
Support Vector ◽  
Spectral Features ◽  
Feature Spaces

Early detection of grapevine viral diseases is critical for early interventions in order to prevent the disease from spreading to the entire vineyard. Hyperspectral remote sensing can potentially detect and quantify viral diseases in a nondestructive manner. This study utilized hyperspectral imagery at the plant level to identify and classify grapevines inoculated with the newly discovered DNA virus grapevine vein-clearing virus (GVCV) at the early asymptomatic stages. An experiment was set up at a test site at South Farm Research Center, Columbia, MO, USA (38.92 N, −92.28 W), with two grapevine groups, namely healthy and GVCV-infected, while other conditions were controlled. Images of each vine were captured by a SPECIM IQ 400–1000 nm hyperspectral sensor (Oulu, Finland). Hyperspectral images were calibrated and preprocessed to retain only grapevine pixels. A statistical approach was employed to discriminate two reflectance spectra patterns between healthy and GVCV vines. Disease-centric vegetation indices (VIs) were established and explored in terms of their importance to the classification power. Pixel-wise (spectral features) classification was performed in parallel with image-wise (joint spatial–spectral features) classification within a framework involving deep learning architectures and traditional machine learning. The results showed that: (1) the discriminative wavelength regions included the 900–940 nm range in the near-infrared (NIR) region in vines 30 days after sowing (DAS) and the entire visual (VIS) region of 400–700 nm in vines 90 DAS; (2) the normalized pheophytization index (NPQI), fluorescence ratio index 1 (FRI1), plant senescence reflectance index (PSRI), anthocyanin index (AntGitelson), and water stress and canopy temperature (WSCT) measures were the most discriminative indices; (3) the support vector machine (SVM) was effective in VI-wise classification with smaller feature spaces, while the RF classifier performed better in pixel-wise and image-wise classification with larger feature spaces; and (4) the automated 3D convolutional neural network (3D-CNN) feature extractor provided promising results over the 2D convolutional neural network (2D-CNN) in learning features from hyperspectral data cubes with a limited number of samples.

scholarly journals SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL IMAGERY USING NEURAL NETWORK ALGORITHM AND HIERARCHICAL SEGMENTATION

2019 ◽  
Vol XLII-2/W12 ◽  
pp. 1-5
Author(s):  
D. Akbari ◽  
M. Moradizadeh ◽  
M. Akbari
Keyword(s):  
Neural Network ◽  
Spatial Information ◽  
Hyperspectral Data ◽  
Support Vector ◽  
Washington Dc ◽  
Hierarchical Segmentation ◽  
Vector Machines ◽  
Neural Network Algorithm ◽  
New Framework

<p><strong>Abstract.</strong> This paper describes a new framework for classification of hyperspectral images, based on both spectral and spatial information. The spatial information is obtained by an enhanced Marker-based Hierarchical Segmentation (MHS) algorithm. The hyperspectral data is first fed into the Multi-Layer Perceptron (MLP) neural network classification algorithm. Then, the MHS algorithm is applied in order to increase the accuracy of less-accurately classified land-cover types. In the proposed approach, the markers are extracted from the classification maps obtained by MLP and Support Vector Machines (SVM) classifiers. Experimental results on Washington DC Mall hyperspectral dataset, demonstrate the superiority of proposed approach compared to the MLP and the original MHS algorithms.</p>

scholarly journals Attention-Based Residual Network with Scattering Transform Features for Hyperspectral Unmixing with Limited Training Samples

2020 ◽  
Vol 12 (3) ◽  
pp. 400 ◽  
Author(s):  
Zeng ◽  
Ritz ◽  
Zhao ◽  
Lan
Keyword(s):  
Neural Network ◽  
Additive Noise ◽  
Hyperspectral Data ◽  
Training Data ◽  
K Nearest Neighbors ◽  
Practical Applications ◽  
Hyperspectral Unmixing ◽  
Scattering Transform ◽  
Training Samples ◽  
Limited Training Samples

This paper proposes a framework for unmixing of hyperspectral data that is based on utilizing the scattering transform to extract deep features that are then used within a neural network. Previous research has shown that using the scattering transform combined with a traditional K-nearest neighbors classifier (STFHU) is able to achieve more accurate unmixing results compared to a convolutional neural network (CNN) applied directly to the hyperspectral images. This paper further explores hyperspectral unmixing in limited training data scenarios, which are likely to occur in practical applications where the access to large amounts of labeled training data is not possible. Here, it is proposed to combine the scattering transform with the attention-based residual neural network (ResNet). Experimental results on three HSI datasets demonstrate that this approach provides at least 40% higher unmixing accuracy compared to the previous STFHU and CNN algorithms when using limited training data, ranging from 5% to 30%, are available. The use of the scattering transform for deriving features within the ResNet unmixing system also leads more than 25% improvement when unmixing hyperspectral data contaminated by additive noise.

scholarly journals Blood Stain Classification with Hyperspectral Imaging and Deep Neural Networks

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6666
Author(s):  
Kamil Książek ◽  
Michał Romaszewski ◽  
Przemysław Głomb ◽  
Bartosz Grabowski ◽  
Michał Cholewa
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Hyperspectral Imaging ◽  
Network Architecture ◽  
Confusion Matrix ◽  
Hyperspectral Data ◽  
Matrix Analysis ◽  
Support Vector ◽  
Test Set

In recent years, growing interest in deep learning neural networks has raised a question on how they can be used for effective processing of high-dimensional datasets produced by hyperspectral imaging (HSI). HSI, traditionally viewed as being within the scope of remote sensing, is used in non-invasive substance classification. One of the areas of potential application is forensic science, where substance classification on the scenes is important. An example problem from that area—blood stain classification—is a case study for the evaluation of methods that process hyperspectral data. To investigate the deep learning classification performance for this problem we have performed experiments on a dataset which has not been previously tested using this kind of model. This dataset consists of several images with blood and blood-like substances like ketchup, tomato concentrate, artificial blood, etc. To test both the classic approach to hyperspectral classification and a more realistic application-oriented scenario, we have prepared two different sets of experiments. In the first one, Hyperspectral Transductive Classification (HTC), both a training and a test set come from the same image. In the second one, Hyperspectral Inductive Classification (HIC), a test set is derived from a different image, which is more challenging for classifiers but more useful from the point of view of forensic investigators. We conducted the study using several architectures like 1D, 2D and 3D convolutional neural networks (CNN), a recurrent neural network (RNN) and a multilayer perceptron (MLP). The performance of the models was compared with baseline results of Support Vector Machine (SVM). We have also presented a model evaluation method based on t-SNE and confusion matrix analysis that allows us to detect and eliminate some cases of model undertraining. Our results show that in the transductive case, all models, including the MLP and the SVM, have comparative performance, with no clear advantage of deep learning models. The Overall Accuracy range across all models is 98–100% for the easier image set, and 74–94% for the more difficult one. However, in a more challenging inductive case, selected deep learning architectures offer a significant advantage; their best Overall Accuracy is in the range of 57–71%, improving the baseline set by the non-deep models by up to 9 percentage points. We have presented a detailed analysis of results and a discussion, including a summary of conclusions for each tested architecture. An analysis of per-class errors shows that the score for each class is highly model-dependent. Considering this and the fact that the best performing models come from two different architecture families (3D CNN and RNN), our results suggest that tailoring the deep neural network architecture to hyperspectral data is still an open problem.

scholarly journals Integrating a Hybrid Back Propagation Neural Network and Particle Swarm Optimization for Estimating Soil Heavy Metal Contents Using Hyperspectral Data

2019 ◽  
Vol 11 (2) ◽  
pp. 419 ◽  
Author(s):  
Piao Liu ◽  
Zhenhua Liu ◽  
Yueming Hu ◽  
Zhou Shi ◽  
Yuchun Pan ◽  
...  
Keyword(s):  
Neural Network ◽  
Heavy Metals ◽  
Heavy Metal ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Hyperspectral Data ◽  
Estimation Accuracy ◽  
Soil Heavy Metals ◽  
Soil Heavy Metal ◽  
Metal Contents

Soil heavy metals affect human life and the environment, and thus, it is very necessary to monitor their contents. Substantial research has been conducted to estimate and map soil heavy metals in large areas using hyperspectral data and machine learning methods (such as neural network), however, lower estimation accuracy is often obtained. In order to improve the estimation accuracy, in this study, a back propagation neural network (BPNN) was combined with the particle swarm optimization (PSO), which led to an integrated PSO-BPNN method used to estimate the contents of soil heavy metals: Cd, Hg, and As. This study was conducted in Guangdong, China, based on the soil heavy metal contents and hyperspectral data collected from 90 soil samples. The prediction accuracies from BPNN and PSO-BPNN were compared using field observations. The results showed that, 1) the sample averages of Cd, Hg, and As were 0.174 mg/kg, 0.132 mg/kg, and 9.761 mg/kg, respectively, with the corresponding maximum values of 0.570 mg/kg, 0.310 mg/kg, and 68.600 mg/kg being higher than the environment baseline values; 2) the transformed and combined spectral variables had higher correlations with the contents of the soil heavy metals than the original spectral data; 3) PSO-BPNN significantly improved the estimation accuracy of the soil heavy metal contents, with the decrease in the mean relative error (MRE) and relative root mean square error (RRMSE) by 68% to 71%, and 64% to 67%, respectively. This indicated that the PSO-BPNN provided great potential to estimate the soil heavy metal contents; and 4) with the PSO-BPNN, the Cd content could also be mapped using HuanJing-1A Hyperspectral Imager (HSI) data with a RRMSE value of 36%, implying that the PSO-BPNN method could be utilized to map the heavy metal content in soil, using both field spectral data and hyperspectral imagery for the large area.

Sign in / Sign up

Export Citation Format

Share Document