Sensors

Research

21 pages, 13766 KiB

Open AccessArticle

A Full-Spectrum Registration Method for Zhuhai-1 Satellite Hyperspectral Imagery

by Jinjun Meng, Jiaqi Wu, Linlin Lu, Qingting Li, Qiang Zhang, Suyun Feng and Jun Yan

Sensors 2020, 20(21), 6298; https://doi.org/10.3390/s20216298 - 5 Nov 2020

Cited by 6 | Viewed by 3193

Accurate registration is an essential prerequisite for analysis and applications involving remote sensing imagery. It is usually difficult to extract enough matching points for inter-band registration in hyperspectral imagery due to the different spectral responses for land features in different image bands. This [...] Read more.

Accurate registration is an essential prerequisite for analysis and applications involving remote sensing imagery. It is usually difficult to extract enough matching points for inter-band registration in hyperspectral imagery due to the different spectral responses for land features in different image bands. This is especially true for non-adjacent bands. The inconsistency in geometric distortion caused by topographic relief also makes it inappropriate to use a single affine transformation relationship for the geometric transformation of the entire image. Currently, accurate registration between spectral bands of Zhuhai-1 satellite hyperspectral imagery remains challenging. In this paper, a full-spectrum registration method was proposed to address this problem. The method combines the transfer strategy based on the affine transformation relationship between adjacent spectrums with the differential correction from dense Delaunay triangulation. Firstly, the scale-invariant feature transform (SIFT) extraction method was used to extract and match feature points of adjacent bands. The RANdom SAmple Consensus (RANSAC) algorithm and the least square method is then used to eliminate mismatching point pairs to obtain fine matching point pairs. Secondly, a dense Delaunay triangulation was constructed based on fine matching point pairs. The affine transformation relation for non-adjacent bands was established for each triangle using the affine transformation relation transfer strategy. Finally, the affine transformation relation was used to perform differential correction for each triangle. Three Zhuhai-1 satellite hyperspectral images covering different terrains were used as experiment data. The evaluation results showed that the adjacent band registration accuracy ranged from 0.2 to 0.6 pixels. The structural similarity measure and cosine similarity measure between non-adjacent bands were both greater than 0.80. Moreover, the full-spectrum registration accuracy was less than 1 pixel. These registration results can meet the needs of Zhuhai-1 hyperspectral imagery applications in various fields. Full article

(This article belongs to the Special Issue Hyperspectral Imaging (HSI) Sensing and Analysis)

► Show Figures

Figure 1

19 pages, 8437 KiB

Open AccessArticle

Spatial–Spectral Feature Refinement for Hyperspectral Image Classification Based on Attention-Dense 3D-2D-CNN

by Jin Zhang, Fengyuan Wei, Fan Feng and Chunyang Wang

Sensors 2020, 20(18), 5191; https://doi.org/10.3390/s20185191 - 11 Sep 2020

Cited by 36 | Viewed by 5072

Abstract

Convolutional neural networks provide an ideal solution for hyperspectral image (HSI) classification. However, the classification effect is not satisfactory when limited training samples are available. Focused on “small sample” hyperspectral classification, we proposed a novel 3D-2D-convolutional neural network (CNN) model named AD-HybridSN (Attention-Dense-HybridSN). [...] Read more.

Convolutional neural networks provide an ideal solution for hyperspectral image (HSI) classification. However, the classification effect is not satisfactory when limited training samples are available. Focused on “small sample” hyperspectral classification, we proposed a novel 3D-2D-convolutional neural network (CNN) model named AD-HybridSN (Attention-Dense-HybridSN). In our proposed model, a dense block was used to reuse shallow features and aimed at better exploiting hierarchical spatial–spectral features. Subsequent depth separable convolutional layers were used to discriminate the spatial information. Further refinement of spatial–spectral features was realized by the channel attention method and spatial attention method, which were performed behind every 3D convolutional layer and every 2D convolutional layer, respectively. Experiment results indicate that our proposed model can learn more discriminative spatial–spectral features using very few training data. In Indian Pines, Salinas and the University of Pavia, AD-HybridSN obtain 97.02%, 99.59% and 98.32% overall accuracy using only 5%, 1% and 1% labeled data for training, respectively, which are far better than all the contrast models. Full article

(This article belongs to the Special Issue Hyperspectral Imaging (HSI) Sensing and Analysis)

► Show Figures

Figure 1

14 pages, 3042 KiB

Open AccessArticle

Application of Convolutional Neural Network-Based Feature Extraction and Data Fusion for Geographical Origin Identification of Radix Astragali by Visible/Short-Wave Near-Infrared and Near Infrared Hyperspectral Imaging

by Qinlin Xiao, Xiulin Bai, Pan Gao and Yong He

Sensors 2020, 20(17), 4940; https://doi.org/10.3390/s20174940 - 1 Sep 2020

Cited by 36 | Viewed by 3530

Abstract

Radix Astragali is a prized traditional Chinese functional food that is used for both medicine and food purposes, with various benefits such as immunomodulation, anti-tumor, and anti-oxidation. The geographical origin of Radix Astragali has a significant impact on its quality attributes. Determining the [...] Read more.

Radix Astragali is a prized traditional Chinese functional food that is used for both medicine and food purposes, with various benefits such as immunomodulation, anti-tumor, and anti-oxidation. The geographical origin of Radix Astragali has a significant impact on its quality attributes. Determining the geographical origins of Radix Astragali is essential for quality evaluation. Hyperspectral imaging covering the visible/short-wave near-infrared range (Vis-NIR, 380–1030 nm) and near-infrared range (NIR, 874–1734 nm) were applied to identify Radix Astragali from five different geographical origins. Principal component analysis (PCA) was utilized to form score images to achieve preliminary qualitative identification. PCA and convolutional neural network (CNN) were used for feature extraction. Measurement-level fusion and feature-level fusion were performed on the original spectra at different spectral ranges and the corresponding features. Support vector machine (SVM), logistic regression (LR), and CNN models based on full wavelengths, extracted features, and fusion datasets were established with excellent results; all the models obtained an accuracy of over 98% for different datasets. The results illustrate that hyperspectral imaging combined with CNN and fusion strategy could be an effective method for origin identification of Radix Astragali. Full article

(This article belongs to the Special Issue Hyperspectral Imaging (HSI) Sensing and Analysis)

► Show Figures

Figure 1

Figure 1
RGB images of Radix Astragali from Gansu province, Heilongjiang province, the Inner Mongolia autonomous region, Shanxi province, and the Xinjiang Uygur autonomous region. Full article ">Figure 2
The structure of the convolutional neural network (CNN) and the flowchart of deep spectral features used in the support vector machine (SVM)/logistic regression (LR)/CNN classifier. Full article ">Figure 3
The average spectra with standard deviation (SD) of Radix Astragali from five origins in the range of (a) 441–947 nm (the standard deviation at 657 and 900 nm are shown); (b) 975–1646 nm (the standard deviation at 1116, 1207, 1311 and 1494 nm are shown). Full article ">Figure 4
The flow chart of the analysis process in this study. Full article ">Figure 5
Principal component analysis (PCA) score images of the first six PCs for Radix Astragali from five geographical origins. (Left side: PCA score images of hyperspectral images in the Vis-NIR region; Right side: PCA score images of hyperspectral images in the NIR region). Full article ">Figure 6
Prediction map for Radix Astragali of all the geographical origins based on the CNN model using full wavelengths: (a) prediction map using Vis-NIR spectra; and (b) prediction map using NIR spectra. Full article ">

21 pages, 7715 KiB

Open AccessArticle

Restoration and Calibration of Tilting Hyperspectral Super-Resolution Image

by Xizhen Zhang, Aiwu Zhang, Mengnan Li, Lulu Liu and Xiaoyan Kang

Sensors 2020, 20(16), 4589; https://doi.org/10.3390/s20164589 - 15 Aug 2020

Cited by 3 | Viewed by 2411

Abstract

Tilting sampling is a novel sampling mode for achieving a higher resolution of hyperspectral imagery. However, most studies on the tilting image have only focused on a single band, which loses the features of hyperspectral imagery. This study focuses on the restoration of [...] Read more.

Tilting sampling is a novel sampling mode for achieving a higher resolution of hyperspectral imagery. However, most studies on the tilting image have only focused on a single band, which loses the features of hyperspectral imagery. This study focuses on the restoration of tilting hyperspectral imagery and the practicality of its results. First, we reduced the huge data of tilting hyperspectral imagery by the p-value sparse matrix band selection method (pSMBS). Then, we restored the reduced imagery by optimal reciprocal cell combined modulation transfer function (MTF) method. Next, we built the relationship between the restored tilting image and the original normal image. We employed the least square method to solve the calibration equation for each band. Finally, the calibrated tilting image and original normal image were both classified by the unsupervised classification method (K-means) to confirm the practicality of calibrated tilting images in remote sensing applications. The results of classification demonstrate the optimal reciprocal cell combined MTF method can effectively restore the tilting image and the calibrated tiling image can be used in remote sensing applications. The restored and calibrated tilting image has a higher resolution and better spectral fidelity. Full article

(This article belongs to the Special Issue Hyperspectral Imaging (HSI) Sensing and Analysis)

► Show Figures

Figure 1

13 pages, 3402 KiB

Open AccessArticle

Low-Cost Hyperspectral Imaging System: Design and Testing for Laboratory-Based Environmental Applications

by Mary B. Stuart, Leigh R. Stanger, Matthew J. Hobbs, Tom D. Pering, Daniel Thio, Andrew J.S. McGonigle and Jon R. Willmott

Sensors 2020, 20(11), 3293; https://doi.org/10.3390/s20113293 - 9 Jun 2020

Cited by 35 | Viewed by 8690

Abstract

The recent surge in the development of low-cost, miniaturised technologies provides a significant opportunity to develop miniaturised hyperspectral imagers at a fraction of the cost of currently available commercial set-ups. This article introduces a low-cost laboratory-based hyperspectral imager developed using commercially available components. [...] Read more.

The recent surge in the development of low-cost, miniaturised technologies provides a significant opportunity to develop miniaturised hyperspectral imagers at a fraction of the cost of currently available commercial set-ups. This article introduces a low-cost laboratory-based hyperspectral imager developed using commercially available components. The imager is capable of quantitative and qualitative hyperspectral measurements, and it was tested in a variety of laboratory-based environmental applications where it demonstrated its ability to collect data that correlates well with existing datasets. In its current format, the imager is an accurate laboratory measurement tool, with significant potential for ongoing future developments. It represents an initial development in accessible hyperspectral technologies, providing a robust basis for future improvements. Full article

(This article belongs to the Special Issue Hyperspectral Imaging (HSI) Sensing and Analysis)

► Show Figures

Figure 1

17 pages, 5600 KiB

Open AccessArticle

Distributed Compressed Hyperspectral Sensing Imaging Based on Spectral Unmixing

by Zhongliang Wang and Hua Xiao

Sensors 2020, 20(8), 2305; https://doi.org/10.3390/s20082305 - 17 Apr 2020

Cited by 8 | Viewed by 2915

Abstract

The huge volume of hyperspectral imagery demands enormous computational resources, storage memory, and bandwidth between the sensor and the ground stations. Compressed sensing theory has great potential to reduce the enormous cost of hyperspectral imagery by only collecting a few compressed measurements on [...] Read more.

The huge volume of hyperspectral imagery demands enormous computational resources, storage memory, and bandwidth between the sensor and the ground stations. Compressed sensing theory has great potential to reduce the enormous cost of hyperspectral imagery by only collecting a few compressed measurements on the onboard imaging system. Inspired by distributed source coding, in this paper, a distributed compressed sensing framework of hyperspectral imagery is proposed. Similar to distributed compressed video sensing, spatial-spectral hyperspectral imagery is separated into key-band and compressed-sensing-band with different sampling rates during collecting data of proposed framework. However, unlike distributed compressed video sensing using side information for reconstruction, the widely used spectral unmixing method is employed for the recovery of hyperspectral imagery. First, endmembers are extracted from the compressed-sensing-band. Then, the endmembers of the key-band are predicted by interpolation method and abundance estimation is achieved by exploiting sparse penalty. Finally, the original hyperspectral imagery is recovered by linear mixing model. Extensive experimental results on multiple real hyperspectral datasets demonstrate that the proposed method can effectively recover the original data. The reconstruction peak signal-to-noise ratio of the proposed framework surpasses other state-of-the-art methods. Full article

(This article belongs to the Special Issue Hyperspectral Imaging (HSI) Sensing and Analysis)

► Show Figures

Figure 1

29 pages, 7479 KiB

Open AccessArticle

Three-Dimensional ResNeXt Network Using Feature Fusion and Label Smoothing for Hyperspectral Image Classification

by Peida Wu, Ziguan Cui, Zongliang Gan and Feng Liu

Sensors 2020, 20(6), 1652; https://doi.org/10.3390/s20061652 - 16 Mar 2020

Cited by 26 | Viewed by 4695

Abstract

In recent years, deep learning methods have been widely used in the hyperspectral image (HSI) classification tasks. Among them, spectral-spatial combined methods based on the three-dimensional (3-D) convolution have shown good performance. However, because of the three-dimensional convolution, increasing network depth will result [...] Read more.

In recent years, deep learning methods have been widely used in the hyperspectral image (HSI) classification tasks. Among them, spectral-spatial combined methods based on the three-dimensional (3-D) convolution have shown good performance. However, because of the three-dimensional convolution, increasing network depth will result in a dramatic rise in the number of parameters. In addition, the previous methods do not make full use of spectral information. They mostly use the data after dimensionality reduction directly as the input of networks, which result in poor classification ability in some categories with small numbers of samples. To address the above two issues, in this paper, we designed an end-to-end 3D-ResNeXt network which adopts feature fusion and label smoothing strategy further. On the one hand, the residual connections and split-transform-merge strategy can alleviate the declining-accuracy phenomenon and decrease the number of parameters. We can adjust the hyperparameter cardinality instead of the network depth to extract more discriminative features of HSIs and improve the classification accuracy. On the other hand, in order to improve the classification accuracies of classes with small numbers of samples, we enrich the input of the 3D-ResNeXt spectral-spatial feature learning network by additional spectral feature learning, and finally use a loss function modified by label smoothing strategy to solve the imbalance of classes. The experimental results on three popular HSI datasets demonstrate the superiority of our proposed network and an effective improvement in the accuracies especially for the classes with small numbers of training samples. Full article

(This article belongs to the Special Issue Hyperspectral Imaging (HSI) Sensing and Analysis)

► Show Figures

Figure 1

15 pages, 4825 KiB

Open AccessArticle

Classification of Granite Soils and Prediction of Soil Water Content Using Hyperspectral Visible and Near-Infrared Imaging

by Hwan-Hui Lim, Enok Cheon, Deuk-Hwan Lee, Jun-Seo Jeon and Seung-Rae Lee

Sensors 2020, 20(6), 1611; https://doi.org/10.3390/s20061611 - 13 Mar 2020

Cited by 9 | Viewed by 4241

Abstract

Soil water content is one of the most important physical indicators of landslide hazards. Therefore, quickly and non-destructively classifying soils and determining or predicting water content are essential tasks for the detection of landslide hazards. We investigated hyperspectral information in the visible and [...] Read more.

Soil water content is one of the most important physical indicators of landslide hazards. Therefore, quickly and non-destructively classifying soils and determining or predicting water content are essential tasks for the detection of landslide hazards. We investigated hyperspectral information in the visible and near-infrared regions (400–1000 nm) of 162 granite soil samples collected from Seoul (Republic of Korea). First, effective wavelengths were extracted from pre-processed spectral data using the successive projection algorithm to develop a classification model. A gray-level co-occurrence matrix was employed to extract textural variables, and a support vector machine was used to establish calibration models and the prediction model. The results show that an optimal correct classification rate of 89.8% could be achieved by combining data sets of effective wavelengths and texture features for modeling. Using the developed classification model, an artificial neural network (ANN) model for the prediction of soil water content was constructed. The input parameter was composed of Munsell soil color, area of reflectance (near-infrared), and dry unit weight. The accuracy in water content prediction of the developed ANN model was verified by a coefficient of determination and mean absolute percentage error of 0.91 and 10.1%, respectively. Full article

(This article belongs to the Special Issue Hyperspectral Imaging (HSI) Sensing and Analysis)

► Show Figures

Figure 1

12 pages, 2171 KiB

Open AccessArticle

Development of a Low-Cost Narrow Band Multispectral Imaging System Coupled with Chemometric Analysis for Rapid Detection of Rice False Smut in Rice Seed

by Haiyong Weng, Ya Tian, Na Wu, Xiaoling Li, Biyun Yang, Yiping Huang, Dapeng Ye and Renye Wu

Sensors 2020, 20(4), 1209; https://doi.org/10.3390/s20041209 - 22 Feb 2020

Cited by 15 | Viewed by 3783

Abstract

Spectral imaging is a promising technique for detecting the quality of rice seeds. However, the high cost of the system has limited it to more practical applications. The study was aimed to develop a low-cost narrow band multispectral imaging system for detecting rice [...] Read more.

Spectral imaging is a promising technique for detecting the quality of rice seeds. However, the high cost of the system has limited it to more practical applications. The study was aimed to develop a low-cost narrow band multispectral imaging system for detecting rice false smut (RFS) in rice seeds. Two different cultivars of rice seeds were artificially inoculated with RFS. Results have demonstrated that spectral features at 460, 520, 660, 740, 850, and 940 nm were well linked to the RFS. It achieved an overall accuracy of 98.7% with a false negative rate of 3.2% for Zheliang, and 91.4% with 6.7% for Xiushui, respectively, using the least squares-support vector machine. Moreover, the robustness of the model was validated through transferring the model of Zheliang to Xiushui with the overall accuracy of 90.3% and false negative rate of 7.8%. These results demonstrate the feasibility of the developed system for RFS identification with a low detecting cost. Full article

(This article belongs to the Special Issue Hyperspectral Imaging (HSI) Sensing and Analysis)

► Show Figures

Figure 1

Figure 1
Two genotypes of rice seeds Zheliang (a) and Xiushui (b) with different infected degrees of rice false smut (RFS). Full article ">Figure 2
Schematic overview of the analytical procedure for rice false smut (RFS) disease detection. Full article ">Figure 3
The linearities of CCD under different exposure time (a) and illuminance distribution (b) at wavelengths of 460, 520, 660, 740, 850, and 940 nm, respectively, at a working distance of 18 cm. Full article ">Figure 4
Mean reflectance spectra of healthy and rice false smut (RFS) infected rice seeds of Zheliang (a) and Xiushui (b). Principal component analysis of reflectance at six wavelengths in healthy, slightly, and severely infected rice seeds of Zheliang (c) and Xiushui (d). Full article ">Figure 5
The overall accuracies and false negative rates from the least squares-support vector machine (LS-SVM) for rice false smut (RFS) disease detection in Xiushui based on the model established from Zheliang. Full article ">

20 pages, 3820 KiB

Open AccessArticle

Learning Deep Hierarchical Spatial–Spectral Features for Hyperspectral Image Classification Based on Residual 3D-2D CNN

by Fan Feng, Shuangting Wang, Chunyang Wang and Jin Zhang

Sensors 2019, 19(23), 5276; https://doi.org/10.3390/s19235276 - 29 Nov 2019

Cited by 71 | Viewed by 5649

Abstract

Every pixel in a hyperspectral image contains detailed spectral information in hundreds of narrow bands captured by hyperspectral sensors. Pixel-wise classification of a hyperspectral image is the cornerstone of various hyperspectral applications. Nowadays, deep learning models represented by the convolutional neural network (CNN) [...] Read more.

Every pixel in a hyperspectral image contains detailed spectral information in hundreds of narrow bands captured by hyperspectral sensors. Pixel-wise classification of a hyperspectral image is the cornerstone of various hyperspectral applications. Nowadays, deep learning models represented by the convolutional neural network (CNN) provides an ideal solution for feature extraction, and has made remarkable achievements in supervised hyperspectral classification. However, hyperspectral image annotation is time-consuming and laborious, and available training data is usually limited. Due to the “small-sample problem”, CNN-based hyperspectral classification is still challenging. Focused on the limited sample-based hyperspectral classification, we designed an 11-layer CNN model called R-HybridSN (Residual-HybridSN) from the perspective of network optimization. With an organic combination of 3D-2D-CNN, residual learning, and depth-separable convolutions, R-HybridSN can better learn deep hierarchical spatial–spectral features with very few training data. The performance of R-HybridSN is evaluated over three public available hyperspectral datasets on different amounts of training samples. Using only 5%, 1%, and 1% labeled data for training in Indian Pines, Salinas, and University of Pavia, respectively, the classification accuracy of R-HybridSN is 96.46%, 98.25%, 96.59%, respectively, which is far better than the contrast models. Full article

(This article belongs to the Special Issue Hyperspectral Imaging (HSI) Sensing and Analysis)

► Show Figures

Figure 1

22 pages, 4427 KiB

Open AccessArticle

Radiometric Assessment of a UAV-Based Push-Broom Hyperspectral Camera

by M. Alejandra P. Barreto, Kasper Johansen, Yoseline Angel and Matthew F. McCabe

Sensors 2019, 19(21), 4699; https://doi.org/10.3390/s19214699 - 29 Oct 2019

Cited by 34 | Viewed by 6160

Abstract

The use of unmanned aerial vehicles (UAVs) for Earth and environmental sensing has increased significantly in recent years. This is particularly true for multi- and hyperspectral sensing, with a variety of both push-broom and snap-shot systems becoming available. However, information on their radiometric [...] Read more.

The use of unmanned aerial vehicles (UAVs) for Earth and environmental sensing has increased significantly in recent years. This is particularly true for multi- and hyperspectral sensing, with a variety of both push-broom and snap-shot systems becoming available. However, information on their radiometric performance and stability over time is often lacking. The authors propose the use of a general protocol for sensor evaluation to characterize the data retrieval and radiometric performance of push-broom hyperspectral cameras, and illustrate the workflow with the Nano-Hyperspec (Headwall Photonics, Boston USA) sensor. The objectives of this analysis were to: (1) assess dark current and white reference consistency, both temporally and spatially; (2) evaluate spectral fidelity; and (3) determine the relationship between sensor-recorded radiance and spectroradiometer-derived reflectance. Both the laboratory-based dark current and white reference evaluations showed an insignificant increase over time (<2%) across spatial pixels and spectral bands for >99.5% of pixel–waveband combinations. Using a mercury/argon (Hg/Ar) lamp, the hyperspectral wavelength bands exhibited a slight shift of 1-3 nm against 29 Hg/Ar wavelength emission lines. The relationship between the Nano-Hyperspec radiance values and spectroradiometer-derived reflectance was found to be highly linear for all spectral bands. The developed protocol for assessing UAV-based radiometric performance of hyperspectral push-broom sensors showed that the Nano-Hyperspec data were both time-stable and spectrally sound. Full article

(This article belongs to the Special Issue Hyperspectral Imaging (HSI) Sensing and Analysis)

► Show Figures

Figure 1

Figure 1
Workflow used in this study for assessing the performance of the push-broom hyperspectral sensor. Full article ">Figure 2
Spectral signature for the dark current (covered lens) experiment with an exposure of 6 ms, showing (a) DN mean spectral signature, (b) standard deviation of the DN spectral signature, (c) radiance mean spectral signature, and (d) standard deviation of the radiance spectral signature. Full article ">Figure 3
Temporal analysis for the dark current experiment with an exposure of 6 ms, showing (a) percentage of variation on a range from −2.5% to 5.6 between the first and the last radiance measurements, and (b) time series analysis of the percentage of variation from the first measurement. The gray region represents the area enclosed between the maximum and minimum values of relative difference. The global mean is depicted in black, the mean for the red-green-blue (RGB) regions of the spectrum are depicted in red, green, and blue, respectively, and the near-infrared (NIR) region is shown in yellow. Full article ">Figure 4
Spectral signature for the white reference with an exposure of 12.5 ms, showing (a) DN mean spectral signature, (b) standard deviation of the DN spectral signature, (c) radiance mean spectral signature, (d) standard deviation of the radiance spectral signature, and (e) Spectralon radiance response. Full article ">Figure 5
Temporal analysis for the white reference experiment at an exposure of 12.5 ms, showing (a) percentage of variation between the first and the last radiance measurement at 30 min, and (b) time series analysis of the percentage of variation in radiance from the first measurement. The gray region represents the area enclosed between the maximum and minimum values of relative difference. The global mean is depicted in black, the mean for the RGB regions of the spectrum are depicted in red, green, and blue, respectively, and the NIR region is shown in yellow. Full article ">Figure 6
Normalized intensity comparison between Hg lamp (a) and Ar lamp (b) emission lines (vertical black lines, see <a href="#sensors-19-04699-t002" class="html-table">Table 2</a> for reference values) and recorded spectra with the ASD Fieldspec-4 (blue curve) and the Nano-Hyperspec sensor (orange). Full article ">Figure 7
Residuals vs. fitted reflectance plots for (a) Spectralon, (b) Masonite, and (c) oak plywood panels. Blue dots correspond to a wavelength of 447 nm in the blue region of the spectrum, green dots to a wavelength of 554 nm in the green region, red dots to a wavelength of 652 nm in the red region, and yellow points to a wavelength of 850 nm in the NIR region. The legend is accompanied by R2 of the regression for the specific wavelengths. Full article ">

Journal Menu

Journal Browser

Hyperspectral Imaging (HSI) Sensing and Analysis

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (11 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI