Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Recent Advances in Multi- and Hyperspectral Image Analysis

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Remote Sensors".

Deadline for manuscript submissions: closed (31 May 2021) | Viewed by 39722

Share This Special Issue

Special Issue Editor

Dr. Jakub Nalepa

E-Mail Website
Guest Editor

1. Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland
2. KP Labs, Konarskiego 18C, 44-100 Gliwice, Poland
Interests: machine learning; deep learning; hyperspectral image analysis; satellite imaging; medical imaging; computer vision; image processing; data mining; super-resolution reconstruction
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Current advancements in sensor technology bring new possibilities in multi- and hyperspectral imaging. Real-life use cases which can benefit from such imagery span various domains, including precision agriculture, chemistry, biology, medicine, land cover applications, management of natural resources, detecting natural disasters, and more. To extract value from the detailed information available in up to hundreds of spectral bands in the electromagnetic spectrum, researchers have been designing a range of image-processing- and machine-learning-powered approaches toward efficient processing of such data. To this end, multi/hyperspectral analysis has bloomed and become an exciting research area which can enable faster adoption of this technology in practice, also when deployed in hardware-constrained and extreme execution environments, e.g., on board of imaging satellites.

The aim of this Special Issue is to gather and present recent advances in multi- and hyperspectral image analysis. The core themes of this topic cover all steps of the data processing pipeline, from its acquisition to final analysis and understanding. These themes include but are not limited to:

Pre/post-processing of multi/hyperspectral images;
Band selection from multi/hyperspectral images;
Feature extraction and learning from multi/hyperspectral images;
Data fusion of high-dimensional data;
Spectral and spatial super-resolution;
Spectral unmixing;
Deep learning-powered algorithms for multi/hyperspectral data analysis;
Classification and segmentation of multi/hyperspectral images;
Multitemporal and multisensor analysis;
Event detection and tracking;
Prediction from multi/hyperspectral data;
Deployment of machine/deep learning-powered techniques for multi/hyperspectral data analysis in hardware-constrained environments;
Robustness of deep learning-powered techniques for multi/hyperspectral data analysis;
Concept drift in multi/hyperspectral data analysis.

Dr. Jakub Nalepa
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

Hyperspectral image analysis
Multispectral image analysis
Band selection
Dimensionality reduction
Feature extraction
Spectral unmixing
Data fusion
Super-resolution reconstruction
Machine learning
Deep learning
On-board processing
Classification
Segmentation
Prediction
Earth observation

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (9 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Editorial

Jump to: Research

8 pages, 197 KiB

Open AccessEditorial

Recent Advances in Multi- and Hyperspectral Image Analysis

by Jakub Nalepa

Sensors 2021, 21(18), 6002; https://doi.org/10.3390/s21186002 - 8 Sep 2021

Cited by 37 | Viewed by 7289

Abstract

Current advancements in sensor technology bring new possibilities in multi- and hyperspectral imaging. Real-life use cases which can benefit from such imagery span across various domains, including precision agriculture, chemistry, biology, medicine, land cover applications, management of natural resources, detecting natural disasters, and more. To extract value from such highly dimensional data capturing up to hundreds of spectral bands in the electromagnetic spectrum, researchers have been developing a range of image processing and machine learning analysis pipelines to process these kind of data as efficiently as possible. To this end, multi- or hyperspectral analysis has bloomed and has become an exciting research area which can enable the faster adoption of this technology in practice, also when such algorithms are deployed in hardware-constrained and extreme execution environments; e.g., on-board imaging satellites. Full article

(This article belongs to the Special Issue Recent Advances in Multi- and Hyperspectral Image Analysis)

Research

Jump to: Editorial

25 pages, 25851 KiB

Open AccessArticle

TaijiGNN: A New Cycle-Consistent Generative Neural Network for High-Quality Bidirectional Transformation between RGB and Multispectral Domains

by Xu Liu, Abdelouahed Gherbi, Wubin Li, Zhenzhou Wei and Mohamed Cheriet

Sensors 2021, 21(16), 5394; https://doi.org/10.3390/s21165394 - 10 Aug 2021

Cited by 3 | Viewed by 2189

Abstract

Since multispectral images (MSIs) and RGB images (RGBs) have significantly different definitions and severely imbalanced information entropies, the spectrum transformation between them, especially reconstructing MSIs from RGBs, is a big challenge. We propose a new approach, the Taiji Generative Neural Network (TaijiGNN), to address the above-mentioned problems. TaijiGNN consists of two generators, G_MSI, and G_RGB. These two generators establish two cycles by connecting one generator’s output with the other’s input. One cycle translates the RGBs into the MSIs and converts the MSIs back to the RGBs. The other cycle does the reverse. The cycles can turn the problem of comparing two different domain images into comparing the same domain images. In the same domain, there are neither different domain definition problems nor severely underconstrained challenges, such as reconstructing MSIs from RGBs. Moreover, according to several investigations and validations, we effectively designed a multilayer perceptron neural network (MLP) to substitute the convolutional neural network (CNN) when implementing the generators to make them simple and high performance. Furthermore, we cut off the two traditional CycleGAN’s identity losses to fit the spectral image translation. We also added two consistent losses of comparing paired images to improve the two generators’ training effectiveness. In addition, during the training process, similar to the ancient Chinese philosophy Taiji’s polarity Yang and polarity Yin, the two generators update their neural network parameters by interacting with and complementing each other until they all converge and the system reaches a dynamic balance. Furthermore, several qualitative and quantitative experiments were conducted on the two classical datasets, CAVE and ICVL, to evaluate the performance of our proposed approach. Promising results were obtained with a well-designed simplistic MLP requiring a minimal amount of training data. Specifically, in the CAVE dataset, to achieve comparable state-of-the-art results, we only need half of the dataset for training; for the ICVL dataset, we used only one-fifth of the dataset to train the model, but obtained state-of-the-art results. Full article

(This article belongs to the Special Issue Recent Advances in Multi- and Hyperspectral Image Analysis)

► Show Figures

Figure 1

30 pages, 7613 KiB

Open AccessArticle

Multi-Scale Superpixels Dimension Reduction Hyperspectral Image Classification Algorithm Based on Low Rank Sparse Representation Joint Hierarchical Recursive Filtering

by Shenming Qu, Xuan Liu and Shengbin Liang

Sensors 2021, 21(11), 3846; https://doi.org/10.3390/s21113846 - 2 Jun 2021

Cited by 6 | Viewed by 3125

Abstract

The original Hyperspectral image (HSI) has different degrees of Hughes phenomenon and mixed noise, leading to the decline of classification accuracy. To make full use of the spatial-spectral joint information of HSI and improve the classification accuracy, a novel dual feature extraction framework joint transform domain-spatial domain filtering based on multi-scale-superpixel-dimensionality reduction (LRS-HRFMSuperPCA) is proposed. Our framework uses the low-rank structure and sparse representation of HSI to repair the unobserved part of the original HSI caused by noise and then denoises it through a block-matching 3D algorithm. Next, the dimension of the reconstructed HSI is reduced by principal component analysis (PCA), and the dimensions of the reduced images are segmented by multi-scale entropy rate superpixels. All the principal component images with superpixels are projected into the reconstructed HSI in parallel. Secondly, PCA is once again used to reduce the dimension of all HSIs with superpixels in scale with hyperpixels. Moreover, hierarchical domain transform recursive filtering is utilized to obtain the feature images; ultimately, the decision fusion strategy based on a support vector machine (SVM) is used for classification. According to the Overall Accuracy (OA), Average Accuracy (AA) and Kappa coefficient on the three datasets (Indian Pines, University of Pavia and Salinas), the experimental results have shown that our proposed method outperforms other state-of-the-art methods. The conclusion is that LRS-HRFMSuperPCA can denoise and reconstruct the original HSI and then extract the space-spectrum joint information fully. Full article

(This article belongs to the Special Issue Recent Advances in Multi- and Hyperspectral Image Analysis)

► Show Figures

Figure 1

20 pages, 7949 KiB

Open AccessArticle

In Vitro and In Vivo Multispectral Photoacoustic Imaging for the Evaluation of Chromophore Concentration

by Aneline Dolet, Rita Ammanouil, Virginie Petrilli, Cédric Richard, Piero Tortoli, Didier Vray and François Varray

Sensors 2021, 21(10), 3366; https://doi.org/10.3390/s21103366 - 12 May 2021

Cited by 8 | Viewed by 3134

Abstract

Multispectral photoacoustic imaging is a powerful noninvasive medical imaging technique that provides access to functional information. In this study, a set of methods is proposed and validated, with experimental multispectral photoacoustic images used to estimate the concentration of chromophores. The unmixing techniques used in this paper consist of two steps: (1) automatic extraction of the reference spectrum of each pure chromophore; and (2) abundance calculation of each pure chromophore from the estimated reference spectra. The compared strategies bring positivity and sum-to-one constraints, from the hyperspectral remote sensing field to multispectral photoacoustic, to evaluate chromophore concentration. Particularly, the study extracts the endmembers and compares the algorithms from the hyperspectral remote sensing domain and a dedicated algorithm for segmentation of multispectral photoacoustic data to this end. First, these strategies are tested with dilution and mixing of chromophores on colored 4% agar phantom data. Then, some preliminary in vivo experiments are performed. These consist of estimations of the oxygen saturation rate (sO

_{2}

) in mouse tumors. This article proposes then a proof-of-concept of the interest to bring hyperspectral remote sensing algorithms to multispectral photoacoustic imaging for the estimation of chromophore concentration. Full article

(This article belongs to the Special Issue Recent Advances in Multi- and Hyperspectral Image Analysis)

► Show Figures

Figure 1

20 pages, 1788 KiB

Open AccessArticle

Hyperspectral Imaging for Bloodstain Identification

by Maheen Zulfiqar, Muhammad Ahmad, Ahmed Sohaib, Manuel Mazzara and Salvatore Distefano

Sensors 2021, 21(9), 3045; https://doi.org/10.3390/s21093045 - 27 Apr 2021

Cited by 32 | Viewed by 5441

Abstract

Blood is key evidence to reconstruct crime scenes in forensic sciences. Blood identification can help to confirm a suspect, and for that reason, several chemical methods are used to reconstruct the crime scene however, these methods can affect subsequent DNA analysis. Therefore, this study presents a non-destructive method for bloodstain identification using Hyperspectral Imaging (HSI, 397–1000 nm range). The proposed method is based on the visualization of heme-components bands in the 500–700 nm spectral range. For experimental and validation purposes, a total of 225 blood (different donors) and non-blood (protein-based ketchup, rust acrylic paint, red acrylic paint, brown acrylic paint, red nail polish, rust nail polish, fake blood, and red ink) samples (HSI cubes, each cube is of size 1000 × 512 × 224, in which 1000 × 512 are the spatial dimensions and 224 spectral bands) were deposited on three substrates (white cotton fabric, white tile, and PVC wall sheet). The samples are imaged for up to three days to include aging. Savitzky Golay filtering has been used to highlight the subtle bands of all samples, particularly the aged ones. Based on the derivative spectrum, important spectral bands were selected to train five different classifiers (SVM, ANN, KNN, Random Forest, and Decision Tree). The comparative analysis reveals that the proposed method outperformed several state-of-the-art methods. Full article

(This article belongs to the Special Issue Recent Advances in Multi- and Hyperspectral Image Analysis)

► Show Figures

Figure 1

18 pages, 6186 KiB

Open AccessArticle

Detection of Potassium Deficiency and Momentary Transpiration Rate Estimation at Early Growth Stages Using Proximal Hyperspectral Imaging and Extreme Gradient Boosting

by Shahar Weksler, Offer Rozenstein, Nadav Haish, Menachem Moshelion, Rony Wallach and Eyal Ben-Dor

Sensors 2021, 21(3), 958; https://doi.org/10.3390/s21030958 - 1 Feb 2021

Cited by 20 | Viewed by 4550

Abstract

Potassium is a macro element in plants that is typically supplied to crops in excess throughout the season to avoid a deficit leading to reduced crop yield. Transpiration rate is a momentary physiological attribute that is indicative of soil water content, the plant’s water requirements, and abiotic stress factors. In this study, two systems were combined to create a hyperspectral–physiological plant database for classification of potassium treatments (low, medium, and high) and estimation of momentary transpiration rate from hyperspectral images. PlantArray 3.0 was used to control fertigation, log ambient conditions, and calculate transpiration rates. In addition, a semi-automated platform carrying a hyperspectral camera was triggered every hour to capture images of a large array of pepper plants. The combined attributes and spectral information on an hourly basis were used to classify plants into their given potassium treatments (average accuracy = 80%) and to estimate transpiration rate (RMSE = 0.025 g/min, R² = 0.75) using the advanced ensemble learning algorithm XGBoost (extreme gradient boosting algorithm). Although potassium has no direct spectral absorption features, the classification results demonstrated the ability to label plants according to potassium treatments based on a remotely measured hyperspectral signal. The ability to estimate transpiration rates for different potassium applications using spectral information can aid in irrigation management and crop yield optimization. These combined results are important for decision-making during the growing season, and particularly at the early stages when potassium levels can still be corrected to prevent yield loss. Full article

(This article belongs to the Special Issue Recent Advances in Multi- and Hyperspectral Image Analysis)

► Show Figures

Figure 1

12 pages, 11234 KiB

Open AccessArticle

Correlations in Joint Spectral and Polarization Imaging

by Guillaume Courtier, Pierre-Jean Lapray, Jean-Baptiste Thomas and Ivar Farup

Sensors 2021, 21(1), 6; https://doi.org/10.3390/s21010006 - 22 Dec 2020

Cited by 15 | Viewed by 3160

Abstract

Recent imaging techniques enable the joint capture of spectral and polarization image data. In order to permit the design of computational imaging techniques and future processing of this information, it is interesting to describe the related image statistics. In particular, in this article, we present observations for different correlations between spectropolarimetric channels. The analysis is performed on several publicly available databases that are unified for joint processing. We perform global investigation and analysis on several specific clusters of materials or reflection types. We observe that polarization channels generally have more inter-channel correlation than the spectral channels. Full article

(This article belongs to the Special Issue Recent Advances in Multi- and Hyperspectral Image Analysis)

► Show Figures

Figure 1

24 pages, 10478 KiB

Open AccessArticle

Blood Stain Classification with Hyperspectral Imaging and Deep Neural Networks

by Kamil Książek, Michał Romaszewski, Przemysław Głomb, Bartosz Grabowski and Michał Cholewa

Sensors 2020, 20(22), 6666; https://doi.org/10.3390/s20226666 - 21 Nov 2020

Cited by 25 | Viewed by 6386

Abstract

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. Full article

(This article belongs to the Special Issue Recent Advances in Multi- and Hyperspectral Image Analysis)

► Show Figures

Figure 1

18 pages, 5287 KiB

Open AccessArticle

Extraction and Analysis of Blue Steel Roofs Information Based on CNN Using Gaofen-2 Imageries

by Meiwei Sun, Yingbin Deng, Miao Li, Hao Jiang, Haoling Huang, Wenyue Liao, Yangxiaoyue Liu, Ji Yang and Yong Li

Sensors 2020, 20(16), 4655; https://doi.org/10.3390/s20164655 - 18 Aug 2020

Cited by 10 | Viewed by 2840

Abstract

Blue steel roof is advantageous for its low cost, durability, and ease of installation. It is generally used by industrial areas. The accurate and rapid mapping of blue steel roof is important for the preliminary assessment of inefficient industrial areas and is one of the key elements for quantifying environmental issues like urban heat islands. Here, the DeeplabV3+ semantic segmentation neural network based on GaoFen-2 images was used to analyze the quantity and spatial distribution of blue steel roofs in the Nanhai district, Foshan (including the towns of Shishan, Guicheng, Dali, and Lishui), which is the important manufacturing industry base of China. We found that: (1) the DeeplabV3+ performs well with an overall accuracy of 92%, higher than the maximum likelihood classification; (2) the distribution of blue steel roofs was not even across the whole study area, but they were evenly distributed within the town scale; and (3) strong positive correlation was observed between blue steel roofs area and industrial gross output. These results not only can be used to detect the inefficient industrial areas for regional planning but also provide fundamental data for studies of urban environmental issues. Full article

(This article belongs to the Special Issue Recent Advances in Multi- and Hyperspectral Image Analysis)

► Show Figures

Journal Menu

Journal Browser

Recent Advances in Multi- and Hyperspectral Image Analysis

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (9 papers)

Editorial

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI