Extraction Of Spectral Information Research Articles

Inversion of Cotton Soil and Plant Analytical Development Based on Unmanned Aerial Vehicle Multispectral Imagery and Mixed Pixel Decomposition

In order to improve the accuracy of multispectral image inversion of soil and plant analytical development (SPAD) of the cotton canopy, image segmentation methods were utilized to remove the background interference, such as soil and shadow in UAV multispectral images. UAV multispectral images of cotton bud stage canopies at three different heights (30 m, 50 m, and 80 m) were acquired. Four methods, namely vegetation index thresholding (VIT), supervised classification by support vector machine (SVM), spectral mixture analysis (SMA), and multiple endmember spectral mixture analysis (MESMA), were used to segment cotton, soil, and shadows in the multispectral images of cotton. The segmented UAV multispectral images were used to extract the spectral information of the cotton canopy, and eight vegetation indices were calculated to construct the dataset. Partial least squares regression (PLSR), Random forest (FR), and support vector regression (SVR) algorithms were used to construct the inversion model of cotton SPAD. This study analyzed the effects of different image segmentation methods on the extraction accuracy of spectral information and the accuracy of SPAD modeling in the cotton canopy. The results showed that (1) The accuracy of spectral information extraction can be improved by removing background interference such as soil and shadows using four image segmentation methods. The correlation between the vegetation indices calculated from MESMA segmented images and the SPAD of the cotton canopy was improved the most; (2) At three different flight altitudes, the vegetation indices calculated by the MESMA segmentation method were used as the input variable, and the SVR model had the best accuracy in the inversion of cotton SPAD, with R2 of 0.810, 0.778, and 0.697, respectively; (3) At a flight altitude of 80 m, the R2 of the SVR models constructed using vegetation indices calculated from images segmented by VIT, SVM, SMA, and MESMA methods were improved by 2.2%, 5.8%, 13.7%, and 17.9%, respectively, compared to the original images. Therefore, the MESMA mixed pixel decomposition method can effectively remove soil and shadows in multispectral images, especially to provide a reference for improving the inversion accuracy of crop physiological parameters in low-resolution images with more mixed pixels.

Conditional Dynamics in Heterodyne Detection of Superradiant Lasing with Incoherently Pumped Atoms.

In this Letter, we use quantum trajectory theory to simulate heterodyne detection of narrow bandwidth superradiant lasing from an incoherently excited atomic ensemble. To this end, we describe the system dynamics and account for stochastic measurement backaction by second-order mean-field theory. Our simulations show how heterodyne measurements break the phase symmetry, and initiate the atomic coherence with a random phase and a long temporal phase coherence. More importantly, our theory allows direct simulation of experimental procedures for extraction of spectral information which do not lend themselves to evaluation with the quantum regression theorem.

Multi-scale spatial and spectral feature fusion for soil carbon content prediction based on hyperspectral images

Soil carbon content prediction based on hyperspectral images can achieve large-scale spatial measurement, which has the advantages of wide coverage and fast information collection, is more suitable for field data collection. However, the research on soil carbon content prediction based on hyperspectral images mainly focuses on feature extraction of spectral information, ignoring the spatial information, and cannot well reveal the intrinsic structural characteristics of data. Aiming at the lack of spatial features consideration in hyperspectral images, soil carbon content prediction methods based on multi-scale feature fusion are proposed by hyperspectral image. At the same time of extracting spectral features from hyperspectral images, the spatial information is used for the first time and a multi-scale spectral and spatial feature network (SpeSpaMN) is designed. In the SpeSpaMN, the multi-scale spectral feature network (SpeMN) is constructed to extract spectral features, the multi-scale spatial feature network (SpaMN) is constructed to extract spatial features. The two networks are fused by using the complementary relationship between different scale features to achieve soil carbon content prediction based on multi-scale feature fusion. The results showed that SpeSpaMN had the best results compared to other methods, followed by the method of SpeMN. The RPD of Inland, Aoshan Bay and Jiaozhou Bay samples based on SpeSpaMN were increased by 47.36%, 37.96% and 4.30% respectively. This paper can effectively solve the problem of the deep fusion of spatial and spectral features in the soil carbon content prediction by hyperspectral image, so as to improve the accuracy and stability of soil carbon content prediction.

Dual-input ultralight multi-head self-attention learning network for hyperspectral image classification

ABSTRACT In the hyperspectral image (HSI) classification tasks, various deep learning models have achieved remarkable success. However, most deep learning models are compute-intensive, requiring significant computing power, time, and other resources. It becomes a challenge to pursue better results while saving computational resources. Therefore, a novel dual-input ultralight multi-head self-attention learning network (DUMS-LN) is proposed for HSI classification. The proposed DUMS-LN consists of three main core modules, namely the high-dimensional reduced module (HDRM), lightweight multi-head self-attention (LMHSA) module, and linearized hierarchical conversion module (LHCM). HDRM is used as a pre-processing module with efficient data compression and combines spatial and spectral information extraction from the raw data to provide cleaner and more comprehensive feature data for subsequent processing. In addition, the core computational module of DUMS-LN is the LMHSA module, which is lightweight but possesses better data processing capability than the traditional multi-head self-attention module. Finally, the LHCM divides the model into two phases, reducing the dimensionality of the feature data phase by phase so that the LMHSA module can perform feature extraction at different levels. Experiments on four benchmark HSI datasets show that the proposed DUMS-LN outperforms the comparison HSI classification algorithms regarding speed and classification accuracy.

In-season forecasting of within-field grain yield from Sentinel-2 time series data

Precise knowledge of cropland productivity is relevant for farmers to enable optimizing managing practices; particularly with the perspective of anticipating crop yield ahead of harvest. The current availability of high spatiotemporal resolution Sentinel-2 satellite data offers a unique opportunity to monitor croplands over time. In this context, the recently introduced kernel NDVI (kNDVI) statistically optimizes the conventional NDVI formulation by applying a nonlinear function to the involved bands, and so maximizes the spectral information extraction. This study proposes a workflow for within-field yield forecasting from Sentinel-2 kNDVI time series analysis focusing on winter cereal croplands in Switzerland over three years, comparing with NDVI as baseline. For a temporally continuous modelling of crop yields, Gaussian Process Regression (GPR) was applied to reconstruct cloud-free time series of the complete crop growing seasons. Following, distinct machine learning regression models (GPR, Kernel Ridge Regression and Random Forest) were developed to forecast yield at any point in time throughout the cropland growing season. The integration of Growing Degree Days (GDD) information as temporal spacing reference of the time series considerably improved the accuracy and consistency of in-season yield forecasting. Training and testing within the same year demonstrated that yield can be accurately forecast approximately 2–2.5 months ahead of harvest, at crops’ anthesis (flowering) phase, with an RMSE up to 0.71 t/ha and a relative RMSE of 7.60%. Although the forecasting accuracy of the models decreased when predicting yield for the unseen years, still satisfactory results were obtained: RMSE = 0.97 t/ha, relative RMSE = 11.47%.

Time-Frequency Analysis of Two-Dimensional Electron Spin Resonance Signals.

Two-dimensional electron spin resonance (2D ESR) spectroscopy is a unique experimental technique for probing protein structure and dynamics, including processes that occur at the microsecond time scale. While it provides significant resolution enhancement over the one-dimensional experimental setup, spectral broadening and noise make extraction of spectral information highly challenging. Traditionally, two-dimensional Fourier transform (2D FT) is applied for the analysis of 2D ESR signals, although its efficiency is limited to stationary signals. In addition, it often fails to resolve overlapping peaks in 2D ESR. In this work, we propose a time-frequency analysis of 2D time-domain signals, which identifies all frequency peaks by decoupling a signal into its distinct constituent components via projection on the time-frequency plane. The method utilizes 2D undecimated discrete wavelet transform (2D UDWT) as an intermediate step in the analysis, followed by signal reconstruction and 2D FT. We have applied the method to a simulated 2D double quantum coherence (DQC) signal for validation and a set of experimental 2D ESR signals, demonstrating its efficiency in resolving overlapping peaks in the frequency domain, while displaying frequency evolution with time in case of non-stationary data.

MDvT: introducing mobile three-dimensional convolution to a vision transformer for hyperspectral image classification

ABSTRACT Hyperspectral images carry numerous spectral bands, and their wealth of band data is a valuable source of information for the accurate classification of ground objects. Three-dimensional (3D) convolution, although an excellent spectral information extraction method, is limited by its huge number of parameters and long model training time. To allow better integration of 3D convolution with the most popular transformer models currently available, a new architecture called mobile 3D convolutional vision transformer (MDvT) is proposed. The MDvT introduces inverted residual structure to reduce the number of model parameters and balance the data mining efficiency of low-dimensional data input. Simultaneously, a square patch is used to cut the sequence of tokens to accelerate the model operation. Through extensive experiments, we evaluated the classification overall performance of the proposed MDvT on the WHU-Hi and Pavia University datasets, and demonstrated significant improvements in classification accuracy and model runtime compared with classical deep learning models. It is worth noting that compared with directly integrating 3D convolution into the transformer model, the MDvT architecture improves the accuracy while reducing the time to train an epoch by approximately 58.54%. To facilitate the reproduction of the work in this paper, the model code is available at https://github.com/gloryofroad/MDvT.

Multi-frame super-resolution of remote sensing images using attention-based GAN models

Multi-frame super-resolution (MFSR) of remote sensing (RS) imageries becomes a critical research topic with the launch of new satellites having video capturing capability and the advancement of artificial intelligence techniques. In this study, an attention-based Generative Adversarial Network (GAN) algorithm is proposed for the multi-frame remote sensing image super-resolution (MRSISR). Firstly, we introduced an attention module to the generator and designed a space-based net that worked on every single frame for better temporal information extraction. Secondly, we proposed a novel attention module for better spatial and spectral information extraction. Thirdly, we applied an attention-based discriminator for the discriminative ability improvement of the discriminator. We implemented several experiments with the state-of-the-art models and the proposed approach using SpaceNet7 and Jilin-1 datasets. We quantitatively and qualitatively compared the results of different multi-frame super-resolution models.

SISLU-Net: Spatial Information-Assisted Spectral Information Learning Unmixing Network for Hyperspectral Images

Spectral unmixing is among one of the major hyperspectral image analysis tasks that aims to extract basic features (endmembers) at the subpixel level and estimate their corresponding proportions (fractional abundances). Recently, the rapid development of deep learning networks has provided us with a new method to solve the problem of spectral unmixing. In this paper, we propose a spatial-information-assisted spectral information learning unmixing network (SISLU-Net) for hyperspectral images. The SISLU-Net consists of two branches. The upper branch focuses on the extraction of spectral information. The input of the upper branch is a number of pixels randomly extracted from the hyperspectral image. The data are fed into the network as a random combination of different pixel blocks each time. The random combination of batches can boost the network to learn global spectral information. Another branch focuses on learning spatial information from the entire hyperspectral image and transmitting it to the upper branch through the shared weight strategy. This allows the network to take into account the spectral information and spatial information of HSI at the same time. In addition, according to the distribution characteristics of endmembers, we employ Wing loss to solve the problem of uneven distributions of endmembers. Experimental results on one synthetic and three real hyperspectral data sets show that SISLU-Net is effective and competitive compared with several state-of-the-art unmixing algorithms in terms of the spectral angle distance (SAD) of the endmembers and the root mean square error (RMSE) of the abundances.

Search for Nonthermal X-ray Emission in the Ophiuchus Galaxy Cluster

We present the results of our study of the X-ray emission from the Ophiuchus galaxy cluster based on INTEGRAL/IBIS data in the energy range 20–120 keV. Our goal is the search for a nonthermal emission component from the cluster. Using the INTEGRAL data over the period of observations 2003–2009, we have constructed the images of the Ophiuchus galaxy cluster in different energy bands from 20 to 120 keV with the extraction of spectral information. We show that in the hard X-ray energy band the source is an extended one with an angular size of $$4.9^{\prime}\pm 0.1^{\prime}$$ . Assuming a fixed intracluster gas temperature of 8.5 keV, a power-law component of the possible nonthermal X-ray emission is observed at a 5.5 $$\sigma$$ significance level, the flux from which is consistent with previous studies. However, in view of the uncertainty in constraining the thermal emission component in the X-ray spectrum at energies above 20 keV, we cannot make the assertion about a significant detection of nonthermal emission from the cluster. Based on the fact of a confident detection of the cluster up to 70 keV, we can draw the conclusion only about the possible presence of a nonthermal excess at energies above 60 keV.

Ranking Theoretical Supernovae Explosion Models from Observations of the Intracluster Gas

The intracluster medium (ICM) is a reservoir of heavy elements synthesized by different supernovae (SNe) types over cosmic history. Different enrichment mechanisms contribute a different relative metal production, predominantly caused by different SNe type dominance. Using spatially resolved X-ray spectroscopy, one can probe the contribution of each metal-enrichment mechanism. However, a large variety of physically feasible supernova (SN) explosion models make the analysis of the ICM enrichment history more uncertain. This paper presents a nonparametric probability distribution function analysis to rank different theoretical SNe yields models by comparing their performance against observations. Specifically, we apply this new methodology to rank 7192 combinations of core-collapse SN and Type Ia SN models using eight abundance ratios from Suzaku observations of 18 galaxy systems (clusters and groups) to test their predictions. This novel technique can compare many SN models and maximize spectral information extraction, considering all the individual measurable abundance ratios and their uncertainties. We find that Type II SNe with nonzero initial metallicity progenitors in general performed better than pair-instability SN and hypernova models, and that 3D SNIa models (with a white dwarf progenitor central density of 2.9 × 109 g cm−3) performed best among all tested SN model pairs.

Static quark anti-quark interactions at non-zero temperature from lattice QCD

We present results on the in-medium interactions of static quark antiquark pairs using realistic 2+1 HISQ flavor lattice QCD. Focus is put on the extraction of spectral information from Wilson line correlators in Coulomb gauge using four complementary methods. Our results indicate that on HISQ lattices, the position of the dominant spectral peak associated with the real-part of the interquark potential remains unaffected by temperature. This is in contrast to prior work in quenched QCD and we present follow up comparisons to newly generated quenched ensembles.

Helical Nanostructures of Ferroelectric Liquid Crystals as Fast Phase Retarders for Spectral Information Extraction Devices: A Comparison with the Nematic Liquid Crystal Phase Retarders.

Extraction of spectral information using liquid crystal (LC) retarders has recently become a topic of great interest because of its importance for creating hyper- and multispectral images in a compact and inexpensive way. However, this method of hyperspectral imaging requires thick LC-layer retarders (50 µm–100 µm and above) to obtain spectral modulation signals for reliable signal reconstruction. This makes the device extremely slow in the case of nematic LCs (NLCs), since the response time of NLCs increases proportionally to the square of the LC-layer thickness, which excludes fast dynamic processes monitoring. In this paper, we explore two approaches for solving the speed problem: the first is based on the use of faster nanospiral ferroelectric liquid crystals as an alternative to NLCs, and the second is based on using a passive multiband filter and focuses on multispectral extraction rather than hyperspectral. A detailed comparative study of nematic and ferroelectric devices is presented. The study is carried out using a 9-spectral bands passive spectral filter, covering the visible and near-infrared ranges. We propose the concept of multispectral rather than hyperspectral extraction, where a small number of wavelengths are sufficient for specific applications.

Optimal window size selection for spectral information extraction of sampling points from UAV multispectral images for soil moisture content inversion

Soil moisture content monitoring with UAV remote sensing always involves the selection of an appropriate window size for spectral information extraction, but research on the effect of window size on the accuracy of soil moisture content monitoring models and the selection of the optimal window size has been rarely reported. To solve these problems, an experiment was conducted on three typical bare plots in Shahaoqu Experimental Station at Hetao Irrigation District, Inner Mongolia, China. First, remote sensing images were obtained from the three bare plots from April 15 through 17, 2019, with a six-rotor UAV equipped with a six-channel multispectral camera. Synchronously, the moisture content at 0–10 cm of the surface soil was measured using the drying method. Then, the spectral information was extracted through windows of 16 different sizes (ranging from 1 * 1 to 31 * 31). Followed was the construction of thirty spectral indices using the ratio and normalized ratio methods, and the processing of the constructed indices using principal component analysis. The principal components accounting for 95% of the cumulative contribution rate were selected as the input variables for the construction of the monitoring models based on BP neural network. Finally, the model accuracy was tested using ANOVA, and the local variogram of the spectrum was used to explore the optimal window size selection. The results demonstrated: (1) There are differences in the spectral information extracted from different sizes of windows, which affects the accuracy of soil moisture monitoring model; (2) The spatial autocorrelation threshold of the plots at the local variogram was 13 * 13, resembling the window size with the highest accuracy, so it is feasible to select the optimal window size with the local variogram; (3) As the window size of spectral information increased, R2 first increased and then decreased, reaching the maximum value of 0.261 at the size of 13 * 13, and RMSE first decreased and then increased, reaching the minimum value of 0.017 when at the size of 7 * 7. These results can provide some reference for window size selection in spectral information extraction to monitor soil moisture content.

Nondestructive detection for Panax notoginseng powder grades based on hyperspectral imaging technology combined with CARS‐PCA and MPA‐LSSVM

AbstractThis study investigated the feasibility of using hyperspectral imaging (HSI) technology to detect Panax notoginseng powder grades. The hyperspectral images of 240 Panax notoginseng powder samples were collected in the spectral range of 450–1,000 nm. Savitzky–golay (SG) and multiplicative scatter correction (MSC) were used to preprocess the original spectra. A method of combing competitive adaptive reweighted sampling (CARS) and principal component analysis (PCA) was used to analyze the spectral data and eliminate the influence caused by the randomness of Monte Carlo (MC) sampling. The least‐squares support vector machine (LSSVM) modeling results showed that CARS‐PCA had better spectral information extraction performance than PCA and CARS, and two principal components were extracted for modeling. The average classification accuracy of PCA‐LSSVM, CARS‐LSSVM, and PCA‐CARS‐LSSVM was 88.33, 90.93, and 92.5%, respectively. To further improve the modeling accuracy, a marine predators algorithm least squares support vector machine (MPA‐LSSVM) model was proposed to identify the grades of Panax notoginseng powder. The result indicated that MPA‐LSSVM had higher modeling accuracy and stronger robustness than the other compared models, and the classification accuracy of the training set and test set was 96.67 and 95%, respectively. The results illustrated the potential of HSI technology as an effective tool in Panax notoginseng powder grades detection.Practical ApplicationThis study verified the feasibility of using HSI technology to detect the grades of Panax notoginseng powder. Two principal components were extracted, which were used for simplifying the LSSVM model based on full wavelengths. The simplified model achieved high classification accuracy (95%), which provides a basis for the design of a multispectral imaging system.

Feedback Convolutional Network for Intelligent Data Fusion Based on Near-Infrared Collaborative IoT Technology

Near-infrared (NIR) data containing spectral response information for detecting target composition are sparsely implied in spectral frequency sequence. Spectral feature information should be extracted using computer-oriented chemometric methods. An Internet of Things (IoT) framework constructed with NIR calibration platform needs some advanced algorithm architectures to realize intelligent analysis. A feedback convolutional neural network (CNN) architecture, including three repeated segments of convolution, pooling, and flattening, is designed in this article for multiple extraction of spectral features from one-dimensional NIR data. An error-feedback iteration mechanism is proposed in the model training process to optimize convolution filters of each segment. Multisegment features are fused successively to ease the sparse information issue. Fusion data are further used to train the calibration models with a parametric-scaling fully connected network to determine the suitable numbers of hidden and output nodes. The adaptive network structure has the advantage of obtaining optimal prediction results from fused feature data. The proposed feedback CNN architecture based on feature information fusion is applied to the NIR rapid quantitative detection of selenium content in paddy rice samples. Experimental results showed that the fusion of multisegment features can enhance the ability of spectral information extraction. The optimal model based on fused feature data performs better than models based on separate feature data of each segment. The feedback convolutional network for information fusion can be applied in the NIR collaborative IoT framework for rapid detection spectroscopy to ensure high-confidence NIR analysis in the artificial intelligence performance of IoT.

Extraction of Spectral Information from Airborne 3D Data for Assessment of Tree Species Proportions

With the rapid development of photogrammetric software and accessible camera technology, land surveys and other mapping organizations now provide various point cloud and digital surface model products from aerial images, often including spectral information. In this study, methods for colouring the point cloud and the importance of different metrics were compared for tree species-specific estimates at a coniferous hemi-boreal test site in southern Sweden. A total of three different data sets of aerial image-based products and one multi-spectral lidar data set were used to estimate tree species-specific proportion and stem volume using an area-based approach. Metrics were calculated for 156 field plots (10 m radius) from point cloud data and used in a Random Forest analysis. Plot level accuracy was evaluated using leave-one-out cross-validation. The results showed small differences in estimation accuracy of species-specific variables between the colouring methods. Simple averages of the spectral metrics had the highest importance and using spectral data from two seasons improved species prediction, especially deciduous proportion. Best tree species-specific proportion was estimated using multi-spectral lidar with 0.22 root mean square error (RMSE) for pine, 0.22 for spruce and 0.16 for deciduous. Corresponding RMSE for aerial images was 0.24, 0.23 and 0.20 for pine, spruce and deciduous, respectively. For the species-specific stem volume at plot level using image data, the RMSE in percent of surveyed mean was 129% for pine, 60% for spruce and 118% for deciduous.

Attention-Based Pyramid Network for Segmentation and Classification of High-Resolution and Hyperspectral Remote Sensing Images

Unlike conventional natural (RGB) images, the inherent large scale and complex structures of remote sensing images pose major challenges such as spatial object distribution diversity and spectral information extraction when existing models are directly applied for image classification. In this study, we develop an attention-based pyramid network for segmentation and classification of remote sensing datasets. Attention mechanisms are used to develop the following modules: (i) a novel and robust attention-based multi-scale fusion method effectively fuses useful spatial or spectral information at different and same scales; (ii) a region pyramid attention mechanism using region-based attention addresses the target geometric size diversity in large-scale remote sensing images; and (iii) cross-scale attention in our adaptive atrous spatial pyramid pooling network adapts to varied contents in a feature-embedded space. Different forms of feature fusion pyramid frameworks are established by combining these attention-based modules. First, a novel segmentation framework, called the heavy-weight spatial feature fusion pyramid network (FFPNet), is proposed to address the spatial problem of high-resolution remote sensing images. Second, an end-to-end spatial-spectral FFPNet is presented for classifying hyperspectral images. Experiments conducted on ISPRS Vaihingen and ISPRS Potsdam high-resolution datasets demonstrate the competitive segmentation accuracy achieved by the proposed heavy-weight spatial FFPNet. Furthermore, experiments on the Indian Pines and the University of Pavia hyperspectral datasets indicate that the proposed spatial-spectral FFPNet outperforms the current state-of-the-art methods in hyperspectral image classification.

Data processing of Zhuhai-1 hyperspectral satellite

The Zhuhai-1 hyperspectral satellite (The Qust No.1), which was launched on 26 April 2018 is the learning and research crystallization of Qingdao university of science and technology in cooperation with Obit aerospace technology company. The Qust No.1 satellite is equipped with a high-resolution hyperspectral camera, achieving global remote sensing coverage and providing high-quality hyperspectral data for relevant scientific and commercial remote sensing applications. Based on the Qust No.1 imagery for Jiaozhou bay, the radiation, atmospheric, orthographical corrections together with the image enhancement and spectral information extraction are analysed and discussed in detail in this paper. The results indicate that there are high imaging quality and excellent information collection ability for the Zhuhai-1 satellite, which has good application prospect in many aspects such as vegetation monitoring, precision agriculture, etc.

A COMPARATIVE ANALYSIS OF SPECTRAL INFORMATION EXTRACTION ALGORITHMS FOR TARGET DETECTION OF HYDROTHERMAL ALTERATION ZONES USING ASTER SATELLITE IMAGE DATA

Abstract. The focus of this paper is to evaluate the performance of the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data for target detection of hydrothermal alteration zones associated with geothermal (GT) springs as proxy for narrowing areas of interest. The study employed the Per-pixel Spectral Angle Mapper (SAM) and the Sub-pixel Linear Spectral Unmixing (LSU) algorithms for spectral information extraction by using the ASTER satellite image data. In both cases, image endmember spectra specifically for kaolinite, alunite, and illite and calcite zones were selected and extracted by using the Analytical Imaging and Geophysics (AIG)-developed processing methods. The results of the analysis show that both SAM and LSU discriminated targets of interest better when employing image spectra and poorly when using library spectra. However, the Per-pixel SAM is unsuitable for target detection and more suited where the objective of the investigation is to classify whole scene and not particular targets as in this case. The LSU was found to be effective for discriminating alterations associated with the thermal springs especially where image endmember spectra are employed for analysis, thus recommended for prefeasibility mapping of GT related resources.