In this paper, we propose an approach based on an Alternating Direction Method of Multipliers (ADMM) to unmix hyperspectral data using a recently proposed linear mixing model in which the spectral variability phenomenon is spectrally modeled in a multiplicative manner. This model allows for pixel-wise variation of the endmembers, resulting in different versions of the reference component spectra being considered in each pixel of the image. The proposed ADMM-based unmixing algorithm involves new iterative update rules. The investigation also evaluates the performance of the designed algorithm against some literature ones previously proposed. To this end, experiments using synthetic hyperspectral data are carried out. Overall, the obtained results prove that the proposed algorithm is very attractive for hyperspectral unmixing taking the spectral variability phenomenon into account.

Marine mucilage outbreaks not only pose a threat to the marine ecosystems, but also are a detriment to economy and public-health. The recent marine mucilage outbreak of Spring 2021 in the Sea of Marmara, Türkiye, was one of most serious recorded mucilage outbreaks, lasting over three months and covering more than 1000 square kilometers. Recently, linear spectral unmixing based environmental monitoring of marine mucilage from hyperspectral data have been shown to provide easy to interpret analysis of this complex phenomenon, in terms of endmember signatures and fractional abundances. This paper carries the work forward and proposes nonlinear unmixing for the environmental monitoring of marine mucilage. Hyperspectral data acquired by the PRISMA mission are used in this investigation.

Disasters in marine ecosystems, such as the outbreak of mucilage in the inland Sea of Marmara in the spring of 2021, raise serious environmental, economic and public health concerns. Recently, methods based on fully unsupervised unmixing and dealing with spectral variability have made it possible to analyze marine mucilage, quantify its abundance and thus to map this harmful phenomenon. This work proposes to use an informed (or semi-supervised) unmixing technique, which is based on nonnegative matrix factorization and dealing with spectral variability, using a field-measured spectrum of high-density (or accumulated) mucilage, in order to detect and map, in particular, this marine material. The used technique is evaluated on real hyperspectral PRISMA data, and compared with other unmixing-based techniques.

In these investigations, a nonlinear spectral unmixing-based approach is considered to estimate, more accurately, some physical parameters of a flare, exploiting Visible Infrared Imaging Radiometer Suite (VIIRS) Night Time Lights (NTL) remote sensing data. These calculated parameters are then used to estimate flared gas volumes, through an intercepting zero polynomial regression model that exploits in-situ measurements. Experiments, using VIIRS NTL data, covering the flare, named FIT-M8-101A-1U and located in the Berkine basin (Hassi Messaoud) in Algeria, are performed. Then, the estimated flared gas volumes are compared with in-situ measurements.

In these investigations, a new informed linear mixing model addressing spectral variability with an associated informed penalized hyperspectral unmixing algorithm is first proposed. This algorithm, which optimizes a new cost function with original iterative and multiplicative update rules, is based on nonnegative matrix factorization. Then, this algorithm is used for detecting and mapping several mineral deposits in the Algerian Central Hoggar. This method unmixes the considered PRISMA hyperspectral remote sensing data by exploiting known spectra of some minerals of interest. Obtained abundance fraction maps are then used to establish a classification map of the investigated area, with the considered mineral deposit classes, at a finer spatial resolution.

Hyperspectral data, acquired by air/spaceborne sensors, are generally exposed to intra-class variability, making their unmixing process more complicated, in terms of precise estimations of endmember spectra and their corresponding abundance fractions, by means of the usual linear mixing model that ignores this concern. Accordingly, further advanced linear mixing models, which address this issue, were proposed recently. Several of them consider this intra-class variability in the spectral part of variables, whereas many ones consider the same phenomenon in the spatial part of variables. In this investigation, a novel linear mixing model is proposed to deal with this phenomenon. This model considers this concern both in the spectral and spatial parts of variables. Moreover, an associated penalized hyperspectral unmixing algorithm, based on multiplicative nonnegative matrix factorization, is designed for the proposed model. This algorithm proves to be practical as obviously reported by conducted experiments and obtained results.

Wildfires are increasing in frequency due to anthropogenic climate change. Live Fuel Moisture Content (LFMC) is a key parameter for wildfire behavior prediction. However, it is very difficult to measure via Earth observation data. This study suggests the use of Soil Moisture Content (SMC) as a substitute for LFMC for such a purpose. The chosen study cases are wildfires that took place in the Sidi Douma forest, Saida, Algeria on August 2-3, 2017. A pre-fire Landsat-8 product is used to generate SMC-related models and indices, namely Temperature Vegetation Dryness Index, Perpendicular Drought Index, Optical Trapezoidal Model, and the Modified Normalized Difference Water Index. The outputs of those models are input to a Gaussian Naive Bayes classifier, which produced 0.70 accuracy, 0.70 precision, 0.69 F1 score, and 0.69 AUC score. The classification is subsequently used to produce a wildfire risk assessment map that is validated and analyzed via the differences in Normalized Burn Ratio between the pre-fire and post-fire Landsat-8 products.

In this paper, a novel approach, based on a multistage informed spectral unmixing technique, for detecting and mapping several mineral deposits in the Gara-Djebilet region (Southwestern Algeria), is presented. The considered technique, which is related to linear spectral unmixing methods, uses an iterative informed multiplicative nonnegative matrix factorization algorithm. This technique unmixes the used PRISMA hyperspectral remote sensing data by exploiting known spectra of the considered minerals. More precisely, the originality of this work consists in applying iteratively, in two stages, the considered informed unmixing algorithm. During the first stage, abundant but irrelevant minerals, with known spectra and present in the considered region, are detected, and are then removed from the original hyperspectral data, which thus lead to the creation of new hyperspectral data to which the considered unmixing technique is applied, during the second stage, in order to detect and map other relevant minerals, with known spectra, and possibly together with unknown materials. Experiments are carried out with the considered real hyperspectral data, which cover the studied area, to assess the potential of the proposed approach. The obtained results are mainly confirmed and validated by prior knowledge of the investigated area.

During oil extraction process, natural gases escape from wells, and the procedure for recovering these gases requires heavy investments from oil and gas companies. That is why, most often, they prefer to burn them with flares. This practice, which is very common by oil and gas companies in oil-producing countries, is highly emitting greenhouse gases. Under increasing pressure from the World Bank and environmental defenders, several producer countries are committed to reducing gas flaring. To this end, researchers in the oil and gas industry, academia and governments are working to develop approaches for determining ways to measure gas flaring and its emissions. Among the most widely used approaches, for local and global monitoring of gas flares, are those that exploit remote sensing data, particularly Night time Light (NtL) ones. Indeed, it is possible to extract, from such data, some physical parameters of flames produced by gas flares, and these parameters can be used to estimate annual volumes of flared gas. In this investigation, three spectral analysis-based approaches are tested to estimate flare physical parameters from Visible Infrared Imaging Radiometer Suite (VIIRS) NtL data. Linear and nonlinear spectral unmixing methods applied on NtL VIIRS data, are anticipated to improve, by using a pure spectrum of flames, results provided by the classical one that considers the modeling of the Planck law curve applied on the manipulated observed mixed data. Experiments, based on realistic synthetic VIIRS NtL data, are conducted and obtained results confirm the expected improvements.

Remote sensing hyperspectral images are usually subject to the intra-class variability phenomenon that complicates the precise estimation of endmember spectra and their abundance fractions when using the spectral unmixing process with the typical Linear Mixing Model (LMM), which ignores this concern. Thus, other refined LMMs, which deal with this issue, were developed. Some of them consider this spectral variability on the spectral part of variables, while other ones consider the same phenomenon on the spatial part of variables. In this work, a recent modified Augmented LMM (ALMM) is used to deal with the intra-class variability, considered on the spatial part of variables, by using smaller matrices that also obey the nonnegativity constraint. Furthermore, a projected gradient-based algorithm, based on Nonnegative Matrix Factorization (NMF), is proposed for the used modified ALMM. This Gradient-NMF-based technique proves to be useful as clearly reported by conducted experiments.

A novel alteration of the Water Cloud Model (WCM) and its inversion is proposed in this research work to improve the accuracy of Soil Moisture Content (SMC) mapping. This paper suggests using the Optical Trapezoid Model as the sole vegetation descriptor in the WCM, as well as the use of a specific configuration of parameters derived from a function of radar frequency, polarization, dielectric particle size, and orientation distribution. The proposed inversion scheme is applied on Sentinel-1 data along with the Landsat-8 images component. The proposed approach achieves higher SMC estimation accuracies compared to those produced by tested methods. Indeed, the designed approach achieved improvements in terms of accuracy as demonstrated by a decrease of Root Mean Square Error values in the order of 0.3% and 0.55% in the Blackwell farms and Sidi Rached study areas respectively.

Hypersharpening consists in generating an unobservable high-spatial-resolution hyperspectral image by fusing an observed low-spatial-resolution hyperspectral image with an observed high-spatial-resolution panchromatic or multispectral one. The obtained image preserves the high spectral resolution of the first image and the high spatial resolution of the second one. Unlike standard hypersharpening methods that do not consider the spectral variability phenomenon, in this letter, a new approach, which addresses this phenomenon, is proposed for fusing hyperspectral and multispectral remote sensing images. This approach, linked to linear spectral unmixing methods, is based on an extension of nonnegative matrix factorization (NMF), namely the inertia-constrained pixel-by-pixel NMF (IP-NMF) algorithm. The developed fusion algorithm, called hyperspectral and multispectral data fusion based on IP-NMF (HMF-IPNMF), is applied to synthetic and real data sets. Experimental results clearly show that the developed fusion method yields sharpened hyperspectral images with higher spectral and spatial fidelities when compared to those provided by tested state-of-the-art methods that do not take spectral variability into account.

In these investigations, an informed unmixing-based approach is considered for detecting and mapping several mineral deposits in the Algerian Central Hoggar. The considered technique, which is related to linear spectral unmixing methods, uses an informed multiplicative nonnegative matrix factorization algorithm. This technique unmixes the used hyperspectral remote sensing data by exploiting known spectra of the considered minerals. Experiments are carried out, to assess the potential of the used technique, on real hyperspectral PRecursore IperSpettrale della Missione Applicativa (PRISMA) data, which cover the considered study area. Obtained maps are analyzed by using a geological map of the investigated region.

Spectral unmixing methods aim at estimating a collection of pure material spectra and their associated proportions in each pixel of the image. Such methods usually suppose that each pure material is represented by a unique spectrum in all image pixels. However, in many cases this assumption is no more valid for materials that exhibit spectral variability due to varying illumination and atmospheric conditions or material composition. Recently, a novel linear mixing model that handles the spectral variability phenomenon, modeled in a multiplicative form, was proposed with an associated unmixing method. In the present paper, two gradient-based approaches, which use the above mixing model and that are based on pixel-by-pixel nonnegative matrix factorization, are proposed. The first approach uses the projected gradient descent algorithm, whereas the second one employs a Newton update. The proposed algorithms minimize a cost function that takes into account the considered linear mixing model with the spectral variability phenomenon. Experiments, based on realistic synthetic data, are conducted to evaluate the performance of the proposed algorithms. The obtained results are also compared to those of methods from the literature. These test results show that the proposed approaches prove to be very attractive for unmixing hyperspectral remote sensing data with spectral variability.

Remote sensing hyperspectral sensors are often limited in their spatial resolutions, which leads to mixed pixels. The linear spectral unmixing process is frequently used to extract endmember spectra and their abundance fractions. The standard linear mixing model considers that each endmember is represented by the same spectral signature in the entire image. However, such a basic hypothesis is not relevant in most practical situations since the spectral signature of an endmember can spatially vary. This intra-class variability phenomenon can be considered by introducing the concept of classes of endmembers. Recently, a structured additively-tuned linear mixing model, with its constraints, was proposed, with an associated unmixing method, to address this phenomenon. That method, based on Nonnegative Matrix Factorization (NMF), optimizes a cost function with iterative and multiplicative update rules supplemented by additional constraints that control the spectral variability. In the present work, two penalization terms that more efficiently manage the spectral variability are added to the considered cost function, for the same structured mixing model, and new NMF-based iterative and multiplicative update rules are deduced for achieving the unmixing process taking the considered phenomenon into account. The proposed algorithm proves to be very attractive as clearly reported by conducted experiments based on synthetic data.

Recently, deep learning methods dominate the proposed solutions for image super-resolution due to their powerful properties. However, for remote sensing benchmarks, it is very expensive to obtain high spatial resolution images. Most of the super-resolution methods use down-sampling techniques to simulate low and high spatial resolution pairs and construct the training samples. As an alternative, the paper introduces a novel public remote sensing dataset (Alsat-2B) of low and high spatial resolution images (10m and 2.5m respectively) where the high-resolution images are obtained through pansharpening. Besides, the performance of some state-of-the-art methods is assessed based on common criteria. The obtained results reveal that the proposed scheme is promising and highlight the challenges in the dataset which show the need for advanced methods to grasp the relationship between the low and high-resolution patches.

The advent of new generation satellites has revolutionized the remote sensing science. Actually, the ability to store satellite data continuously for future use has enabled precise geographical and temporal monitoring of the Earth's surface evolution. In this work, the remote sensing field for change detection, in bi-temporal optical satellite imagery, is investigated. The proposed approach consists in adapting a Siamese fully convolutional network, using an end-to-end training and employing « long skip-connections », to exploit the results of the Euclidean Distance and the Image Difference for the pixel classification. The proposed model training refers to a database created in these investigations from available bi-temporal multisource satellite images and their respective ground truths. The designed model is evaluated by using different types of images and several experiments are carried out to validate the proposed approach addressing the change detection task in remote sensing imagery.

In this work, a hypersharpening approach, creating fused hyperspectral remote sensing images with high spatial and spectral resolutions, is introduced. This approach, linked to linear spectral unmixing (LSU) methods and based on a multiplicative nonnegative matrix factorization (NMF) technique, extends the Joint-Criterion NMF (JCNMF) algorithm, by addressing the spectral variability phenomenon. This method is designed for combining low spatial resolution hyperspectral and high spatial resolution multispectral data. It optimizes the considered criterion that deals with the spectral variability phenomenon by using a specific structure of involved matrices. The introduced algorithm, which uses multiplicative and iterative update rules, is applied to realistic synthetic data, and its effectiveness, in the spatial and spectral domains, is evaluated by considering commonly used assessment protocol and performance criteria. The obtained results prove that the introduced algorithm yields fused hyperspectral data with good spectral and spatial fidelities. These results also illustrate that the proposed algorithm significantly outperforms two tested literature ones that do not take the spectral variability phenomenon into account.

This paper introduces a new multilevel fusion approach for Soil Moisture Content (SMC) estimation. This approach includes the following indices and models; the Normalized Difference Water Index (NDWI), the Modified Normalized Difference Water Index (MNDWI), the Perpendicular Drought Index (PDI), and the Temperature Vegetation Dryness Index (TVDI), extracted from Landsat-8 data, and the inversion of the Integral Equation Model (IEM) from Sentinel-1 data with the support of surface roughness measurements. The proposed fusion occurs on the feature and decision levels. At the feature level, features extracted from each of the above indices/models are combined to obtain three feature vectors, those vectors are later used in the decision level via the Fully Constrained Least Squares (FCLS) technique. The areas of interest of this study are; Blackwell Farms, Guildford, United Kingdom, and Sidi Rached, Tipasa, Algeria. The proposed system yielded lower Root Mean Square Errors (RMSE) (1.09% on average) than that of IEM inversion.

Land cover classification is one of the most important research fields in the remote sensing community. With the rapid growth of remote sensing sensors, it has received much attention in the last years, and rich temporal, spectral and spatial information were generated. Existing land cover classification approaches can be categorized into single time and multi-temporal observations processing techniques. Due to changes of reflective features over time, multi-temporal land cover classification approaches may be hard to be implemented. In these investigations, a new hybrid neural networks model is proposed to tackle such issues, and in particular, for easily multi-temporal vegetation mapping and monitoring. The proposed model combines convolutional and recurrent neural networks to capture local features and long-term dependencies of multi-temporal remote sensing images. This combination is expected to extract useful features for their automatically classification. The proposed model is applied to multi-temporal publicly available Sentinel-2A datasets with vegetation as the main theme, and obtained experimental results are evaluated with established criteria.

Convolutional Neural Network (CNN) has boosted the performance of Very High Resolution (VHR) remote sensing data classification. Moreover, the continuous development of CNN techniques for image scenes description has entered a new challenge. The deep neural network models require a huge number of training samples, which is the main limitation of processing remote sensing data. To overcome this issue, a new method, based on the Capsule neural network for VHR image scenes recognition is proposed in this work. Experiments on the public Aerial Image Dataset (AID) benchmark, containing different areal categories with sub-meter spatial resolution are conducted. The obtained results demonstrate the effectiveness of the proposed method, as compared with the classical CNN model.

In a very recent paper, we introduced (i) a specific hyper-spectral mixing model for the sea bottom, based on a detailed physical analysis which includes the adjacency effect, and (ii) an associated unmixing method, which is not blind in the sense that it requires a prior estimation of various parameters of that mixing model. We here proceed much further, by first analytically showing that this model can be seen as a specific member of the general class of mixing models involving spectral variability. Therefore, we then process such data with the IP-NMF and UP-NMF blind unmixing methods that we recently proposed in other works to handle spectral variability. Such a variability especially occurs when sea depth significantly varies over the considered scene, and we show that IP-NMF and UP-NMF then yield significantly better pure spectra estimation than a classical method from the literature which was not designed to handle such a variability.

In remote sensing, supervised multiclass classifiers show a very promising performance in terms of classification accuracy. However, they require that all classes, in the study area, are labeled. In many applications, users may only be interested in specific land classes. When considering only one class, this referred to as One-Class classification (OC) problem. In this paper, we investigated the possibility of using Convolutional Neural Networks (CNN) within the Positive and Unlabeled Learning (PUL) framework for estimating the urban tree canopy coverage from very high spatial resolution aerial imagery. We also compared the proposed approach to the Binary CNN classification and to ensemble classifications based on various color-texture based features. The obtained classification accuracies show that PUL strategies provide competitive extraction results, especially the proposed CNN based one, due to the fact that PUL is a positive-unlabeled method in which large amounts of available unlabeled samples is incorporated into the training phase, allowing the classifier to model effectively the tree class.

Several studies have demonstrated the efficiency of using spatial information in representation of hyperspectral (HS) images. Texture features are known as one of the most important categories of spatial information in various applications of image processing. This study evaluates the capability of recently proposed descriptors named multiband compact texture unit. This method extracts texture by characterizing simultaneously spatial relationship in the same band and across the different bands. The proposed evaluation is performed in the context of patch-based classification paradigm using two HS datasets. For that, objects were generated through superpixel segmentation. The classification in the object-feature space is performed using a random forest algorithm. The proposed approach is compared to various other color-texture analysis methods, including: Integrative gray-level co-occurrence matrix, Opponent Gabor features and Opponent local binary patterns. Experimental results show that multiband compact texture unit method produces the best results.

This paper presents a fusion method generating unobservable sharpened hyperspectral remote sensing data with high spatial and spectral resolutions. This method, related to linear spectral unmixing (LSU) techniques, and based on nonnegative matrix factorization (NMF), introduces Joint-Variables NMF (JVNMF) for fusing observable low spatial resolution hyperspectral and high spatial resolution multispectral data. It optimizes a joint-variables criterion that exploits spatial and spectral degradation models between the two considered images, and therefore considers a reduced number of unknown variables. This approach, called Grd-JVNMF, is a gradient-based method and uses iterative update rules. The proposed method is applied to realistic synthetic and semi-real data, and its effectiveness, in spatial and spectral domains, is evaluated with established performance criteria. Experimental results show that the proposed Grd-JVNMF method yields multi-sharpened hyperspectral data with good spectral and spatial fidelities. These tests also show that the proposed method outperforms tested literature ones.

Change detection in land and urban environments has been an important task in remote sensing field. Deep learning has recently received an increasing attention from researchers and has been successfully applied for many domains. In remote sensing, it is very difficult to construct a large-scale well-annotated dataset due to the expense of data acquisition and the costly annotation, which limits its development. In this work, we introduce deep transfer learning as a way of overcoming the application of deep learning techniques for optical remote sensing change detection. Through several experiments, we investigate various uses of pre-trained Convolutional Neural Networks (CNNs) models. Our experiments on bi-temporal dataset show that VGG16 and ResNet networks consistently yield the best performances across considered strategies. It also appears that fine-tuning pre-trained CNN models is the best performing strategies.

This paper presents a change detection approach for optical remote sensing images based on deep learning. Due to the excellent performance of Convolutional Neural Network (CNN) in feature learning, two models are explored in this work, where the proposed algorithms show how to learn, directly from images, a similarity function to compare bitemporal images. Two-stream network named as Siamese network is presented. First, bi-temporal images are fed directly into the proposed network. Second, a combination of the aforementioned model with a perceptual loss is presented, this combination focus on high representational features that are extracted from a pre-trained network on large dataset of natural images (ImageNet) rather than opting directly on remote sensing images. Experimental results on real dataset show the effectiveness and the superiority of the proposed framework.

The acquired images of the first Algerian high spatial resolution satellite Alsat-2 (A and B) images by the pushbroom scanner present a non-rigid misalignment among their different bands. The elimination of this registration error is a critical preprocessing step to assure the best use of this data for further applications. In this paper, a new approach for Alsat-2 band to band registration is proposed. This approach, called dense vector matching, leads to subpixel accuracies of the considered images. The proposed algorithm is based on a non-centered cross correlation technique. Indeed, it uses the following idea: when correlating each line-vector and each column-vector of the reference band with the neighboring vectors in the target band, subpixel misalignments are estimated by getting the maximum correlation after performing a cubic polynomial fit. Therefore, when applying the proposed algorithm to all bands, for each given pixel in the reference band, the new position of the corresponding pixel in the target bands is computed by subtracting the line and column registration errors from the reference position. Finally, the pixel-values of corrected target band are calculated by using the bilinear interpolation. Experiments are conducted to evaluate the proposed approach, and subpixel registrations are obtained on the corrected images, leading to an improvement of the multispectral images quality.

Date palm trees are important economic crops in many countries and counting their numbers in a plantation area is crucial information for predicting the yield of date fruits, determination of insurance and financial aids, etc. In this abstract, a supervised tree counting framework is proposed using Convolutional Neural Network (CNN). The proposed approach casts the counting process into a regression problem, instead of following the classification or detection framework. To further decrease the prediction error of counting, we fine-tuned a pretrained CNN architecture into regression model. As the final output, not only the tree count is estimated for an image, but also its spatial density map is provided. Trained with small image patches cropped from airborne dataset, the proposed method is compared to manual counting and obtains good performance.

This abstract proposes a method to enhance the classification of high spatial remotely sensed imagery by using Multiband Compact Texture Unit (MBCTU) descriptor and pre-trained convolutional neural networks (CNN) feature extractor. MBCTU was used in order to take into account intra- and interband spatial interactions by characterizing texture using relative pixel values in a multispectral neighborhood instead of a monoband neighborhood. The derived new encoded images are fed to a deep feature extractor (fine-tuned CNN). Finally, the obtained deep features are classified using k nearest neighbor'S (KNN) algorithm to produce the classification map. The proposed approach is applied to the classification of hyperspectral and multispectral datasets. Results indicate that the proposed approach can achieve accurate classification results compared to other approaches using the full spectral dataset.

Hyperspectral remote sensing data offer unique opportunities for the characterization of land surface in urban areas. However, no hyperspectral- unmixing based studies have been conducted to automatically detect photovoltaic panels, which represent one of the important components of energy systems in such areas. In this paper, a hyperspectral-unmixing based method is proposed to detect photovoltaic panels and to estimate their areas. This approach is based on an original multiplicative nonnegative matrix factorization (NMF) algorithm with some known photovoltaic panel spectra. The proposed method can be considered as a partial/informed NMF approach. Experiments are conducted on realistic synthetic and real data to evaluate the performance of the proposed approach. In both cases, obtained results show that the proposed method yields much better overall performance than a method from the literature.

Hyperspectral remote sensing data are widely used in various applications like classification and target detection. However, recently the influence of shadow has become increasingly greater due to the higher spatial resolution of such data. Shaded areas usually have lower intensity and fuzzy boundary, which make the images hard to interpret automatically. To overcome this issue, shadow correction/compensation of hyperspectral remote sensing data is one of the most used techniques. This process includes in general, the detection and de-shadowing steps. In this work, which focuses only on the de-shadowing step, a new hyperspectral unmixing-based shadow correction/compensation is presented. Experiments are conducted on a real hyperspectral image to evaluate the performance of the proposed approach. Experiments show that the proposed method yields satisfactory de-shadowing results and provides better overall performance compared to another unmixing-based method from the literature.

A strong intern dynamic characterizes towns, a very high spatial heterogeneity of their elements, their 3D geometric shapes (horizontal and vertical) inducing shadows, and their large variety of materials. These characteristics make the collection of information of land surface properties and urban descriptors more delicate. Due to the enhancement of spatial to deepen the observation of urban areas. Nevertheless, such a type of sensors would not contribute to the characterization of the urban land surface properties (chemical composition of materials, species of vegetation, quality of soils, etc.). They and show great potentials might consider Hyperspectral imagery capacities as providing useful products but it becomes mandatory to define which type of information these different sensors can deliver. The ANR HYEP project has the purpose to demonstrate the benefit of a second generation of hyperspectral space borne mission characterized by a high spatial resolution (8m GSD) and a high temporal revisit. After a detailed description of the motivation of such a proposal, applications are given focused on urban vegetation, sealed and impervious areas, solar panel area estimation.

In this paper, a new approach is proposed for linear endmember spectra extraction from a highly mixed hyperspectral image combined with high spatial resolution multispectral data containing pure pixels. This new approach, which is applied to unmix the considered hyperspectral image, is based on a modified version of nonnegative matrix factorization (NMF) coupled with nonnegative least squares (NLS). The multispectral data are used to initialize the hyperspectral NMF algorithm and to constrain it during matrix updates. Experiments based on synthetic and real data are performed to evaluate the performance of the proposed approach and to compare it with five methods from the literature only applied to the hyperspectral data. The obtained performance shows the superiority of the proposed approach as compared with all other methods. Also, the impact, on the proposed method, of spectral variability between hyperspectral and multispectral data is evaluated, and the obtained results show the robustness of the proposed method to this variability.

Hypersharpening aims at combining an observable low-spatial resolution hyperspectral image with a high-spatial resolution remote sensing image, in particular a multispectral one, to generate an unobservable image with the high spectral resolution of the former and the high spatial resolution of the latter. In this paper, two such new fusion methods are proposed. These methods, related to linear spectral unmixing techniques, and based on nonnegative matrix factorization (NMF), optimize a new joint criterion and extend the recently proposed joint NMF (JNMF) method. The first approach, called gradient-based joint-criterion NMF (Grd-JCNMF), is a gradient-based method. The second one, called multiplicative JCNMF (Mult-JCNMF), uses new designed multiplicative update rules. These two JCNMF approaches are applied to synthetic and semireal data, and their effectiveness, in spatial and spectral domains, is evaluated with commonly used performance criteria. Experimental results show that the proposed JCNMF methods yield sharpened hyperspectral data with good spectral and spatial fidelities. The obtained results are compared with the performance of two NMF-based methods and one approach based on a sparse representation. These results show that the proposed methods significantly outperform the well-known coupled NMF sharpening method for most performance figures. Also, the proposed Mult-JCNMF method provides the results that are similar to those obtained by JNMF, with a lower computational cost. Compared with the tested sparse-representation-based approach, the proposed methods give better results. Moreover, the proposed Grd-JCNMF method considerably surpasses all other tested methods.

In this paper, a new projected-gradient method for bilinear matrix factorization with nonnegativity constraints is proposed for extracting hyperspectral endmember spectra. The proposed method is designed for a bilinear mixing model faced in urban hyperspectral remote sensing images. Experiments based on realistic synthetic data, generated according to the considered bilinear mixing model, are conducted to evaluate the performance of the proposed method and of approaches from the literature. Experimental results show that the proposed method yields much better overall performance than the used literature approaches.

In this paper, we propose a new multi-sharpening approach for improving the spatial resolution of hyperspectral data. This approach, based on the linear-quadratic spectral unmixing concept, uses a linear-quadratic nonnegative matrix factorization multiplicative algorithm. Our method first consists in unmixing the low spatial resolution hyperspectral data and high spatial resolution multispectral data. The obtained high resolution spectral and spatial parts of information are then recombined, according to the linear-quadratic mixing model, in order to obtain unobservable multi-sharpened high spatial resolution hyperspectral data. Experiments, based on realistic synthetic and real data, are carried out to evaluate the performance of the proposed approach and of linear nonnegative matrix factorization-based approaches from the literature. We show that our proposed approach significantly outperforms the used literature methods.

Remote sensing hyperspectral sensors typically collect data in contiguous narrow bands (up to several hundred bands) in the electromagnetic spectrum. In hyperspectral imagery, pixels are often linear mixtures of pure materials (endmembers) contained in the observed scene. In this paper, we propose a new unsupervised spatial method (called 2D-VM) for endmember spectra extraction from data to be collected by future higher spatial resolution hyperspectral sensors, which will allow the existence of some pure pixels. This method is related to the Blind Mixture Identification (BMI) problem, and is based on Sparse Component Analysis (SCA). It extracts the endmember spectra by using a spatial variance-based SCA method, which detects a few pure-pixel zones. Experiments based on synthetic but realistic data are performed to compare the performance of the proposed approach and of methods from the literature. We show that our approach outperforms all other methods.