Hyperspectral sensors provide high spectral resolution, enabling accurate material discrimination and effective target detection. However, their practical use is constrained by limited spatial resolution and high acquisition costs. This paper proposes a novel framework to enhance small-target detection in multispectral imagery by leveraging deep learning-based spectral reconstruction to generate high-resolution hyperspectral representations from multispectral inputs. Two state-of-the-art reconstruction networks, MST++ and MIRNet, are trained using paired multispectral–hyperspectral samples derived from AVIRIS-NG data through proper spectral response functions. To improve discriminative capability for the target of interest, a rapid, target-specific fine-tuning stage is introduced, allowing the models to adapt to spectral signatures that are poorly represented or absent in the original training data. Target detection is performed using a spectral signature-based detector applied to the reconstructed hyperspectral data. The proposed framework is evaluated in a real-world scenario involving known field-deployed targets and hyperspectral imagery acquired from an unmanned aerial vehicle. Experimental results demonstrate that the proposed approach significantly outperforms baseline detection applied directly to multispectral data. These findings underscore the effectiveness of spectral reconstruction for downstream tasks such as target detection, particularly in scenarios where hyperspectral data are expensive or unavailable.

Hyperspectral imaging offers high spectral resolution for accurate material discrimination and target detection, yet it is hindered by low spatial resolution and high operational costs. In this work, we present a novel framework that leverages deep learning-based spectral reconstruction to convert multispectral imagery into hyperspectral data with enhanced spectral and spatial resolution, specifically tailored for target detection. Our approach considers a spectral reconstruction network named MST++ that has been initially trained on multispectral-hyperspectral image pairs generated from AVIRISNG by means of proper Spectral Response Functions. A targeted fine-tuning procedure is then applied to optimize the recovery of discriminative spectral features for small, camouflaged targets. For the detection stage, reference-based matched filters exploit the prior spectral signatures of the targets. Validation on real multispectral data acquired by a UAV in field conditions demonstrates that our method significantly enhances the detection of small targets, achieving performance metrics intermediate between conventional multispectral and true hyperspectral imagery. These results underscore the potential of spectral reconstruction techniques as a cost-effective solution to augment target detection capabilities in scenarios where high-end hyperspectral sensors are not available.

This paper provides an overview of the main activities and results of HYPERHEALTH project (funded by the Italian Space Agency). Specific focus of this paper is hyperspectral PRISMA data exploitation, mostly as regards PRISMA-based atmospheric constituent estimation and allergenic vegetation monitoring.

Moving target detection (MTD) is a crucial task in computer vision applications. In this paper, we investigate the problem of detecting moving targets in infrared (IR) surveillance video sequences captured using a steady camera in a maritime setting. For this purpose, we employ robust principal component analysis (RPCA), which is an improvement of principal component analysis (PCA) that separates an input matrix into the following two matrices: a low-rank matrix that is representative, in our case study, of the slowly changing background, and a sparse matrix that is representative of the foreground. RPCA is usually implemented in a non-causal batch form. To pursue a real-time application, we tested an online implementation, which, unfortunately, was affected by the presence of the target in the scene during the initialization phase. Therefore, we improved the robustness by implementing a saliency-based strategy. The advantages offered by the resulting technique, which we called "saliency-aided online moving window RPCA" (S-OMW-RPCA) are the following: RPCA is implemented online; along with the temporal features exploited by RPCA, the spatial features are also taken into consideration by using a saliency filter; the results are robust against the condition of the scene during the initialization. Finally, we compare the performance of the proposed technique in terms of precision, recall, and execution time with that of an online RPCA, thus, showing the effectiveness of the saliency-based approach.

HYPERHEALTH project is co-funded by Italian Space Agency (ASI) in the framework of the "PRISMA Scienza" program. The program supports R&D projects proposed by experts in hyperspectral remote sensing sector from national public research institutions to industries, also in the framework of international partnerships. The aim is designing, developing and testing innovative methods, techniques and algorithms for exploitation of hyperspectral data, with reliable perspectives as to engineering and pre-operational development, thus contributing to the improvement of socio-economic benefits of the end-user community. This paper outlines HYPERHEALTH main goals and activities.

The rapid growth of hyperspectral satellite missions and the subsequent availability of hyperspectral images have encouraged the remote sensing community to investigate their potential in estimating the concentration of gases, such as methane (CH $_{ \boldsymbol {4}}$ ) and carbon dioxide (CO $_{ \boldsymbol {2}}$ ), which are related to the greenhouse effect. Though satellite hyperspectral sensors are not specifically designed for this purpose, they are expected to complement more specific satellite missions, such as NASA’s Orbiting Carbon Observatory -2 and -3 (OCO-2 and OCO-3), both in terms of enriched temporal sampling and improved spatial resolution. In this work, we present a new method to estimate the column-averaged dry-air mole fraction of CO $_{ \boldsymbol {2}}$ from hyperspectral data on a per-pixel basis. The method, which is here tailored to PRISMA images, leverages the spectral radiance samples collected in the short-wave InfraRed (SWIR) spectral region around the CO $_{ \boldsymbol {2}}$ absorption band at 2000 nm. By assuming a linear model to describe the dependence of the observed radiance on the CO $_{ \boldsymbol {2}}$ concentration, the estimation problem is reduced to matched filtering and can be effectively implemented in compliance with the low computational burden required to perform a pixel-by-pixel analysis. The performance of the presented method is investigated by means of a rigorous, physically based simulator that accurately reproduces the at-sensor radiance allowing one to check the validity of the assumptions and to assess the algorithm accuracy. The results show that the presented algorithm outperforms a benchmark continuum interpolated band ratio (CIBR)-based approach, which has been proposed in the literature to get fast per-pixel estimates of CO $_{ \boldsymbol {2}}$ concentration.

In the ambit of the computer vision, the moving object detection is an extremely important topic which has drawn the interest of the scientific community. Recently, an emerging dimensionality reduction technique, called Dynamic Mode Decomposition (DMD), has been exploited to make an estimation of the background. The DMD is a pure data-driven technique which provides information about the spatial and temporal evolution of the input video. The main idea behind the usage of the DMD is the possibility of isolating the modes that addresses the background in order to obtain the signal associated with the target by subtraction. In the practice, the DMD produces a unimodal representation of the background, which provides good results under the assumptions that the background is quasi-static, the foreground objects are small and their motion is fast. The objective of this study is to verify the applicability of the DMD in the case of InfraRed videos of maritime scenarios with extended naval targets. In this context, the foreground is neither small, nor fast. To face that problem, we propose a spatial-multiscale approach which slightly improves the detection accuracy of the DMD-based detector. The proposed approach has been tested on a real dataset collected under real operational conditions, during an experimental activity lead by the NATO STO-CMRE in February 2022 in Portovenere (Italy). The performance has been evaluated in terms of precision and recall and has been compared to other state-of-the-art moving target detection algorithms.

PRISMA is a hyperspectral pushbroom sensor, launched by the Italian Space Agency in 2019. PRISMA collects the reflected Earth signal from VNIR to the SWIR with 230 spectral bands with a variable FWHM according to the prism dispersion element. This work intends to develop a procedure suitable to monitor the consistency of photon and thermal noise components across a times series of L1 radiance images collected on different Mediterranean scenarios (i.e. rural and coastal). To improve the retrieval of the useful signal and the random noise on PRISMA images the spatial variability of the scenes has been considered in the new version of the HYperspectral Noise Parameters Estimation (HYNPE) algorithm. The procedure, tested on two PRISMA time series, has assessed quite stable and coherent values for the retrieved noise coefficients, not significantly affected by seasonal radiance variations and scene characteristics

The unique spectral content provided by PRISMA's hyperspectral sensor gives the possibility to study the Earth's surface and environment from space in unprecedented detail. In this respect, our work presents the results of an Italian Space Agency-funded project aiming to develop eight prototypes for providing Value Added products based on such data. Prototypes focus on vegetation, urban areas, water quality, material detection, and natural hazards, combining multiple state-of-the-art techniques based on Machine Learning, physical models, and index-based algorithms. This is particularly relevant given the increasing demand for accurate information to address sustainable policies and support decision-making processes. Through a series of case studies, we highlight the versatility and utility of PRISMA's hyperspectral data for various scientific and operational applications.

We present a new strategy to identify bad pixels in hyperspectral pushbroom sensors and to replace the inaccurate radiance values with estimates derived from spectral and spatial analysis. The proposed method is quite effective to correct spaceborne hyperspectral data where the regular calibration of the instrument is more complex than in airborne applications. In this paper we discuss the results obtained on images acquired by the PRISMA hyperspectral instrument operated by the Italian Space Agency (ASI). These preliminary results show the effectiveness of the proposed strategy both in detecting even subtle sources of fixed pattern noise, otherwise undetectable using visual inspection of a single spectral band, and in accurately reconstructing the missing radiance values.

This article deals with the problem of improving the spatial resolution of hyperspectral (HS) data from the PRecursore IperSpettrale della Missione Applicativa (PRISMA) mission. For this purpose, higher spatial resolution data from the Sentinel-2 (S2) mission are exploited. Particularly, 10 S2 bands at 10 and 20 m spatial resolution are used to accomplish the PRISMA super-resolution (SR) task. The article presents a new end-to-end procedure, called PRISMA-SR, that starting from the S2 data and the low-resolution PRISMA image, provides a super-resolved image with a spatial resolution of 10 m and the same spectral resolution as the PRISMA HS sensor. The first step of the PRISMA-SR procedure consists in fusing S2 data at different spatial resolutions to obtain a synthetic MS image with 10 m spatial resolution and 10 spectral bands. Then, an unsupervised procedure is applied to coregister the fused S2 image and the PRISMA image. Finally, the two images at different spatial resolutions are properly combined in order to obtain the super-resolved HS image. Solutions for each step of the PRISMA-SR processing chain are proposed and discussed. Simulated data are used to show the effectiveness of the PRISMA-SR scheme and to investigate the impact on its performance of each step of the processing chain. Real S2 and PRISMA images are finally considered to provide an example of the application of the PRISMA-SR.

A Bayesian Likelihood Ratio Test (LRT) detector is analytically derived here for the replacement target model and using the non-parametric variable-bandwidth kernel density estimator to model the hyperspectral background. The detector is compared to the recent Generalized LRT detector, based on the same non-parametric model for the background. Experimental results obtained on two hyperspectral sub-pixel target detection scenarios reveal the great potential of the proposed detector and set the basis for future investigations.

In maritime surveillance, real-time moving target detection is a crucial task. The purpose of our work was to test some moving target detection techniques inspired by the state-of-the-art on a specific dataset of interest. In this paper, we analyze the performance obtained by Frame Difference and Gaussian Mixture Model-based methods in static InfraRed video sequences. The dataset was collected under real operational conditions during a recent experimental activity. The frames in the dataset are characterized by heterogeneous backgrounds and different targets covering a wide range of sizes and speeds. To evaluate the performance, the ground truth has been manually labeled through direct observation in 4706 frames. All the examined techniques are used to estimate the background. They are preceded by a frame-based z-normalization. After the background estimation, the absolute difference with the normalized frame is computed to highlight both hot and cold targets. Once highlighted, the targets can be separated from the background with a threshold. Then, morphological operations both in time and space are executed to delete small and brief false alarms. Finally, blob analysis is computed to extract the Regions of Interest. The algorithms have been evaluated based on their Precision-Recall curves, and Mean Execution Times.

In the maritime environment, Situational Awareness (SA) is a crucial task for many applications, including the defense of the naval tactical space. In this context, Electro-Optical (EO) sensors and, particularly InfraRed (IR) sensors, contribute to building the Local Area Picture (LAP). The purpose of this study is to face the challenging task of highlighting extended targets with respect to the open sea background without any prior knowledge about the size and position within the images. In this work, only single-frame object detection algorithms have been considered. As this task has been extensively explored in the three-channel color image domain, we adapted some color native state-of-the-art strategies on the IR monochromatic dimension. The algorithms have been tested on a dataset collected through a cooled Medium Wavelength (MW) sensor and an uncooled Long Wavelength (LW) sensor. The ground truth (GT) has been built through direct observation. Each technique has been then evaluated on the two sub-bands images according to broadly used performance indices.

Sea mines are still a concrete menace both for military and civilian ships and detecting them is necessary to ensure the safety of the navigation. In this work we explored the possibility of automatically detect mines by using unmanned Autonomous Underwater Vehicles equipped with Side Scan Sonar (SSS) Sensors. To accomplish the detection task, we considered saliency detection algorithms coming from RGB and radar fields to highlight the mines with respect to the background. The algorithms were tested on a valuable dataset of images collected by the Italian Navy under operational conditions during several activities conducted in the Mediterranean Sea. We evaluated the performance according to broadly used performance indices such as ROC curves and MAE scores. Furthermore, a new performance analysis score called FAR@95%Pd is presented.

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

In this work, we deal with the problem of atmospheric compensation (AC) of hyperspectral data collected in the visible and near-infrared (VNIR) spectral range. We propose the "learning-based" approach which uses artificial intelligence algorithms to directly estimate the spectral reflectance from the observed at-sensor radiance image. It uses a parametric regressor whose parameters are learned by means of a strategy based on synthetic data. Such data are generated taking into account 1) the radiative transfer in the atmosphere; 2) the variability of the surface spectral reflectance; and 3) the effects of signal-dependent random noise and spectral miscalibration errors. According to this general framework, we propose a specific multilinear regressor that starting from the knowledge of the atmospheric visibility compensates the water absorption and provides the spectral reflectance of each pixel of the analyzed image. Furthermore, a specific image-based procedure is presented for visibility estimation. The experiment over simulated data is presented and discussed. The test on simulated data aims at showing the effectiveness of the proposed strategy in a completely controlled environment. Experiments are also carried out on three real hyperspectral images acquired by two hyperspectral sensors. The obtained results confirm the effectiveness of the proposed approach by comparing the retrieved reflectance spectra with in-situ measurements or with those obtained by using a well-known commercial AC software.

This work deals with submerged object recognition methodologies with fluorescence LIDAR that can be applied when no prior information about environmental conditions is available. Previous invariant methods rely upon conventional unconstrained and constrained subspace projection concepts. This paper investigates application of sparsity-based concepts within this framework. A method enforcing both L 1 and L 2 norm penalties is investigated. Both synthetic and real data are employed to evaluate the potential of the method. Experimental results reveal that sparsity-based methods can be useful in this context and deserve further investigation.

In this work we extend the recently proposed Learning-Based approach to Atmospheric Compensation (LBAC) with respect to two different aspects: 1) the platform for data acquisition and 2) the spectral range covered by the sensor. Particularly, we propose the extension of LBAC to spaceborne hyperspectral sensor operating in the Visible Near InfraRed (VNIR) and Short-Wave InfraRed (SWIR) portion of the electromagnetic spectrum. We specifically refer to the sensor of the PRISMA (PRecursore IperSpettrale della Missione Applicativa) mission, the recent Earth Observation mission of the Italian Space Agency that offers a great opportunity to improve the knowledge on the scientific and commercial applications of spaceborne hyperspectral data. Results obtained on PRISMA hyperspectral images are presented and discussed.

Water quality assessment plays an important role in sustainable development of natural resources. Fluorescence LIDAR is among the preferred remote sensors used in water quality monitoring. This work presents an underwater fluorescence LIDAR simulator for water quality assessment developed to design, test, and validate methodologies for the retrieval of key biophysical parameters or to discriminate dissolved substances and pollutants. Experimental results illustrating the usefulness of the simulator are provided focusing, as a case-study, on a key water quality indicator playing a major role in the global carbon balance, namely the Chromophoric/colored Dissolved Organic Matter (CDOM).