Recent advances in the field of lightweight technical platforms like UAV or nano-satellite have increased the demand for compact sensors including infrared hyperspectral cameras which are used nowadays in number of military and civilian applications. We propose a new compact infrared hyperspectral camera, the performance of which will allow it to be used in applications like gas detection, military vehicle detection, industrial installation surveillance or agriculture. To do so, we have chosen Fourier transform imaging spectrometry using a birefringent lateral shearing interferometer. Thereafter, we have deeply studied wave propagation in such an interferometer to find out optimal geometries, and we have designed three prototypes: two in the mid-infrared, partially and entirely cooled, and the other in the far infrared spectral domain. The partially cooled prototype has been realized, characterized in the laboratory and tested on the field. This field campaign provided hyperspectral images on real operating conditions. Analysis of these images allowed us to estimate the performance of our system and to identify the points to be improved. ; Les récentes avancées dans le domaine des plates-formes d'instrumentation légères telles que les drones ou les nano-satellites ont fortement augmenté la demande de capteurs compacts, y compris les capteurs d'imagerie hyperspectrale infrarouge qui sont utilisés, de nos jours, dans des nombreuses applications militaires et civiles. Nous proposons une nouvelle caméra hyperspectrale compacte infrarouge dont les performances nous permettront de viser les domaines applicatifs tels que la détection de gaz (panaches volcaniques ou industriels), la détection de véhicules militaires, la surveillance d'ouvrages (barrages, pipelines) ou encore l'agriculture. Pour y arriver, nous avons choisi la spectro-imagerie par transformée de Fourier utilisant un interféromètre biréfringent à décalage latéral. Nous avons ensuite procédé à une modélisation approfondie de tels interféromètres afin de ...
Recent advances in the field of lightweight technical platforms like UAV or nano-satellite have increased the demand for compact sensors including infrared hyperspectral cameras which are used nowadays in number of military and civilian applications. We propose a new compact infrared hyperspectral camera, the performance of which will allow it to be used in applications like gas detection, military vehicle detection, industrial installation surveillance or agriculture. To do so, we have chosen Fourier transform imaging spectrometry using a birefringent lateral shearing interferometer. Thereafter, we have deeply studied wave propagation in such an interferometer to find out optimal geometries, and we have designed three prototypes: two in the mid-infrared, partially and entirely cooled, and the other in the far infrared spectral domain. The partially cooled prototype has been realized, characterized in the laboratory and tested on the field. This field campaign provided hyperspectral images on real operating conditions. Analysis of these images allowed us to estimate the performance of our system and to identify the points to be improved. ; Les récentes avancées dans le domaine des plates-formes d'instrumentation légères telles que les drones ou les nano-satellites ont fortement augmenté la demande de capteurs compacts, y compris les capteurs d'imagerie hyperspectrale infrarouge qui sont utilisés, de nos jours, dans des nombreuses applications militaires et civiles. Nous proposons une nouvelle caméra hyperspectrale compacte infrarouge dont les performances nous permettront de viser les domaines applicatifs tels que la détection de gaz (panaches volcaniques ou industriels), la détection de véhicules militaires, la surveillance d'ouvrages (barrages, pipelines) ou encore l'agriculture. Pour y arriver, nous avons choisi la spectro-imagerie par transformée de Fourier utilisant un interféromètre biréfringent à décalage latéral. Nous avons ensuite procédé à une modélisation approfondie de tels interféromètres afin de déterminer une configuration optimale associant compacité et résolution spectrale requise. Cette modélisation a été utilisée pour dimensionner trois prototypes avec des spécifications précises : deux prototypes dans le moyen infrarouge, l'un entièrement refroidi et l'autre partiellement refroidi et un prototype dans le lointain infrarouge. Nous avons ensuite réalisé le prototype partiellement refroidi que nous avons caractérisé en laboratoire et que nous avons mis en œuvre sur le terrain. Cette campagne de mesures nous a permis d'obtenir des images hyperspectrales dans des conditions réelles d'utilisation. Par l'analyse de ces images, nous avons évalué les performances opérationnelles de notre système et identifié les points à améliorer.
Recent advances in the field of lightweight technical platforms like UAV or nano-satellite have increased the demand for compact sensors including infrared hyperspectral cameras which are used nowadays in number of military and civilian applications. We propose a new compact infrared hyperspectral camera, the performance of which will allow it to be used in applications like gas detection, military vehicle detection, industrial installation surveillance or agriculture. To do so, we have chosen Fourier transform imaging spectrometry using a birefringent lateral shearing interferometer. Thereafter, we have deeply studied wave propagation in such an interferometer to find out optimal geometries, and we have designed three prototypes: two in the mid-infrared, partially and entirely cooled, and the other in the far infrared spectral domain. The partially cooled prototype has been realized, characterized in the laboratory and tested on the field. This field campaign provided hyperspectral images on real operating conditions. Analysis of these images allowed us to estimate the performance of our system and to identify the points to be improved. ; Les récentes avancées dans le domaine des plates-formes d'instrumentation légères telles que les drones ou les nano-satellites ont fortement augmenté la demande de capteurs compacts, y compris les capteurs d'imagerie hyperspectrale infrarouge qui sont utilisés, de nos jours, dans des nombreuses applications militaires et civiles. Nous proposons une nouvelle caméra hyperspectrale compacte infrarouge dont les performances nous permettront de viser les domaines applicatifs tels que la détection de gaz (panaches volcaniques ou industriels), la détection de véhicules militaires, la surveillance d'ouvrages (barrages, pipelines) ou encore l'agriculture. Pour y arriver, nous avons choisi la spectro-imagerie par transformée de Fourier utilisant un interféromètre biréfringent à décalage latéral. Nous avons ensuite procédé à une modélisation approfondie de tels interféromètres afin de déterminer une configuration optimale associant compacité et résolution spectrale requise. Cette modélisation a été utilisée pour dimensionner trois prototypes avec des spécifications précises : deux prototypes dans le moyen infrarouge, l'un entièrement refroidi et l'autre partiellement refroidi et un prototype dans le lointain infrarouge. Nous avons ensuite réalisé le prototype partiellement refroidi que nous avons caractérisé en laboratoire et que nous avons mis en œuvre sur le terrain. Cette campagne de mesures nous a permis d'obtenir des images hyperspectrales dans des conditions réelles d'utilisation. Par l'analyse de ces images, nous avons évalué les performances opérationnelles de notre système et identifié les points à améliorer.
With the global war on terrorism, the nature of military warfare has changed significantly. The United States Air Force is at the forefront of research and development in the field of intelligence, surveillance, and reconnaissance that provides American forces on the ground and in the air with the capability to seek, monitor, and destroy mobile terrorist targets in hostile territory. One such capability recognizes and persistently tracks multiple moving vehicles in complex, highly ambiguous urban environments. The thesis investigates the feasibility of augmenting a multiple-target tracking system with hyperspectral imagery. The research effort evaluates hyperspectral data classification using fuzzy c-means and the self-organizing map clustering algorithms for remote identification of moving vehicles. Results demonstrate a resounding 29.33% gain in performance from the baseline kinematic-only tracking to the hyperspectral-augmented tracking. Through a novel methodology, the hyperspectral observations are integrated in the MTT paradigm. Furthermore, several novel ideas are developed and implemented—spectral gating of hyperspectral observations, a cost function for hyperspectral observation-to-track association, and a self-organizing map filtering method. It appears that relatively little work in the target tracking and hyperspectral image classification literature exists that addresses these areas. Finally, two hyperspectral sensor modes are evaluated—Pushbroom and Region-of-Interest. Both modes are based on realistic technologies, and investigating their performance is the goal of performance-driven sensing. Performance comparison of the two modes can drive future design of hyperspectral sensors.
"This book is intended to provide a detailed perspective on techniques and challenges in detecting the urban materials using hyperspectral data including systematic perspective on spectral properties of the materials and methods. It adopts process chain approach in describing the topic and explains image processing steps from reflectance calibration to final insights. The objective of the book is to provide in depth information on hyperspectral remote sensing of urban materials covering global case studies as applicable. It covers complete processing chain of hyperspectral data specifically in urban environment and gives more information about the mapping and classification of urban scenes. The book includes information from basic imaging spectroscopy to the advanced methods such as deep learning for imaging spectroscopy and reviews detailed spectral characteristics of urban materials commonly found in world cities. It also discusses advanced supervised methods such as deep learning with due focus on hyperspectral data analysis. This book is aimed at professionals and graduate students in Hyperspectral Imaging, Urban Remote Sensing, and Hyperspectral Image Processing"--
Hyperspectral image (HSI) based detection has attracted considerable attention recently in agriculture, environmental protection and military applications as different wavelengths of light can be advantageously used to discriminate different types of objects. Unfortunately, estimating the background distribution and the detection of interesting local objects is not straightforward, and anomaly detectors may give false alarms. In this paper, a Deep Belief Network (DBN) based anomaly detector is proposed. The high-level features and reconstruction errors are learned through the network in a manner which is not affected by previous background distribution assumption. To reduce contamination by local anomalies, adaptive weights are constructed from reconstruction errors and statistical information. By using the code image which is generated during the inference of DBN and modified by adaptively updated weights, a local Euclidean distance between under test pixels and their neighboring pixels is used to determine the anomaly targets. Experimental results on synthetic and recorded HSI datasets show the performance of proposed method outperforms the classic global Reed-Xiaoli detector (RXD), local RX detector (LRXD) and the-state-of-the-art Collaborative Representation detector (CRD).
The alignment of images, also known as registration, is a relevant task in the processing of hyperspectral images. Among the feature-based registration methods, Speeded Up Robust Features (SURF) has been proposed as a computationally efficient approach. In this paper HSI–SURF is proposed. This is a method to register hyperspectral remote sensing images based on SURF that takes advantage of the full spectral information of the images. In this sense, the proposed method selects specific bands of the images and adapts the keypoint descriptor and the matching stages to benefit from the spectral information, thus increasing the effectiveness of the registration. ; This work was supported in part by the Consellería de Educación, Universidade e Formación Profesional [grant numbers GRC2014/008, ED431C 2018/19, and ED431G/08] and Ministerio de Economía y Empresa, Government of Spain [grant number TIN2016-76373-P] and by Junta de Castilla y Leon - ERDF (PROPHET Project) [grant number VA082P17]. All are cofunded by the European Regional Development Fund (ERDF). The work of Alvaro Ordóñez was also supported by the Ministerio de Ciencia, Innovación y Universidades, Government of Spain, under a FPU Grant [grant number FPU16/03537]
"Hyperspectral imaging, as an emerging technology, acquires and analyzes a large amount of spectral and spatial information from a real scene in the form of three-dimensional images. The technology offers unprecedented capabilities, compared to conventional imaging and spectroscopy, for a wide range of applications from satellite remote sensing to biomedical imaging and to product quality and safety inspection. Image processing and analysis is thus at the core of the technology. With rapid developments both in hardware and software in recent years and increased demands for better quality and safer food products, we have witnessed expanding R&D activities and applications of hyperspectral imaging technology in objective, rapid, non-destructive and automated safety inspection and quality control for a variety of food and agricultural products and production. Hyperspectral Imaging Technology in Food and Agriculture is focused on major recent advances in research and applications of hyperspectral imaging technology in food and agriculture. The book begins with the fundamentals of the technology, followed by a comprehensive coverage of food quality and safety evaluation in meats, fruits, vegetables, grains and other foods, as well as remote sensing for crop production. This book is written by international peers who have academic and professional credentials, with each chapter addressing a particular topic or specific application of the technology. The book provides the engineer and technologist working in the food and agricultural industry with critical, comprehensive and readily accessible information on hyperspectral imaging technology. It also serves as an essential reference source to undergraduate and postgraduate students and researchers in universities and research institutions"--Back cover
Hyperspectral images contain a great amount of information which can be used to more robustly register such images. In this article, we present a phase correlation method to register two hyperspectral images that takes into account their multiband structure. The proposed method is based on principal component analysis, the multilayer fractional Fourier transform, a combination of log-polar maps, and peak processing. The combination of maps is aimed at highlighting some peaks in the log-polar map using information from different bands. The method is robust and has been successfully tested for any rotation angle with commonly used hyperspectral scenes in remote sensing for scales of up to 7.5× and with pairs of hyperspectral images taken on different dates by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) sensor for scales of up to 6.0× ; This work was supported in part by the Consellería de Cultura, Educación e Ordenación Universitaria [grant numbers GRC2014/008 and ED431G/08] and Ministry of Education, Culture and Sport, Government of Spain [grant numbers TIN2013-41129-P and TIN2016-76373-P] both are co-funded by the European Regional Development Fund (ERDF) ; SI
The use of Convolutional Neural Networks (CNNs) to solve Domain Adaptation (DA) image classification problems in the context of remote sensing has proven to provide good results but at high computational cost. To avoid this problem, a deep learning network for DA in remote sensing hyperspectral images called TCANet is proposed. As a standard CNN, TCANet consists of several stages built based on convolutional filters that operate on patches of the hyperspectral image. Unlike the former, the coefficients of the filter are obtained through Transfer Component Analysis (TCA). This approach has two advantages: firstly, TCANet does not require training based on backpropagation, since TCA is itself a learning method that obtains the filter coefficients directly from the input data. Second, DA is performed on the fly since TCA, in addition to performing dimensional reduction, obtains components that minimize the difference in distributions of data in the different domains corresponding to the source and target images. To build an operating scheme, TCANet includes an initial stage that exploits the spatial information by providing patches around each sample as input data to the network. An output stage performing feature extraction that introduces sufficient invariance and robustness in the final features is also included. Since TCA is sensitive to normalization, to reduce the difference between source and target domains, a previous unsupervised domain shift minimization algorithm consisting of applying conditional correlation alignment (CCA) is conditionally applied. The results of a classification scheme based on CCA and TCANet show that the DA technique proposed outperforms other more complex DA techniques ; This work was supported in part by Consellería de Educación, Universidade e Formación Profesional [grant numbers GRC2014/008, ED431C 2018/19, and ED431G/08] and Ministerio de Economía y Empresa, GovernmentofSpain[grantnumberTIN2016-76373-P].Allareco–fundedbytheEuropeanRegionalDevelopment Fund (ERDF). This work ...
In latest years, the possibility to exploit the high amount of spectral information has made hyperspectral remote sensing a very promising approach to detect changes occurred in multi-temporal images. Detection of changes in images of the same area collected at different times is of crucial interest in military and civilian applications, spanning from wide area surveillance and damage assessment to geology and land cover. In military operations, the interest is in rapid location and tracking of objects of interest, people, vehicles or equipment that pose a potential threat. In civilian contexts, changes of interest may include different types of natural or manmade threats, such as the path of an impending storm or the source of a hazardous material spill. In this PhD thesis, the focus is on Anomalous Change Detection (ACD) in airborne hyperspectral images. The goal is the detection of small changes occurred in two images of the same scene, i.e. changes having size comparable with the sensor ground resolution. The objects of interest typically occupy few pixels of the image and change detection must be accomplished in a pixel-wise fashion. Moreover, since the images are in general not radiometrically comparable, because illumination, atmospheric and environmental conditions change from one acquisition to the other, pervasive and uninteresting changes must be accounted for in developing ACD strategies. ACD process can be distinguished into two main phases: a pre-processing step, which includes radiometric correction, image co-registration and noise filtering, and a detection step, where the pre-processed images are compared according to a defined criterion in order to derive a statistical ACD map highlighting the anomalous changes occurred in the scene. In the literature, ACD has been widely investigated providing valuable methods in order to cope with these problems. In this work, a general overview of ACD methods is given reviewing the most known pre-processing and detection methods proposed in the literature. The analysis has been conducted unifying different techniques in a common framework based on binary decision theory, where one has to test the two competing hypotheses H0 (change absent) and H1 (change present) on the basis of an observation vector derived from the radiance measured on each pixel of the two images. Particular emphasis has been posed on statistical approaches, where ACD is derived in the framework of Neymann Pearson theory and the decision rule is carried out on the basis of the statistical properties assumed for the two hypotheses distribution, the observation vector space and the secondary data exploited for the estimation of the unknown parameters. Typically, ACD techniques assume that the observation represents the realization of jointly Gaussian spatially stationary random process. Though such assumption is adopted because of its mathematical tractability, it may be quite simplistic to model the multimodality usually met in real data. A more appropriate model is that adopted to derive the well known RX anomaly detector which assumes the local Gaussianity of the hyperspectral data. In this framework, a new statistical ACD method has been proposed considering the local Gaussianity of the hyperspectral data. The assumption of local stationarity for the observations in the two hypotheses is taken into account by considering two different models, leading to two different detectors. In addition, when data are collected by airborne platforms, perfect co-registration between images is very difficult to achieve. As a consequence, a residual misregistration (RMR) error should be taken into account in developing ACD techniques. Different techniques have been proposed to cope with the performance degradation problem due to the RMR, embedding the a priori knowledge on the statistical properties of the RMR in the change detection scheme. In this context, a new method has been proposed for the estimation of the first and second order statistics of the RMR. The technique is based on a sequential strategy that exploits the Scale Invariant Feature Transform (SIFT) algorithm cascaded with the Minimum Covariance Determinant algorithm. The proposed method adapts the SIFT procedure to hyperspectral images and improves the robustness of the outliers filtering by means of a highly robust estimator of multivariate location. Then, the attention has been focused on noise filtering techniques aimed at enforcing the consistency of the ACD process. To this purpose, a new method has been proposed to mitigate the negative effects due to random noise. In particular, this is achieved by means of a band selection technique aimed at discarding spectral channels whose useful signal content is low compared with the noise contribution. Band selection is performed on a per-pixel basis by exploiting the estimates of the noise variance accounting also for the presence of the signal dependent noise component. Finally, the effectiveness of the proposed techniques has been extensively evaluated by employing different real hyperspectral datasets containing anomalous changes collected in different acquisition conditions and on different scenarios, highlighting advantages and drawbacks of each method. In summary, the main issues related to ACD in multi-temporal hyperspectral images have been examined in this PhD thesis. With reference to the pre-processing step, two original contributions have been offered: i) an unsupervised technique for the estimation of the RMR noise affecting hyperspectral images, and ii) an adaptive approach for ACD which mitigates the negative effects due to random noise. As to the detection step, a survey of the existing techniques has been carried out, highlighting the major drawbacks and disadvantages, and a novel contribution has been offered by presenting a new statistical ACD method which considers the local Gaussianity of the hyperspectral data.
In: ISPRS journal of photogrammetry and remote sensing: official publication of the International Society for Photogrammetry and Remote Sensing (ISPRS), Band 88, S. 101-118