We present the design, development, and test of three novel, distinct automatic target recognition (ATR) systems for the recognition of airplanes and, more specifically, non-cooperative airplanes, i.e. airplanes that do not provide information when interrogated, in the framework of passive bistatic radar systems. Passive bistatic radar systems use one or more illuminators of opportunity (already present in the field), with frequencies up to 1 GHz for the transmitter part of the systems considered here, and one or more receivers, deployed by the persons managing the system, and not co-located with the transmitters. The sole source of information are the signal scattered on the airplane and the direct-path signal that are collected by the receiver, some basic knowledge about the transmitter, and the geometrical bistatic radar configuration. The three distinct ATR systems that we built respectively use the radar images, the bistatic complex radar cross-section (BS-RCS), and the bistatic radar cross-section (BS-RCS) of the targets. We use data acquired either on scale models of airplanes placed in an anechoic, electromagnetic chamber or on real-size airplanes using a bistatic testbed consisting of a VOR transmitter and a software-defined radio (SDR) receiver, located near Orly airport, France. We describe the radar phenomenology pertinent for the problem at hand, as well as the mathematical underpinnings of the derivation of the bistatic RCS values and of the construction of the radar images.For the classification of the observed targets into pre-defined classes, we use either extremely randomized trees or subspace methods. A key feature of our approach is that we break the recognition problem into a set of sub-problems by decomposing the parameter space, which consists of the frequency, the polarization, the aspect angle, and the bistatic angle, into regions. We build one recognizer for each region. We first validate the extra-trees method on the radar images of the MSTAR dataset, featuring ground vehicles. We then test the method on the images of the airplanes constructed from data acquired in the anechoic chamber, achieving a probability of correct recognition up to 0.99.We test the subspace methods on the BS-CRCS and on the BS-RCS of the airplanes extracted from the data acquired in the anechoic chamber, achieving a probability of correct recognition up to 0.98, with variations according to the frequency band, the polarization, the sector of aspect angle, the sector of bistatic angle, and the number of (Tx,Rx) pairs used. The ATR system deployed in the field gives a probability of correct recognition of $0.82$, with variations according to the sector of aspect angle and the sector of bistatic angle.

Throughout the world, there is a great demand to map out the increasing environmental changes and life habitats on Earth. The vast majority of Earth Observations today, are collected using satellites. The Global Watch Center (GWC) initiative was started with the purpose of producing a global situational awareness of the premises for all life on Earth. By collecting, studying and analyzing vast amounts of data in an automatic, scalable and transparent way, the GWC aims are to work towards reaching the United Nations (UN) Sustainable Development Goals (SDG). The GWC vision is to make use of qualified accessible data together with leading organizations in order to lay the foundation of the important decisions that have the biggest potential to make an actual difference for the common awaited future. As a show-case for the initiative, the UN strategic department has recommended a specific use-case, involving mapping large accumulation of waste in areas greatly affected, which they believe will profit the initiative very much. This Master Thesis aim is, in an automatic and scalable way, to detect and classify dumpsites in Kampala, the capital of Uganda, by using available satellite imagery. The hopes are that showing technical feasibility and presenting interesting remarks will aid in spurring further interest in coming closer to a realization of the initiative. The technical approach is to use a lightweight version of Automatic Target Recognition. This is conventionally used in military applications but is here used, to detect and classify features of large accumulations of solid-waste by using techniques from the field of Image Analysis and Data Mining. Choice of data source, this study's area of interest as well as choice of methodology for Feature Extraction and choice of the Machine Learning algorithm Support Vector Machine will all be described and implemented. With a classification precision of 95 percent will technical results be presented, with the ambition to promote further work and contribute to the GWC initiative with valuable information for later realization.

No description available.

No description available.

Dans cette thèse, nous présentons la conception, le développement et le test de trois systèmes de reconnaissance automatique de cibles (ATR) visant à reconnaître des avions non-coopératifs, c’est-à-dire des avions ne fournissant par leur identité, en utilisant des signaux de radars passifs bistatiques. Les radars passifs bistatiques utilisent un ou plusieurs émetteurs d’opportunité (déjà présents sur le terrain), avec des fréquences allant jusqu’à 1 GHz pour les émetteurs considérés ici, et un ou plusieurs récepteurs déployés par le gestionnaire du système et non-colocalisés avec les émetteurs. Les seules informations utilisées sont les signaux réfléchis sur les avions et les signaux directement reçus qui sont tous les deux collectés par le récepteur, quelques informations concernant l’émetteur, et la configuration géométrique du radar bistatique.Les trois systèmes ATR que nous avons construits utilisent respectivement les images radar, les surfaces équivalentes radar (SER) complexes bistatiques et les SER réelles bistatiques. Nous utilisons des données acquises soit sur des modèles d’avions placés en chambre anéchoique à l’ONERA, soit sur des avions réels en utilisant un banc d’essai bistatique consistant en un émetteur VOR et un récepteur basé sur la radio-logicielle (SDR), et que nous avons déployé aux alentours de l’aéroport d’Orly. Nous décrivons d’abord la phénoménologie radar pertinente pour notre problème ainsi que les fondements mathématiques pour la dérivation de la SER bistatique d’un objet, et pour la construction d’images radar d’un objet.Nous utilisons deux méthodes pour la classification de cibles en classes prédéfinies : les arbres extrêmement aléatoires (extra-trees) et les méthodes de sous-espaces. Une caractéristique-clé de notre approche est que nous divisons le problème de reconnaissance global en un ensemble de sous-problèmes par décomposition de l’espace des paramètres (fréquence, polarisation, angle d’aspect et angle bistatique) en régions. Nous construisons un classificateur par région.Nous validons en premier lieu la méthode des extra-trees sur la base de données MSTAR, composée d’images radar de véhicules terrestres. Ensuite, nous testons cette méthode sur des images radar d’avions que nous avons construites à partir des données acquises en chambre anéchoique. Nous obtenons un pourcentage de classification allant jusqu’à 99%. Nous testons ensuite la méthode de sous-espaces sur les SER bistatiques (complexes et réelles) des avions que nous avons extraits des données de chambre anéchoique. Nous obtenons un pourcentage de classification allant jusqu’à 98%, avec des variations suivant la fréquence, la polarisation, l’angle d’aspect, l’angle bistatique et le nombre de paires émetteur-récepteur utilisées. Nous testons enfin la méthode de sous-espaces sur les SER bistatiques (réelles) extraites des signaux acquis par le banc d’essai déployé à Orly. Nous obtenons une probabilité de classification de 82%, avec des variations suivant l’angle d’aspect et l’angle bistatique. On a donc démontré dans cette thèse que l’on peut reconnaitre des cibles aériennes à partir de leur SER acquise en utilisant des signaux de radars passifs bistatiques. / We present the design, development, and test of three novel, distinct automatic target recognition (ATR) systems for the recognition of airplanes and, more specifically, non-cooperative airplanes, i.e. airplanes that do not provide information when interrogated, in the framework of passive bistatic radar systems. Passive bistatic radar systems use one or more illuminators of opportunity (already present in the field), with frequencies up to 1 GHz for the transmitter part of the systems considered here, and one or more receivers, deployed by the persons managing the system, and not co-located with the transmitters. The sole source of information are the signal scattered on the airplane and the direct-path signal that are collected by the receiver, some basic knowledge about the transmitter, and the geometrical bistatic radar configuration. The three distinct ATR systems that we built respectively use the radar images, the bistatic complex radar cross-section (BS-RCS), and the bistatic radar cross-section (BS-RCS) of the targets. We use data acquired either on scale models of airplanes placed in an anechoic, electromagnetic chamber or on real-size airplanes using a bistatic testbed consisting of a VOR transmitter and a software-defined radio (SDR) receiver, located near Orly airport, France. We describe the radar phenomenology pertinent for the problem at hand, as well as the mathematical underpinnings of the derivation of the bistatic RCS values and of the construction of the radar images.For the classification of the observed targets into pre-defined classes, we use either extremely randomized trees or subspace methods. A key feature of our approach is that we break the recognition problem into a set of sub-problems by decomposing the parameter space, which consists of the frequency, the polarization, the aspect angle, and the bistatic angle, into regions. We build one recognizer for each region. We first validate the extra-trees method on the radar images of the MSTAR dataset, featuring ground vehicles. We then test the method on the images of the airplanes constructed from data acquired in the anechoic chamber, achieving a probability of correct recognition up to 0.99.We test the subspace methods on the BS-CRCS and on the BS-RCS of the airplanes extracted from the data acquired in the anechoic chamber, achieving a probability of correct recognition up to 0.98, with variations according to the frequency band, the polarization, the sector of aspect angle, the sector of bistatic angle, and the number of (Tx,Rx) pairs used. The ATR system deployed in the field gives a probability of correct recognition of $0.82$, with variations according to the sector of aspect angle and the sector of bistatic angle.

No description available.