Spelling suggestions: "subject:"1arget aclassification"" "subject:"1arget 1classification""
11 |
Amélioration des techniques de reconnaissance automatique de mines marines par analyse de l'écho à partir d'images sonar haute résolution / Improvement of automatic recognition techniques of marine mines by analyzing echo in high resolution sonar imagesElbergui, Ayda 10 December 2013 (has links)
La classification des cibles sous-marines est principalement basée sur l'analyse de l'ombre acoustique. La nouvelle génération des sonars d'imagerie fournit une description plus précise de la rétrodiffusion de l'onde acoustique par les cibles. Par conséquent, la combinaison de l'analyse de l'ombre et de l'écho est une voie prometteuse pour améliorer la classification automatique des cibles. Quelques systèmes performants de classification automatique des cibles s'appuient sur un modèle pour faire l'apprentissage au lieu d'utiliser uniquement des réponses expérimentales ou simulées de cibles pour entraîner le classificateur. Avec une approche basée modèle, un bon niveau de performance en classification peut être obtenu si la modélisation de la réponse acoustique de la cible est suffisamment précise. La mise en œuvre de la méthode de classification a nécessité de modéliser avec précision la réponse acoustique des cibles. Le résultat de cette modélisation est un simulateur d'images sonar (SIS). Comme les sonars d'imagerie fonctionnent à haute et très haute fréquence le modèle est basé sur le lancer de rayons acoustiques. Plusieurs phénomènes sont pris en compte pour augmenter le réalisme de la réponse acoustique (les effets des trajets multiples, l'interaction avec le fond marin, la diffraction, etc.). La première phase du classificateur utilise une approche basée sur un modèle. L'information utile dans la signature acoustique de la cible est nommée « A-scan ». Dans la pratique, l'A-scan de la cible détectée est comparé à un ensemble d'A-scans générés par SIS dans les mêmes conditions opérationnelles. Ces gabarits (A-scans) sont créés en modélisant des objets manufacturés de formes simples et complexes (mines ou non mines). Cette phase intègre un module de filtrage adapté pour permettre un résultat de classification plus souple capable de fournir un degré d'appartenance en fonction du maximum de corrélation obtenu. Avec cette approche, l'ensemble d'apprentissage peut être enrichi afin d'améliorer la classification lorsque les classes sont fortement corrélées. Si la différence entre les coefficients de corrélation de l'ensemble de classes les plus probables n'est pas suffisante, le résultat est considéré ambigu. Une deuxième phase est proposée afin de distinguer ces classes en ajoutant de nouveaux descripteurs et/ou en ajoutant davantage d'A-scans dans la base d'apprentissage et ce, dans de nouvelles configurations proches des configurations ambiguës. Ce processus de classification est principalement évalué sur des données simulées et sur un jeu limité de données réelles. L'utilisation de l'A-scan a permis d'atteindre des bonnes performances de classification en mono-vue et a amélioré le résultat de classification pour certaines ambiguïtés récurrentes avec des méthodes basées uniquement sur l'analyse d'ombre. / Underwater target classification is mainly based on the analysis of the acoustic shadows. The new generation of imaging sonar provides a more accurate description of the acoustic wave scattered by the targets. Therefore, combining the analysis of shadows and echoes is a promising way to improve automated target classification. Some reliable schemes for automated target classification rely on model based learning instead of only using experimental samples of target acoustic response to train the classifier. With this approach, a good performance level in classification can be obtained if the modeling of the target acoustic response is accurate enough. The implementation of the classification method first consists in precisely modeling the acoustic response of the targets. The result of the modeling process is a simulator called SIS (Sonar Image Simulator). As imaging sonars operate at high or very high frequency the core of the model is based on acoustical ray-tracing. Several phenomena have been considered to increase the realism of the acoustic response (multi-path propagation, interaction with the surrounding seabed, edge diffraction, etc.). The first step of the classifier consists of a model-based approach. The classification method uses the highlight information of the acoustic signature of the target called « A-scan ». This method consists in comparing the A-scan of the detected target with a set of simulated A-scans generated by SIS in the same operational conditions. To train the classifier, a Template base (A-scans) is created by modeling manmade objects of simple and complex shapes (Mine Like Objects or not). It is based on matched filtering in order to allow more flexible result by introducing a degree of match related to the maximum of correlation coefficient. With this approach the training set can be extended increasingly to improve classification when classes are strongly correlated. If the difference between the correlation coefficients of the most likely classes is not sufficient the result is considered ambiguous. A second stage is proposed in order to discriminate these classes by adding new features and/or extending the initial training data set by including more A-scans in new configurations derived from the ambiguous ones. This classification process is mainly assessed on simulated side scan sonar data but also on a limited data set of real data. The use of A-scans have achieved good classification performances in a mono-view configuration and can improve the result of classification for some remaining confusions using methods only based on shadow analysis.
|
12 |
Application Of High Frequency Natural Resonances Extracted From Electromagnetic Scattering Response For Discrimination Of Radar Targets With Minor VariationsMenon, K Rajalakshmi 04 1900 (has links)
Radars, as the name suggests, were traditionally used for Radio Detection and Ranging. Nevertheless, advances in high resolution electromagnetic simulations, Ultra Wide-Band sources, signal processing and computer technologies have resulted in a possible perception of radars as sensors for target discrimination. In this thesis, the feasibility of discrimination between targets even with minor variations in structure and material composition on the basis of radar echoes is effectively demonstrated.
It is well-known that the echoes from any target are affected by its natural frequencies which are dependent only on the shape and material composition of the target, and independent of the aspect angle or the incident waveform. The E-pulse technique is based on the fact that incident waveforms can be designed that uniquely annihilate the echoes from chosen regions of a target, and forms the basis of the method of discrimination proposed in this thesis.
Earlier methods reported in the literature, effectively discriminated only between different classes of targets with substantial variations in the overall dimensions of the body. Discrimination of targets of the same class with a minor structural modification or with a material coating on specific areas was rather difficult. This thesis attempts and successfully validates a method which comprehensively addresses this problem. The key idea of this method is to use the higher frequency resonances (which characterise the finer details of a target) in the E-pulse technique.
An obviously important aspect of target discrimination is therefore that of precisely estimating the natural frequencies for each target and understanding the changes in these frequencies, and their associations with the changes in structure and material composition. Current approaches to determine these frequencies are either based In the time or frequency
domains. While the latter approach comprises the computation of the roots of a related determinantal equation, in the time domain, the natural frequencies are extracted from the
response of a target to an impulse. Such a response can either be generated from actual experiments or by simulating the scattering response using Computational Electromagnetic (CEM) techniques. In this work, the impulse response is obtained from the frequency response of the scatterers in the frequency range of interest. Since no single CEM technique can effectively cover the entire range of frequencies needed for the E-Pulse synthesis. The Method of Moments and Physical Optics have been used for low and high frequency scattering respectively. The results obtained using the latter technique are validated by comparing with those obtained using Method of Moments at the transition frequencies and Geometrical Theory of Diffraction (GTD).
The natural frequencies (i.e., poles of a corresponding transfer function) are extracted from the impulse response using Prony's algorithm. One of the parameters in this method is the number of such poles (i.e.. the order of the transfer function) present in the response, and the accuracy of the computed pole values depends on this assumed order. Here, the Hankel singular values of a transfer function is used to estimate the number of poles. This in turn implies that a specific norm of the error between a transfer function corresponding to the frequency response generated earlier, and a transfer function with an assumed order obtained using Prony's method is minimised.
In the thesis, a wide range of target shapes are considered for purposes of illustration: wires, cylinders, spheres, plates and complex bodies such as aircraft, and the discrimination capability is demonstrated by introducing minor perturbations in their shape and/or material composition. .The following cases are considered here: (a) Wires: Conducting wires with a protrusion in one segment; conducting wire from another coated with a dielectric in a segment, (b) Cylinders: Conducting cylinders with one perturbed; conducting cylinders with a portion scrapped off in the middle, (c) Plates: Conducting plates with a elongation on one comer; conducting plate with another one with a hole in the centre, (d) Spheres: Conducting spheres with different radii; conducting spheres with Radar Absorbing Material coated spheres with different coating thickness; conducting spheres with chiral coated spheres with varying coating thickness, (e) Aircraft: Canonical model of MiG-29 aircraft from a similar one with stores placed under the wing.
|
Page generated in 0.082 seconds