• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 31
  • 4
  • 1
  • 1
  • Tagged with
  • 43
  • 43
  • 28
  • 21
  • 19
  • 15
  • 11
  • 10
  • 8
  • 8
  • 8
  • 7
  • 7
  • 6
  • 6
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
31

Automatic Target Recognition In Infrared Imagery

Bayik, Tuba Makbule 01 September 2004 (has links) (PDF)
The task of automatically recognizing targets in IR imagery has a history of approximately 25 years of research and development. ATR is an application of pattern recognition and scene analysis in the field of defense industry and it is still one of the challenging problems. This thesis may be viewed as an exploratory study of ATR problem with encouraging recognition algorithms implemented in the area. The examined algorithms are among the solutions to the ATR problem, which are reported to have good performance in the literature. Throughout the study, PCA, subspace LDA, ICA, nearest mean classifier, K nearest neighbors classifier, nearest neighbor classifier, LVQ classifier are implemented and their performances are compared in the aspect of recognition rate. According to the simulation results, the system, which uses the ICA as the feature extractor and LVQ as the classifier, has the best performing results. The good performance of this system is due to the higher order statistics of the data and the success of LVQ in modifying the decision boundaries.
32

Análise discriminatória de alvos da paisagem urbana em imagens aéreas multiespectrais

Barros, Anderson de Freitas [UNESP] 29 November 2010 (has links) (PDF)
Made available in DSpace on 2014-06-11T19:23:09Z (GMT). No. of bitstreams: 0 Previous issue date: 2010-11-29Bitstream added on 2014-06-13T19:09:02Z : No. of bitstreams: 1 barros_af_me_prud.pdf: 2562561 bytes, checksum: b5202d1eb66d73f102e8800f69945a7a (MD5) / O reconhecimento de padrões de alvos específicos presentes na paisagem urbana como telhados de edificações as quais não são padronizados, ou seja, possuem variadas formas geométricas, dimensões, cores e texturas não é uma tarefa simples devido à alta complexidade desses alvos. Detectar e discriminar esses alvos constitui tarefa fundamental nos processos de mapeamento baseados em análise de imagem. Entretanto, graças aos avanços tecnológicos incorporados às câmaras fotogramétricas digitais, tem-se percebido um aumento contínuo da resolução espectral. Isso torna possível adquirir imagens com maior potencial para a discriminação devido aos atributos espectrais. Como alternativa de sistema de aerolevantamento, foi desenvolvido o Sistema Aerotransportado de Aquisição e Pós- Processamento de Imagens Digitais (SAAPI) o qual é capaz de adquirir imagens aéreas multiespectrais com alta resolução espacial. O SAAPI é composto por sensores de quadro capazes de produzir imagens multiespectrais com características de flexibilidade, confiabilidade e baixo custo. Mas, esses dados espectrais devem ser avaliados em aplicações de reconhecimento de padrões para aprimorar sua utilização. Nesse contexto, este trabalho busca ajustar índices de realce para serem capazes de destacar alvos específicos como corpo d’água, sombra, via pavimentada e vegetação presentes na paisagem urbana registrados em imagens adquiridas pelo SAAPI... / Pattern recognition of specific targets in the urban scenery is not a simple task due to its high complexity. Recognizing building roofs, per example, has very variable features like geometrical form, dimension, color and texture. Detection and discrimination of these targets are basic tasks in mapping processes which are based on image analysis. Technological advancements of digital cameras have helped to improve the continuous increase of spectral resolution. Consequently, it allows the acquisition of aerial image data with higher potential for target discrimination based on spectral response. As an alternative to areal surveying system, it was developed the Lightweight Airborne Image Acquisition System (SAAPI) in order to survey high resolution areal-based multispectral images. The SAAPI is made-up of sensors to produce multispectral images with characteristics of flexibility, reliability and low cost. However, these spectral data must be evaluated for pattern recognition applications. Thus, this research intends to adjust enhancement indexes to detection of specific targets in the urban scenery, like water, shadow, paved roads and vegetation in images taken through the SAAPI... (Complete abstract click electronic access below)
33

Využití robotické totální stanice pro měření jeřábových drah / Application of robotic total station for crane tracks measurement

Chomjak, Ján January 2014 (has links)
This diploma thesis deals with application of robotic total station for crane tracks measuring. To determinate straight of rail tracks was used system of automatic target recognition. One crane track was measured by two methods. Horizontal deviation from straight direction was determinated directly by the method “line of sight” and indirectly using measuring angles and lengths. To determinate height continuance was used engineering and trigonometric leveling. The results of measuring proved, that reached deviations between methods are minimal, so we consider them as equal. System system of automatic target recognition reliably and with sufficient accuracy aims to the prism-centre.
34

Accuracy analysis and Calibration of Total Station based on the Reflectorless Distance Measurement

Reda Adinew, Amezene, Bedada Damtie, Bekele January 2012 (has links)
Abstract Reflectorless EDM technology uses phase measuring or pulsed lasers to measure targets of a reflective and non-reflective nature. Reflectorless distance measurement provides rapid measurement by saving time and labour for surveyors. However, the accuracy of these types of measurements is under question because of the variety of constraints that affect the measurement. This paper attempts to show the techniques of total station calibration and to investigate the possible sources of error in reflectorless distance measurement. As a result, the effects of different color targets and angle incidence on distance measurement were checked. The precision of reflectorless distance measurement also investigated. In addition, comparison was made for manual and automatic target recognition measurement. Further experiment was performed on how to calibrate the total station instrument and the performance of the instrument was checked by KTH-TSC software. The experiments were evaluated by taking the reflector reading as ‘true value’ to check the accuracy of reflectorless measurement. The effects of colour surfaces on distance measurement have no significant difference. Besides, the result shows that the error in distance increased as the angle of incidence in the target increases. The result also indicates that automatic target recognition mode is the most advisable technique for precise measurement. Finally, an optimal number of seven target points was found for the calculation of prism constant. / Sammandrag Reflektorlös EDM-tekniken använder fas mätning eller pulsade lasrar för att mäta mål en reflekterande och icke-reflekterande karaktär. Reflektorlös avståndsmätning ger snabb mätning genom att spara tid och arbete för inspektörer. Emellertid är noggrannheten hos dessa typer av mätningar under fråga på grund av olika begränsningar som påverkar mätningen. Denna uppsats försöker visa de metoder för totalstation kalibrering och att undersöka eventuella felkällor i reflektorlös avståndsmätning. Som ett resultat var effekterna av olika färger mål och vinkel inverkan på avståndsmätning kontrolleras. Noggrannheten i reflektorlös avståndsmätning undersökt också. Dessutom gjordes jämförelse för manuell och automatisk måligenkännande mätning. Ytterligare experiment utfördes på hur man kalibrerar totalstationen instrumentet och prestanda instrumentet kontrollerades av KTH-TSC programvara. Experimenten utvärderades genom att reflektorn läsning som "sanna värdet" för att kontrollera riktigheten i reflektorlös mätning. Effekterna av färgytor på avståndsmätning har ingen signifikant skillnad. Dessutom visar resultatet felet i avståndet ökade infallsvinkeln i målet ökar. Resultatet visar också automatiskt måligenkännande läget är det mest lämpligt tekniken för exakt mätning. Slutligen ett optimalt antal av sju målpunkter hittades för beräkning av prismakonstanten.
35

Deep Learning For RADAR Signal Processing

Wharton, Michael K. January 2021 (has links)
No description available.
36

Automatic target recognition using passive bistatic radar signals. / Reconnaissance automatique de cibles par utilisation de signaux de radars passifs bistatiques

Pisane, Jonathan 04 April 2013 (has links)
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.
37

Nucleotide Complementarity Features in the Design of Effective Artificial miRNAs

Yan, Yifei 04 1900 (has links)
No description available.
38

A Scalable Approach for Detecting Dumpsites using Automatic Target Recognition with Feature Selection and SVM through Satellite Imagery

Skogsmo, Markus January 2020 (has links)
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.
39

A 2D/3D Feature-Level Information Fusion Architecture For Remote Sensing Applications

Schierl, Jonathan 11 August 2022 (has links)
No description available.
40

Impact of Phase Information on Radar Automatic Target Recognition

Moore, Linda Jennifer January 2016 (has links)
No description available.

Page generated in 0.119 seconds