Automatic target recognition in infrared imagery

Download

index.pdf

Date

2004

Author

Bayık, Tuba Makbule

Metadata

Show full item record

Item Usage Stats

151
views

68
downloads

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.

Subject Keywords

Technology.

URI

http://etd.lib.metu.edu.tr/upload/2/12605388/index.pdf
https://hdl.handle.net/11511/14396

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Modeling of a generic laser guided weapon with velocity pursuit guidance and its performance analysis using various control strategies Güner, Dünya Rauf Levent; Platin, Bülent Emre; Department of Mechanical Engineering (2004) In this thesis, a base for the modeling and analysis of laser guided weapons is constituted. In particular, the effects of several control schemes on the performance of a generic laser guided weapon system are investigated. In this generic model, it is assumed that the velocity pursuit guidance is employed via a velocity aligning seeker as the sole sensor. The laser seeker is modeled experimentally, based on data obtained by conducting a series of tests. The laser reflection is also modeled. Aerodynamic coe...
Moving Object Detction in 2D and 3D Scenes Sırtkaya, Salim; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2004) This thesis describes the theoretical bases, development and testing of an integrated moving object detection framework in 2D and 3D scenes. The detection problem is analyzed in stationary and non-stationary camera sequences and different algorithms are developed for each case. Two methods are proposed in stationary camera sequences: background extraction followed by differencing and thresholding, and motion detection using optical flow field calculated by أKanade-Lucas Feature Trackerؤ. For non-stationary ...
Offshore oil slick detection with remote sensing techniques Akar, Sertaç; Süzen, Mehmet Lütfi; Department of Geological Engineering (2007) The aim of this thesis is to develop a methodology for detection of naturally occurring offshore oil slicks originating from hydrocarbon seeps using satellite remote sensing techniques. In this scope, Synthetic Aperture Radar (SAR) imagery has been utilized. Case study area was Andrusov High in the Central Black Sea. Hydrocarbon seepage from tectonic or stratigraphic origin at the sea floor causes oily gas plumes to rise up to the sea surface. They form thin oil films on the sea surface called oil slicks. P...
Infrared low observable material design, synthesis and characterization Keskin, Ahmet; Ünalan, Hüsnü Emrah; Bek, Alpan; Department of Metallurgical and Materials Engineering (2023-1-27) In recent years, infrared low-observable technology has come to the fore in the aerospace and defense industry to conceal military aircraft against rapidly developing infrared search and tracking systems. Pigment materials developed for coatings applied to aircraft surfaces based on materials science and engineering in line with electromagnetic principles play a crucial role in this regard. Although low-observable structures were obtained in the 8-14 µm infrared wavelength range in particle studies, radar a...
Automatic Mesh Generator Integrated Missile Design Tool Development Köseömür, Oğuz Ziya; Baran, Özgür Uğraş (null; 2019-09-20) In this study, a software that is utilized after the pre-design phase of the missile design is presented. This software consists of computational domain modeller and multi-block structured mesh generator. Geometrical design variables of the missile used in the software are based on Missile DATCOM and the presented software eliminates the time consumed between the preliminary design and the CFD analysis by automating the computational domain generation. In order to model the different orientations of the fin...

Citation Formats

T. M. Bayık, “Automatic target recognition in infrared imagery,” M.S. - Master of Science, Middle East Technical University, 2004.