Use this URL to cite or link to this record in EThOS:
Title: Analysis of performance of automatic target recognition systems
Author: Marino, G.
ISNI:       0000 0004 2730 0062
Awarding Body: Cranfield University
Current Institution: Cranfield University
Date of Award: 2012
Availability of Full Text:
Access from EThOS:
Access from Institution:
An Automatic Target Recognition (ATR) system is a sensor which is usually able to recognize targets or objects based on gathered data. The application of automatic target recognition technology is a critical element of robotic warfare. ATR systems are used in unmanned aerial vehicles and cruise missiles. There are many systems which are able to collect data (e.g. radar sensor, electro-optic sensor, infra-red devices) which are commonly used to collect information and detect, recognise and classify potential targets. Despite significant effort during the last decades, some problems in ATR systems have not been solved yet. This Ph.D. tried to understand the variation of the information content into an ATR system and how to measure as well as how to preserve information when it passes through the processing chain because they have not been investigated properly yet. Moreover the investigation focused also on the definition of class-separability in ATR system and on the definition of the degree of separability. As a consequence, experiments have been performed for understanding how to assess the degree of class-separability and how the choice of the parameters of an ATR system can affect the final classifier performance (i.e. selecting the most reliable as well as the most information ii iii preserving ones). As results of the investigations of this thesis, some important results have been obtained: Definition of the class-separability and of the degree of classseparability (i.e. the requirements that a metric for class-separability has to satisfy); definition of a new metric for assessing the degree of classseparability; definition of the most important parameters which affect the classifier performance or reduce/increase the degree of class-separability (i.e. Signal to Clutter Ratio, Clutter models, effects of despeckling processing). Particularly the definition of metrics for assessing the presence of artefacts introduced by denoising algorithms, the ability of denoising algorithms in preserving geometrical features of potential targets, the suitability of current mathematical models at each stage of processing chain (especially for clutter models in radar systems) and the measurement of variation of information content through the processing chain are some of them most important issues which have been investigated.
Supervisor: Hughes, E. J. Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available