Statistical target behaviour in SAR images

Blacknell, D.

doi:10.1049/ip-rsn:20000321

Cited by 2 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparison with the original image shows that a substantial reduction in the noise artefacts has been achieved. In particular, element (4,1) in the image array is highly corrupted in the original image but smoothing over aspect angles has allowed much of the underlying structure to be estimated. These results demonstrate the effectiveness of this conceptually simple target smoothing technique.…”

Section: Target Smoothingmentioning

confidence: 99%

See 1 more Smart Citation

<title>Feature analysis for SAR ATR</title>

Blacknell¹

2000

SAR Image Analysis, Modeling, and Techniques III

View full text Add to dashboard Cite

Feature-based automatic target recognition (ATR) discriminates between target classes on the basis of the values taken by certain target features. The conventional approach is to select the best features for a particular task from a large set of features which have been pre-defined on the basis of physical intuition. A simple feature might be target area whilst a more sophisticated feature might be some measure of fractal dimension. ATR performance will be influenced by the choice of features and by the accuracy with which the statistical behaviour of these features has been characterised. This paper describes a technique which can be used to determine statistical feature behaviour despite limited examples of target realisations. It also addresses the problem of feature choice by introducing a method for assessing the information carried by different features. This leads to a potential technique for adaptive feature generation. These ideas are illustrated by application to synthetic aperture radar (SAR) images of vehicles.

show abstract

Section: Target Smoothingmentioning

confidence: 99%

“…The feature values are simply measured for each realisation and the relevant statistical quantities calculated over the sample values [4].…”

Section: Noise Modelmentioning

confidence: 99%

<title>Feature analysis for SAR ATR</title>

Blacknell¹

2000

SAR Image Analysis, Modeling, and Techniques III

View full text Add to dashboard Cite

show abstract

“…The statistical behaviour of features can be measured, despite limited examples of target realisations, by means of Monte Carlo simulation using a target model based on a smooth underlying radar-cross section and a corrupting noise process. This technique has been described in [4] and so no further details will be given here.…”

Section: Introductionmentioning

confidence: 99%

<title>Adaptive design and characterization of features for SAR ATR</title>

Blacknell¹

2001

Algorithms for Synthetic Aperture Radar Imagery VIII

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) is an essential sensor for military surface surveillance because of its unique ability to operate day or night through weather, smoke and dust. Of particular importance is the problem of automatic target recognition (ATR) which aims to identify targets of military significance within radar images. The Defence Evaluation and Research Agency (DERA) of the UK has a substantial programme of research into ATR algorithms for SAR battlefield surveillance. This covers both feature-based techniques which are the subject of this paper and model-based techniques. Feature-based ATR discriminates between target classes on the basis of the values taken by certain target features. The conventional approach is to select the best features for a particular task from a large set of features which have been pre-defined on the basis of physical intuition. A simple feature might be target area whilst a more sophisticated feature might be some measure of fractal dimension. ATR performance will be influenced by the type of features used and by the accuracy with which the statistical behaviour of these features has been characterised. This paper describes a technique which can be used to determine statistical feature behaviour despite limited examples of target realisations. It also addresses the problem of feature choice by introducing a method for adaptive feature design which automatically recognises the information not already contained in the existing feature set and develops a feature to represent this missing information. These ideas are illustrated by application to synthetic aperture radar (SAR) images of vehicles.

show abstract

Statistical target behaviour in SAR images

Cited by 2 publications

References 4 publications

<title>Feature analysis for SAR ATR</title>

<title>Feature analysis for SAR ATR</title>

<title>Adaptive design and characterization of features for SAR ATR</title>

Contact Info

Product

Resources

About