Non-Cooperative SAR Automatic Target Recognition Based on Scattering Centers Models.

Gustavo F Araujo,Renato Machado,Mats I Pettersson

doi:10.3390/s22031293

Abstract

This article proposes an Automatic Target Recognition (ATR) algorithm to classify non-cooperative targets in Synthetic Aperture Radar (SAR) images. The scarcity or nonexistence of measured SAR data demands that classification algorithms rely only on synthetic data for training purposes. Based on a model represented by the set of scattering centers extracted from purely synthetic data, the proposed algorithm generates hypotheses for the set of scattering centers extracted from the target under test belonging to each class. A Goodness of Fit test is considered to verify each hypothesis, where the Likelihood Ratio Test is modified by a scattering center-weighting function common to both the model and target. Some algorithm variations are assessed for scattering center extraction and hypothesis generation and verification. The proposed solution is the first model-based classification algorithm to address the recently released Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset on a synthetic training data basis. As a result, an accuracy of in a 10-target test within a class experiment under Standard Operating Conditions (SOCs) was obtained. The algorithm was also pioneered in testing the SAMPLE dataset in Extend Operating Conditions (EOCs), assuming noise contamination and different target configurations. The proposed algorithm was shown to be robust for SNRs greater than dB.

Highlights

This article proposes an Automatic Target Recognition (ATR) algorithm to classify noncooperative targets in Synthetic Aperture Radar (SAR) images
Synthetic Aperture Radar (SAR) appears to be an outstanding tool for producing high-resolution terrain images. Such sensors stand out for three reasons: (i) radar is an active sensor that provides its own illumination, which gives it the ability to operate in the dark; (ii) clouds and rain do not prevent the passage of electromagnetic waves at common radar operating frequencies; (iii) the radar energy backscattered by different materials allows a complementary detail for target discrimination [2]
As seen in Section 3.1.1, the Likelihood Ratio Test (LRT) stood out regarding PXS and Mean Square Error (MSE) variation

Summary

Introduction

This article proposes an Automatic Target Recognition (ATR) algorithm to classify noncooperative targets in Synthetic Aperture Radar (SAR) images. Since the 1990s, Automatic Target Recognition (ATR) has been a very active field of study, given the diversity of its applications and the growing development of remotesensing technologies [1] In this context, Synthetic Aperture Radar (SAR) appears to be an outstanding tool for producing high-resolution terrain images. Synthetic Aperture Radar (SAR) appears to be an outstanding tool for producing high-resolution terrain images Such sensors stand out for three reasons: (i) radar is an active sensor that provides its own illumination, which gives it the ability to operate in the dark; (ii) clouds and rain do not prevent the passage of electromagnetic waves at common radar operating frequencies; (iii) the radar energy backscattered by different materials allows a complementary detail for target discrimination [2]. SAR images are formed from the backscattering of electromagnetic microwaves and their interaction with the geometry and target material

Methods

Results

Discussion

Conclusion