Machine Learning Models for Improved Tracking from Range-Doppler Map Images

TL;DR

This paper introduces machine learning models for target detection and uncertainty estimation in range-Doppler map images, significantly enhancing multi-target tracking performance in complex scenarios.

Contribution

It presents novel machine learning approaches specifically designed for target detection and uncertainty estimation in RDM images, improving GMTI radar tracking.

Findings

Enhanced tracking accuracy in multi-target scenarios

Significant performance improvements over traditional methods

Effective uncertainty estimation for better tracking robustness

Abstract

Statistical tracking filters depend on accurate target measurements and uncertainty estimates for good tracking performance. In this work, we propose novel machine learning models for target detection and uncertainty estimation in range-Doppler map (RDM) images for Ground Moving Target Indicator (GMTI) radars. We show that by using the outputs of these models, we can significantly improve the performance of a multiple hypothesis tracker for complex multi-target air-to-ground tracking scenarios.