Machine Learning Models for Improved Tracking from Range-Doppler Map Images
This work addresses tracking challenges in radar systems, specifically for air-to-ground scenarios, but appears incremental as it builds on existing tracking methods with new machine learning components.
The paper tackled the problem of improving tracking performance for Ground Moving Target Indicator radars by proposing novel machine learning models for target detection and uncertainty estimation in range-Doppler map images, resulting in significant performance gains for a multiple hypothesis tracker in complex multi-target air-to-ground scenarios.
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.