Radar Data Association for Multi-Object Tracking Using Neural Networks

• Grant number: 25/01070-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: April 01, 2025
• End date: March 31, 2026
• Field of knowledge: Engineering - Electrical Engineering
• Principal Investigator: Marcos Rogério Fernandes
• Grantee: Thaís Laura Anício Andrade
• Host Institution: Escola de Engenharia de São Carlos (EESC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

This scientific initiation proposal aims to develop a study on the problem of associating data generated by radars for multi-object tracking using neural networks. To achieve this, a two-dimensional multi-object trajectory simulator will be developed to generate synthetic signals for the training and validation of neural networks. Specifically, the simulator to be developed should be capable of generating synthetic signals that emulate real signals produced by a radar system, such as radial distance (range), radial velocity (range rate), and azimuth for multiple objects. Several modern applications involve, directly or indirectly, the use of radars and multi-object tracking. For instance, airports require radars to ensure the safe landing and takeoff of passenger or cargo aircraft; unmanned autonomous vehicles may use radar systems to navigate urban areas, among other applications. Additionally, in situations where border or protected space monitoring is necessary, tracking objects, people, or vehicles moving through the area is crucial. Thus, this project aims to contribute to the improvement of data association and multi-object tracking technologies that can be applied to critical modern-day technologies. Furthermore, this work will allow the candidate to engage in signal processing, dynamic system simulation, machine learning, and also develop and enhance practical programming skills.