Autonomous Drones Localization and Navigation based on Data Fusion from Images using Computer Vision Algorithms and integrating with IMU and GPS data.

• Grant number: 25/04939-7
• Support Opportunities: Scholarships in Brazil - Master
• Start date: September 01, 2025
• End date: August 31, 2027
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Fernando Santos Osório
• Grantee: Marcos Vinicius Alves da Rocha
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

This research project aims to study, propose and develop methods and algorithms for autonomous aerial navigation (drones), with self-localization, based on a Computer Vision System, with GPS/GNSS and IMU data fusion. We will consider data from Inertial Measurement Unit (IMU), including data from a digital compass, a barometer, and using satellite signals (GPS/GNSS). Data fusion techniques will be adopted in order to integrate the processed images (extracted information from images) with the GNSS and IMU data, improving the system robustness. The main focus of this project will be the Computer Vision System, which aims to recognize landmarks and control/maintain the pose - localization and orientation of the Drone (relative to the geographic north), based on the scene elements. The Inertial Measurement Unit (IMU) combines two main sensors, the accelerometer and the gyroscope, thus becoming an inertial navigation system; in addition to this, a magnetometer operating as a compass, and a barometer for altitude measurement, are also applied, constituting redundancies to assist the Computer Vision System, and helping to increase the accuracy of localization, pose, and navigation path following. This project also includes satellite signals (GPS/GNSS) with latitude, longitude and altitude (global coordinates) captured from different satellites systems with a GPS/GNSS receiver. In short, the project aims to implement an autonomous drone with localization and navigation systems for aerial applications, by combining three other systems, namely: computer vision system, satellite navigation system and inertial navigation system. (AU)