Drone Detection and Tracking Using YOLO on Raspberry Pi

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science and Info Sys

Date of Award

1-10-2024

Abstract

The increasing popularity of unmanned aerial vehicles (drones) has led to a growing demand for effective drone detection and tracking systems. This research proposes a novel approach to address this need by developing an efficient and accurate drone detection and tracking system using the YOLO (You Only Look Once) object detection algorithm on the Raspberry Pi 4 platform (Raspberry Pi Foundation, n.d.). The primary aim of this study is to train a custom YOLO model specifically designed for drone detection. To achieve this, a diverse dataset of drone images will be collected and annotated with bounding box labels to facilitate model training. The YOLO model will be fine-tuned and optimized to ensure high accuracy in detecting drones. To enable real-time drone detection and tracking capabilities, the YOLO model will be further optimized for deployment on the Raspberry Pi 4, taking into account its limited computational resources and processing capabilities. The integration of the YOLO model with the Raspberry Pi 4 will be tested using live video feeds from a camera mounted on the Raspberry Pi 4, allowing for real-time monitoring and tracking of drones. The proposed research is expected to yield significant contributions to the field of drone technology and its applications in various domains, including surveillance, security, and autonomous navigation. By successfully implementing this drone detection and tracking system, the study aims to enhance the capabilities of unmanned aerial vehicles to autonomously track and detect other drones accurately.

Advisor

Mutlu Mete

Subject Categories

Computer Sciences | Physical Sciences and Mathematics

Link to Full Text

Share

COinS