Using AI-Enhanced UAVs to Detect and Size Marine Contaminations

Abstract

This paper explores the utilization of unmanned aerial vehicles, remote sensing, and machine vision to detect and estimate the size of contaminations in seawater. The study outlines the essential setups and adjustments to simulate this process in indoor and outdoor settings. The proposed system is designed to chart the optimal path for a quadrotor, utilized in these experiments, allowing it to navigate and pinpoint oil spill locations within the test arena. The drone successfully detects and accurately reports the oil spill's location across multiple trials. The results confirm the effectiveness of the proposed system in detecting and assessing oil spills, showcasing its potential in real-world applications.