Related Experiment Video
Updated: May 8, 2025

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
Published on: February 25, 2021
Enhanced YOLOv8 Ship Detection Empower Unmanned Surface Vehicles for Advanced Maritime Surveillance
Abdelilah Haijoub1, Anas Hatim2, Antonio Guerrero-Gonzalez3
1Engineering Sciences Laboratory, National School of Applied Sciences of Kenitra, Ibn Tofail University, Kenitra 14000, Morocco.
This study introduces an AI system for detecting and tracking unmanned surface vehicles (USVs) using an enhanced YOLOv8 model. The system achieves high accuracy and speed with low energy consumption, advancing maritime surveillance capabilities.
Area of Science:
- Computer Science
- Robotics
- Maritime Technology
Background:
- Maritime surveillance is evolving with AI and machine learning integration into Unmanned Surface Vehicles (USVs).
- Existing systems require optimization for real-time performance and energy efficiency in maritime environments.
Purpose of the Study:
- To develop and evaluate an AI-powered system for detecting and tracking USVs in maritime settings.
- To optimize the system for real-time operation and energy efficiency on embedded platforms.
Main Methods:
- An enhanced YOLOv8 model was fine-tuned for maritime surveillance tasks.
- The AI system was deployed on an NVIDIA Jetson TX2 platform with an optimized architecture and perception module.
Main Results:
- The system achieved a mean Average Precision (mAP) of 0.99 for detection accuracy.
- Operational speed reached 17.99 FPS with an energy consumption of 5.61 joules.
Conclusions:
- The developed AI system offers a significant advancement in maritime safety, security, and environmental monitoring.
- The balance of high accuracy, processing speed, and energy efficiency demonstrates the system's practical viability for real-world applications.
More Related Videos
09:22Quantitatively Measuring In situ Flows using a Self-Contained Underwater Velocimetry Apparatus SCUVA
Published on: October 31, 2011
07:43Methods for Image-based Surveys of Benthic Macroinvertebrates and Their Habitat Exemplified by the Drop Camera Survey for the Atlantic Sea Scallop
Published on: July 2, 2018
Related Concept Videos
Buoyancy and Stability for Submerged and Floating Bodies
Types of Global Positioning System Surveys
Buoyancy
Uniform Depth Channel Flow
Drift Velocity
Uniform Depth Channel Flow: Problem Solving