Enhancing Disaster Response Efforts with YOLOv8-based Human Detection in Mobile Robotics | ||
| International Integrated Intelligent Systems | ||
| Article 5, Volume 2, Issue 1, January 2025 PDF (370.15 K) | ||
| Document Type: Original Article | ||
| DOI: 10.21608/iiis.2025.292458.1036 | ||
| Authors | ||
| khaled Alnabulseih* 1; Abd-EL-Rahman Abd-EL-Rehim1; Mohamed Badawi Badawi2; Rania Elgohary3 | ||
| 1Department of Artificial intelligence, Misr university for science and technology | ||
| 2Department of Artificial Intelligence, College of Information Technology, Misr University for Science and Technology (MUST), 6th of October City 12566, Egypt | ||
| 3Department of Information Systems, Faculty of Computer and Information Sciences, Ain Shams University, Cairo, Egypt | ||
| Abstract | ||
| In the aftermath of natural disasters, the swift detection of individuals trapped beneath debris is crucial for successful rescue operations. This paper presents a Mobile Controlled Robot with advanced human detection capabilities designed to expedite search and rescue missions, emphasizing the importance of rapid response to save lives. Utilizing a YOLOv8 model with 90% accuracy, the robot analyzes real-time images captured by a webcam to detect human forms and movements, triggering a buzzer alert to notify rescue teams upon identifying potential victims. The robot’s remote operation via a mobile interface enhances flexibility and adaptability in complex terrains, allowing rescue personnel to control it from a safe distance. Equipped with all-terrain wheels, obstacle-avoidance sensors, and a thermal imaging camera, the robot can navigate through rubble and confined spaces, even in low visibility conditions. The mobile interface provides real-time video feed and sensor data to the rescue team, enabling quick, informed decision-making. The robot’s modular design allows for easy upgrades and maintenance, making it a cost-effective long-term solution. Rigorous testing has demonstrated the system’s efficacy and reliability in accurately locating trapped individuals, offering a promising improvement in the efficiency and effectiveness of disaster response operations. | ||
| Keywords | ||
| Robotics; YOLO; Deep learning; Fire rescue | ||
|
Statistics Article View: 292 PDF Download: 265 |
||
