Unmanned aerial vehicles (UAVs), or drones, have become indispensable in surveillance, search and rescue, and border security operations due to their versatility and ability to navigate challenging environments. Despite advancements in drone technology, real-time human detection remains a significant challenge, constrained by computational limitations, environmental variability, and the demand for high-speed processing. This paper introduces an innovative human detection system powered by the lightweight YOLOv3-tiny deep learning algorithm, integrated into a UAV platform for efficient and accurate detection. The system balances real-time performance with computational efficiency, making it well-suited for resource-limited environments. Extensive experiments validate its reliability across diverse scenarios, including military zone monitoring and border patrol operations. The results demonstrate its potential to address key challenges in UAV applications, offering a scalable and effective solution for enhancing autonomous security and surveillance systems.
YOLO-DRONE: Deep Learning Deployment for Drone Human Detection
13.04.2025
1149756 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Drone-YOLO: An Efficient Neural Network Method for Target Detection in Drone Images
DOAJ | 2023
|Drone Detection using YOLO and SSD A Comparative Study
IEEE | 2022
|