Unmanned Aerial Vehicles (UAVs), commonly known as drones, have emerged as pivotal tools in various fields due to their ability to cover vast areas swiftly and efficiently. This research focuses on the utilization of UAVs in the domain of surveillance, particularly for reconnaissance missions in military applications. The primary advantage of UAVs lies in their capacity to gather strategic intelligence without exposing human lives to potential risks. In military scenarios, UAVs play a crucial role in collecting data on opponent activities, with a specific emphasis on hostile vehicle detection. One of the primary challenges in implementing object detection on drones is the acquisition of diverse and representative datasets. This paper introduces a novel algorithm designed to automate the process of dataset collection and subsequent machine learning model training. The proposed algorithm aims to enable Unmanned Aerial Vehicles to autonomously learn and adapt to variations in hostile vehicle appearances, enhancing the accuracy and robustness of the detection system.
YOLO-Based Approach for Hostile Vehicle Identification Using Automated Dataset
19.12.2024
560914 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Enhanced Vehicle Plate Identification using YOLO
IEEE | 2022
|Interlocking hostile signal identification method and system
Europäisches Patentamt | 2024
|