Development of Anti-UAV System Using Visual Artificial Intelligence

Abstract

Unmanned Aerial Vehicles (UAV) was first developed as a tool for military purposes. Due to the rapid growth in technology, UAVs are now used in various applications including civil needs. Of course, there are consequences for this where UAVs can be misused by irresponsible parties. One example is the use of UAVs in airport fields which can disrupt the airport operations and possibly become a serious threat towards security and safety of flights in the airport. This paper will discuss the artificial intelligence (AI) modeling to detect UAVs. This AI modeling is the first step in designing counter unmanned aerial system (C-UAS). UAV detection will use deep learning using YOLOv4 (single-stage detection) for optimal detection speed and accuracy. There are a total of 500 image data processed and used in two AI modeling experiments in this study. Gaussian blur filter is used to create dataset variations so that the training can be processed more efficiently and the model can detect better. The results shows that the training dataset that has been processed with gaussian blur (filtered dataset) increases the AI model’s detection performance in rainy and clear conditions. Therefore, the model trained using filtered datasets is more suitable for use in detecting UAV objects in anti-UAV systems.