Perbandingan Algoritma YOLOv4 dan YOLOv4-tiny dalam Deteksi Korban Bencana Alam: Comparison of YOLOv4 and YOLOv4-tiny Algorithms in the Detection of Victims of Natural Disasters

El hakim, Faris Abdi
Islam Mashuri, M Adamu

NU-JST
Vol 1 No 2 (2024): Published in November of 2024

Currently, artificial intelligence technology is widely discussed by researchers and this technology can help us in our daily lives. So that there are many applications in various fields, one of which is the topic in our paper namely the detection of victims of natural disasters. This is really needed by the rescue team in speeding up the search for victims of natural disasters because the tools currently used are only heavy equipment, so it takes a long time to search for victims of natural disasters. In this paper we will compare the speed of detection and accuracy in detecting victims of natural disasters using the You Only Look Once (YOLO) version 4 and YOLOv4-tiny algorithms. We train with the same parameters and dataset but with a different architecture. From the results, we get the YOLOv4-tiny algorithm is faster in detecting disaster victims but has an accuracy of 75% whereas the YOLOv4 algorithm takes longer to detect victims of natural disasters but has an accuracy of 54%.