Ahmad Harun, - and Mustakim, - and Oktaf Brilian Kharisma, - (2023) IMPLEMENTASI DEEP LEARNING MENGGUNAKAN METODE YOU ONLY LOOK ONCE UNTUK MENDETEKSI ROKOK. JURNAL MEDIA INFORMATIKA BUDIDARMA, 7 (1). ISSN eISSN 2548-8368 - pISSN 2614-5278

Preview

Text TA Paper Ahmad Harun.pdf Download (9MB) | Preview

Abstract

Cigarettes are processed products from tobacco products which are used by burning and then smoked. Smoking activities are often found in everyday life, including in public infrastructure. The approach taken to prevent this activity generally uses manual information or human intervention. In terms of this approach, there are often many problems and failures due to the lack of manpower and supporting rules. Therefore, this study was structured with the aim of being able to detect smoking objects in real time using the You Only Look Once (YOLO) method. YOLO which is based on deep learning is very good at detecting objects, this model provides a single convolution neural network in assigning location and classification. So that in its application, YOLO is very fast in detecting and recognizing objects. This study conducted experiments on the training dataset in testing the YOLOv3, YOLOv3-Tiny and YOLOv4 models. The best training results were obtained in the YOLOv4 model with a composition of 80% training and 20% validation data sharing with a Mean Average Precision (mAP) of 92.54% and an F1-Score of 0.89. This study also conducted experiments on testing to detect cigarettes in real time, where the system can detect cigarettes up to a distance of 4.5 meters, and the highest detection accuracy is obtained at a distance of 1 meter, namely 99.03%.

Actions (login required)

View Item