Deteksi Alat Pelindung Diri Menggunakan Metode YOLO dan Faster R-CNN

Jonathan Adiwibowo (Program Studi Informatika)
Kartika Gunadi (Program Studi Informatika)
Endang Setyati (Program Studi Teknologi Informasi)

Jurnal Infra
Vol 8, No 2 (2020)

In order to ensure security and safety measures in industrial zones or any other areas that needed to use personal protective equipment are an important matter. Many workers keep disregarding and violating the rule to use personal protective equipment in the area. Therefore, a program was created that could help supervising the workers to use personal protective equipment. In this study an experiment will be conducted to help recognize the characteristics of personal protective equipment, especially in head. In recent studies that have been carried out Rifki Dita Wahyu Pradana, et. Al. using CNN to produce an overall accuracy 80%. This study will be using 2 methods, You Only Look Once and Faster Region-Convolutional Neural Network (Faster R-CNN). The YOLO method is used to find regions of worker’s head while Faster R-CNN method is used to classify personal protective equipment used by worker. The results of the Faster R-CNN classification will be calculated using a confusion matrix in order to get the accuracy of the correct prediction. The results from this study will identify workers using personal protective equipment in the video. Average accuracy that has been obtained is 93.61%.