딥 러닝 기반 작업자 개인보호구 착용 및 얼굴 신원 확인 시스템
Deep Learning-Based Worker Personal Protective Equipment and Face Identification System
0
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
산업현장에서 가장 많이 발생하는 안전사고 중 하나는 안전모, 안전고리, 안전화 등 개인보호구의 미착용으로 발생하는 사고이다. 이에 본 논문에서는 산업현장의 안전관리를 위한 작업자 개인보호구 착용 및 얼굴 신원 확인에 관한 연구를 수행하였다. 산업현장 작업자와 개인보호구 착용 이미지 및 영상 데이터 셋을 준비하고, 개인보호구 검출을 위한 YOLOv5s 모델과 얼굴 인식을 위한 FaceNet 모델을 적용하였다. 실험을 통해 작업자 개인보호구 검출 및 얼굴 인식에 대한 정확도, 정밀도, 재현도, 조화 평균, 얼굴쌍 비교 등 성능을 확인하였다. 본 논문은 작업자 영상에 의한 얼굴 인식과 개인보호구 검출로 작업자 신원과 개인보호구 착용 준수 여부를 동시에 확인할 수 있는 차별성이 있으며 딥 러닝 기반 작업자 개인보호구 착용 및 신원을 확인하였다.
Abstract
One of the most common safety accidents in industrial sites is accidents caused by not wearing personal protective equipment such as helmets, safety rings, and safety boots. According to domestic industrial accident analysis, 37.3% of all deaths occurred without a helmet on. Accident prevention systems in industrial sites require automated technology application. Recently, many efforts have been made to introduce an automated safety management method using image recognition technology based on computer vision and deep learning. Therefore, in this paper, a study was conducted on worker wearing personal protective equipment and face identification for safety management in industrial sites. An image data set of industrial site workers and personal protective equipment wearing was prepared, and a YOLOv5s model for personal protective equipment detection and a FaceNet model for face recognition were applied. Through the experiment, performance such as accuracy, precision, reproducibility, harmonic mean, and face pair comparison was confirmed for the detection of worker's personal protective equipment and face recognition. This paper is differentiated in that it is possible to simultaneously check the identity of the worker and compliance with the wearing of personal protective equipment through face recognition and personal protective equipment detection by the worker image, and deep learning-based worker wearing and identity of personal protective equipment was confirmed.
참고문헌 (15)
- S. H. Jeung, "Improved system for establishing a culture to wear personal protective gear", Journal of the korea institute of construction safety, 2(1), pp.16~20 (2019)
- A. Krizhevsky, "ImageNet classification with deep convolutional neural networks", Advances in neural information processing systems, 25 (2012)
- C. H. Hwang, "Improving data quality using a deep learning network", Indonesian journal of electrical engineering and computer science, 20(1), pp.306~312 (2020)
- 이종원, "Deep Learning Document Analysis System Based on Keyword Frequency and Section Centrality Analysis", Journal of Information and Communication Convergence Engineering, 19(1), pp.48~53 (2021), 한국정보통신학회[DOI]
- S. Ren, "Faster r-cnn: towards real-time object detection with region proposal networks", Advances in neural information processing systems, 39, pp.1137~1149 (2017)
- C. H. Hwang, "Pine wilt disease spreading prevention system using semantic segmentation", International journal of electrical and computer engineering, 11(3), pp.2667~2674 (2021)
- J. Redmon, "You only look once: Unified, real-time object detection", Proceeding of IEEE conference on computer vision and pattern recognition(CVPR), pp.779~788 (2016)
- W. Liu, "Ssd:Single shot multibox detector", European conference on computer vision, (봄), pp.21~37 (2016)
- W. Deng, "Transform-invariant pca: a unified approach to fully automatic face alignment, representation, and recognition", IEEE transactions on pattern analysis and machine intelligence, 36(6), pp.1275~1284 (2013)
- Z. Matthew, "TVisualizing and understanding convolutional networks", European conference on computer vision, pp.818~833 (2014)
- F. Schroff, "Facenet: A unified embedding for face recognition and clustering", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.815~823 (2015)
- Q. Fang, "A deep learning-based method for detecting non-certified work on construction sites", Advanced Engineering Informatics, 35, pp.56~68 (2018)
- S. Y. Jeon, "A study on deep learning based personal protective equipment detection", Korea broadcasting and media engineering society summet conference, pp.650~651 (2020)
- 정형근, "딥러닝을 이용한 시스템식별에 관한 연구", 한국지식정보기술학회 논문지, 14(4), pp.359~368 (2019), 한국지식정보기술학회[DOI]
- 노시영, "YOLO 기반 나방 유충 탐지 모델의 연구", 한국지식정보기술학회 논문지, 16(6), pp.1185~1193 (2021), 한국지식정보기술학회[DOI]