Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Dataset Construction and Model Learning for Manufacturing Worker Safety Management

제조업 근로자 안전관리를 위한 데이터셋 구축과 모델 학습

  • Received : 2021.06.03
  • Accepted : 2021.06.22
  • Published : 2021.07.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, the "Act of Serious Disasters, etc" was enacted and institutional and social interest in safety accidents is increasing. In this paper, we analyze statistical data published by government agency on safety accidents that occur in manufacturing sites, and compare various object detection models based on deep learning to build a model to determine dangerous situations to reduce the occurrence of safety accidents. The data-set was directly constructed by collecting images from CCTVs at the manufacturing site, and the YOLO-v4, SSD, CenterNet models were used as training data and evaluation data for learning. As a result, the YOLO-v4 model obtained a value of 81% of mAP. It is meaningful to select a class in an industrial field and directly build a dataset to learn a model, and it is thought that it can be used as an initial research data for a system that determines a risk situation and infers it.

최근 "중대재해 등에 관한 법률"이 제정되고 안전사고에 관한 제도적, 사회적 관심이 높아지고 있다. 본 논문에서는 제조업 현장에서 발생한 안전사고에 대해 정부 기관에서 발간한 통계 자료를 분석하고, 안전사고 발생을 줄이기 위해 위험 상황을 판정하는 모델을 구축하기 위한 딥러닝 기반에 다양한 객체 탐지 모델을 학습시켜 비교 분석하였다. 제조업 현장에 있는 CCTV에서 영상을 수집하여 직접 데이터셋을 구축하였으며, YOLO-v4, SSD, CenterNet 모델에 훈련 데이터와 검증 데이터로 이를 활용하고 학습을 진행하였다. 그 결과 YOLO-v4 모델이 mAP 81%의 수치를 얻었다. 산업 현장에서 클래스를 선정하고 데이터셋을 직접 구축하여 모델 학습을 하는 데 의의가 있으며 이를 통해 위험 상황을 판정하고 이를 추론하는 시스템의 초기 연구자료로 활용할 수 있을 것으로 사료된다.

Keywords

Acknowledgement

This work was supported by the Korea Medical Device Development Fund grant funded by the Korea government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: P0015365)

References

  1. M. Jeong, C. Lee, and W. Cho, "Design of Integrated Safery System for Sealed Places," Journal of the Korea Institute of Information and Communication Engineering, vol. 23, no. 1, pp. 97-102, Jan. 2019. https://doi.org/10.6109/JKIICE.2019.23.1.97
  2. Z. Fang and P. Kim, "Comparison of Deep-Learning Algorithms for the Detection of Railroad Pedestrians," Journal of Information and Communication Convergence Engineering, vol. 18, no. 1, pp. 28-32, Mar. 2020. https://doi.org/10.6109/jicce.2020.18.1.28
  3. Ministry of Employment and Labor. Status of industrial accidents at the end of December 2020 [Internet]. Available: https://www.moel.go.kr/policy/policydata/view.do?bbs_seq=20210401122.
  4. D. Kim, J. Kong, J. Lim, and B. Sho, "A Study on Data Collection and Object Detection using Faster R-CNN for Application to Construction Site Safety," Journal of Korean Society of Hazard Mitigation, vol. 20, no. 1, pp. 119-126, Feb. 2020. https://doi.org/10.9798/kosham.2020.20.1.119
  5. S. Shim and S. Choi, "Development on Identification Algorithm of Risk Situation around Construction Vehicle using YOLO-v3," Journal of the Korea Academia-Industrial cooperation Society, vol. 20, no. 7, pp. 622-629, Jul. 2019. https://doi.org/10.5762/KAIS.2019.20.7.622
  6. Ministry of Land, Infrastructure and Transport. Realization of commercialization of smart construction core technology by 2025 [Internet]. Available: https://www.molit.go.kr/USR/NEWS/m_71/dtl.jsp?lcmspage=1&id=95083436.
  7. A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, "YOLOv4: Optimal Speed and Accuracy of Object Detection," arXiv preprint arXiv:2004.10934, 2020.
  8. S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, "Path Aggregation Network for Instance Segmentation," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8759-8768, 2018.
  9. W. Liu, D. Auguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, and A. C. Berg, "SSD: Single Shot MultiBox Detector," in European Conference on Computer Vision (ECCV), Springer, Cham, pp. 21-37, 2016.
  10. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, "MobileNetV2: Inverted Residuals and Linear Bottleneck," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4510-4520, 2018.
  11. X. Zhou, D. Wang, and P. Krahenbuhl, "Object as Points," arXiv preprint, arXiv:1904.07850, 2019.