A Robust Real-time Component for Personal Protective Equipment Detection in an Industrial Setting. Torres, P., Davys, A., Silva, T., Schirmer, L., Kuramoto, A., Itagyba, B., Salgado, C., Comandulli, S., Ventura, P., Fialho, L., Fischer, M., Kalinowski, M., Barbosa, S., & Lopes, H. In ICEIS 2021 - Proceedings of the 23rd International Conference on Enterprise Information Systems, Online Streaming, April 26-28, 2021, pages 693-700, 2021. Author version doi abstract bibtex 1 download In large industries, such as construction, metallurgy, and oil, workers are continually exposed to various hazards in their workplace. Accordingly to the International Labor Organization (ILO), there are 340 million occupational accidents annually. Personal Protective Equipment (PPE) is used to ensure the essential protection of workers’ health and safety. There is a great effort to ensure that these types of equipment are used properly. In such an environment, it is common to have closed-circuit television (CCTV) cameras to monitor workers, as those can be used to verify the PPE’s proper usage. Some works address this problem using CCTV images; however, they frequently can not deal with multiples safe equipment usage detection and others even skip the verification phase, making only the detection. In this paper, we propose a novel cognitive safety analysis component for a monitoring system. This component acts to detect the proper usage of PPE’s in real-time using data stream from regular CCTV cameras. We built the system component based on the top of state-of-art deep learning techniques for object detection. The methodology is robust with consistent and promising results for Mean Average Precision (80.19% mAP) and can act in real-time (80 FPS).
@inproceedings{TorresDSSKISCVF21,
author = {Pedro Torres and
Andre Davys and
Thuener Silva and
Luiz Schirmer and
Andre Kuramoto and
Bruno Itagyba and
Cristiane Salgado and
Sidney Comandulli and
Patricia Ventura and
Leonardo Fialho and
Marinho Fischer and
Marcos Kalinowski and
Simone Barbosa and
Helio Lopes},
title = {A Robust Real-time Component for Personal Protective Equipment Detection in an Industrial Setting},
abstract = {In large industries, such as construction, metallurgy, and oil, workers are continually exposed to various hazards in their workplace. Accordingly to the International Labor Organization (ILO), there are 340 million occupational accidents annually. Personal Protective Equipment (PPE) is used to ensure the essential protection of workers’ health and safety. There is a great effort to ensure that these types of equipment are used properly. In such an environment, it is common to have closed-circuit television (CCTV) cameras to monitor workers, as those can be used to verify the PPE’s proper usage. Some works address this problem using CCTV images; however, they frequently can not deal with multiples safe equipment usage detection and others even skip the verification phase, making only the detection. In this paper, we propose a novel cognitive safety analysis component for a monitoring system. This component acts to detect the proper usage of PPE’s in real-time using data stream from regular CCTV cameras. We built the system component based on the top of state-of-art deep learning techniques for object detection. The methodology is robust with consistent and promising results for Mean Average Precision (80.19% mAP) and can act in real-time (80 FPS).},
booktitle = {{ICEIS} 2021 - Proceedings of the 23rd International Conference on Enterprise Information Systems, Online Streaming, April 26-28,
2021},
pages = {693-700},
note = {},
year = {2021},
urlAuthor_version = {http://www.inf.puc-rio.br/~kalinowski/publications/TorresDSSKISCVF21.pdf},
doi = {10.5220/0010452606930700},
}
Downloads: 1
{"_id":"2JeeET9aJJ5Eh8N4B","bibbaseid":"torres-davys-silva-schirmer-kuramoto-itagyba-salgado-comandulli-etal-arobustrealtimecomponentforpersonalprotectiveequipmentdetectioninanindustrialsetting-2021","author_short":["Torres, P.","Davys, A.","Silva, T.","Schirmer, L.","Kuramoto, A.","Itagyba, B.","Salgado, C.","Comandulli, S.","Ventura, P.","Fialho, L.","Fischer, M.","Kalinowski, M.","Barbosa, S.","Lopes, H."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Pedro"],"propositions":[],"lastnames":["Torres"],"suffixes":[]},{"firstnames":["Andre"],"propositions":[],"lastnames":["Davys"],"suffixes":[]},{"firstnames":["Thuener"],"propositions":[],"lastnames":["Silva"],"suffixes":[]},{"firstnames":["Luiz"],"propositions":[],"lastnames":["Schirmer"],"suffixes":[]},{"firstnames":["Andre"],"propositions":[],"lastnames":["Kuramoto"],"suffixes":[]},{"firstnames":["Bruno"],"propositions":[],"lastnames":["Itagyba"],"suffixes":[]},{"firstnames":["Cristiane"],"propositions":[],"lastnames":["Salgado"],"suffixes":[]},{"firstnames":["Sidney"],"propositions":[],"lastnames":["Comandulli"],"suffixes":[]},{"firstnames":["Patricia"],"propositions":[],"lastnames":["Ventura"],"suffixes":[]},{"firstnames":["Leonardo"],"propositions":[],"lastnames":["Fialho"],"suffixes":[]},{"firstnames":["Marinho"],"propositions":[],"lastnames":["Fischer"],"suffixes":[]},{"firstnames":["Marcos"],"propositions":[],"lastnames":["Kalinowski"],"suffixes":[]},{"firstnames":["Simone"],"propositions":[],"lastnames":["Barbosa"],"suffixes":[]},{"firstnames":["Helio"],"propositions":[],"lastnames":["Lopes"],"suffixes":[]}],"title":"A Robust Real-time Component for Personal Protective Equipment Detection in an Industrial Setting","abstract":"In large industries, such as construction, metallurgy, and oil, workers are continually exposed to various hazards in their workplace. Accordingly to the International Labor Organization (ILO), there are 340 million occupational accidents annually. Personal Protective Equipment (PPE) is used to ensure the essential protection of workers’ health and safety. There is a great effort to ensure that these types of equipment are used properly. In such an environment, it is common to have closed-circuit television (CCTV) cameras to monitor workers, as those can be used to verify the PPE’s proper usage. Some works address this problem using CCTV images; however, they frequently can not deal with multiples safe equipment usage detection and others even skip the verification phase, making only the detection. In this paper, we propose a novel cognitive safety analysis component for a monitoring system. This component acts to detect the proper usage of PPE’s in real-time using data stream from regular CCTV cameras. We built the system component based on the top of state-of-art deep learning techniques for object detection. The methodology is robust with consistent and promising results for Mean Average Precision (80.19% mAP) and can act in real-time (80 FPS).","booktitle":"ICEIS 2021 - Proceedings of the 23rd International Conference on Enterprise Information Systems, Online Streaming, April 26-28, 2021","pages":"693-700","note":"","year":"2021","urlauthor_version":"http://www.inf.puc-rio.br/~kalinowski/publications/TorresDSSKISCVF21.pdf","doi":"10.5220/0010452606930700","bibtex":"@inproceedings{TorresDSSKISCVF21,\r\n author = {Pedro Torres and\r\n Andre Davys and\r\n Thuener Silva and\r\n Luiz Schirmer and\r\n Andre Kuramoto and\r\n Bruno Itagyba and\r\n Cristiane Salgado and\r\n Sidney Comandulli and\r\n Patricia Ventura and\r\n Leonardo Fialho and\r\n Marinho Fischer and\r\n Marcos Kalinowski and\r\n Simone Barbosa and\r\n Helio Lopes},\r\n title = {A Robust Real-time Component for Personal Protective Equipment Detection in an Industrial Setting},\r\n abstract = {In large industries, such as construction, metallurgy, and oil, workers are continually exposed to various hazards in their workplace. Accordingly to the International Labor Organization (ILO), there are 340 million occupational accidents annually. Personal Protective Equipment (PPE) is used to ensure the essential protection of workers’ health and safety. There is a great effort to ensure that these types of equipment are used properly. In such an environment, it is common to have closed-circuit television (CCTV) cameras to monitor workers, as those can be used to verify the PPE’s proper usage. Some works address this problem using CCTV images; however, they frequently can not deal with multiples safe equipment usage detection and others even skip the verification phase, making only the detection. In this paper, we propose a novel cognitive safety analysis component for a monitoring system. This component acts to detect the proper usage of PPE’s in real-time using data stream from regular CCTV cameras. We built the system component based on the top of state-of-art deep learning techniques for object detection. The methodology is robust with consistent and promising results for Mean Average Precision (80.19% mAP) and can act in real-time (80 FPS).},\r\n booktitle = {{ICEIS} 2021 - Proceedings of the 23rd International Conference on Enterprise Information Systems, Online Streaming, April 26-28,\r\n 2021},\r\n pages = {693-700},\r\n note = {}, \r\n year = {2021},\r\n urlAuthor_version = {http://www.inf.puc-rio.br/~kalinowski/publications/TorresDSSKISCVF21.pdf},\r\n doi = {10.5220/0010452606930700},\r\n}\r\n\r\n","author_short":["Torres, P.","Davys, A.","Silva, T.","Schirmer, L.","Kuramoto, A.","Itagyba, B.","Salgado, C.","Comandulli, S.","Ventura, P.","Fialho, L.","Fischer, M.","Kalinowski, M.","Barbosa, S.","Lopes, H."],"key":"TorresDSSKISCVF21","id":"TorresDSSKISCVF21","bibbaseid":"torres-davys-silva-schirmer-kuramoto-itagyba-salgado-comandulli-etal-arobustrealtimecomponentforpersonalprotectiveequipmentdetectioninanindustrialsetting-2021","role":"author","urls":{"Author version":"http://www.inf.puc-rio.br/~kalinowski/publications/TorresDSSKISCVF21.pdf"},"metadata":{"authorlinks":{}},"downloads":1,"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/f/2Gq6bNPQ845THHiMW/KalinowskiPapers.bib","dataSources":["vp6ff9ZJkhXGDuh9E","JhEx5LqjNuowkDTYw","FPdHx2YNMWt6KHbaS","oL8GbjE74fizfjkxY","Wbj3iHa4hGsGjEGJE","q7rgFjFgwoTSGkm3G","aKfxcyv7C9p9ytdpG","9pAzChfPy53GguqQk","B8Jierr7smZsGa7Jb","tvqztEQv84agmtPEB","FGDKYBjH9upApdKoL"],"keywords":[],"search_terms":["robust","real","time","component","personal","protective","equipment","detection","industrial","setting","torres","davys","silva","schirmer","kuramoto","itagyba","salgado","comandulli","ventura","fialho","fischer","kalinowski","barbosa","lopes"],"title":"A Robust Real-time Component for Personal Protective Equipment Detection in an Industrial Setting","year":2021,"downloads":1}