{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T09:45:39Z","timestamp":1792057539787,"version":"4.4.0"},"reference-count":31,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T00:00:00Z","timestamp":1762214400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The agricultural sector remains one of the most hazardous working environments, with viticulture posing particularly high risks due to repetitive manual tasks, pesticide exposure, and machinery operation. This study explores the potential of vision-based Artificial Intelligence (AI) systems to enhance occupational health and safety by evaluating their coherence with human expert assessments. A dataset of 203 annotated images, collected from 50 vineyards in Northern Italy, was analyzed across three domains: manual work activities, workplace environments, and agricultural machinery. Each image was independently assessed by safety professionals and an AI pipeline integrating convolutional neural networks, regulatory contextualization, and risk matrix evaluation. Agreement between AI and experts was quantified using weighted Cohen\u2019s Kappa, achieving values of 0.94\u20130.96, with overall classification error rates below 14%. Errors were primarily false negatives in machinery images, reflecting visual complexity and operational variability. Statistical analyses, including McNemar and Wilcoxon signed-rank tests, revealed no significant differences between AI and expert classifications. These findings suggest that AI can provide reliable, standardized risk detection while highlighting limitations such as reduced sensitivity in complex scenarios and the need for explainable models. Overall, integrating AI with complementary sensors and regulatory frameworks offers a credible path toward proactive, transparent, and preventive safety management in viticulture and potentially other high-risk agricultural sectors. Furthermore, vision-based AI systems inherently act as optical sensors capable of capturing and interpreting occupational risk conditions. Their integration with complementary sensor technologies\u2014such as inertial, environmental, and proximity sensors\u2014can enhance the precision and contextual awareness of automated safety assessments in viticulture.<\/jats:p>","DOI":"10.3390\/s25216749","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T17:06:06Z","timestamp":1762362366000},"page":"6749","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Preliminary Study of Vision-Based Artificial Intelligence Application to Evaluate Occupational Risks in Viticulture"],"prefix":"10.3390","volume":"25","author":[{"given":"Sirio R. S.","family":"Cividino","sequence":"first","affiliation":[{"name":"Department of Human Science and Quality of Life Promotion, San Raffaele Telematic University, Via Val Cannuta 247, 00166 Rome, Italy"},{"name":"Centro di Ricerca Studi dei Laghi, Via Vittor Pisani 8, 20100 Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0756-3821","authenticated-orcid":false,"given":"Alessio","family":"Cappelli","sequence":"additional","affiliation":[{"name":"Department of Human Science and Quality of Life Promotion, San Raffaele Telematic University, Via Val Cannuta 247, 00166 Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6877-9370","authenticated-orcid":false,"given":"Paolo","family":"Belluco","sequence":"additional","affiliation":[{"name":"LWT3, Via Caduti di Marcinelle 7, 20134 Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabiano","family":"Rinaldi","sequence":"additional","affiliation":[{"name":"Centro di Ricerca Studi dei Laghi, Via Vittor Pisani 8, 20100 Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lena","family":"Avramovic","sequence":"additional","affiliation":[{"name":"Centro di Ricerca Studi dei Laghi, Via Vittor Pisani 8, 20100 Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8800-1777","authenticated-orcid":false,"given":"Mauro","family":"Zaninelli","sequence":"additional","affiliation":[{"name":"Department of Human Science and Quality of Life Promotion, San Raffaele Telematic University, Via Val Cannuta 247, 00166 Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Izquierdo-Bueno, I., Moraga, J., Cantoral, J.M., Carb\u00fa, M., Garrido, C., and Gonz\u00e1lez-Rodr\u00edguez, V.E. (2024). Smart viniculture: Applying artificial intelligence for improved winemaking and risk management. Appl. Sci., 14.","DOI":"10.20944\/preprints202409.0580.v1"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"135855","DOI":"10.1109\/ACCESS.2019.2941566","article-title":"Safety + AI: A novel approach to update safety models using artificial intelligence","volume":"7","author":"Gheraibia","year":"2019","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"103138","DOI":"10.1016\/j.apergo.2020.103138","article-title":"A novel vision-based real-time method for evaluating postural risk factors associated with musculoskeletal disorders","volume":"87","author":"Li","year":"2020","journal-title":"Appl. Ergon."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"de Lavor, J.M., Pina, A.K.A., de Brito, C.A., de Almeida, W.B., Brusaca, L.A., Schmit, E.F.D., de Oliveira, A.B., da Silva, A.A.M., Magalh\u00e3es, P.A.F., and Locks, F. (2024). Objective measures of work and non-work physical behaviors associated with neck and back pain in viticulture workers. Appl. Sci., 14.","DOI":"10.3390\/app14219637"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4081\/jae.2009.1.1","article-title":"Safety in wine cellars: The situation in Friuli-Venezia Giulia, Italy","volume":"1","author":"Gubiani","year":"2009","journal-title":"J. Agric. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1539\/joh.10-0031-OA","article-title":"Biomechanical and Psychosocial Work Exposures and Musculoskeletal Symptoms among Vineyard Workers","volume":"53","author":"Bernard","year":"2011","journal-title":"J. Occup. Health"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Facchinetti, D., Santoro, S., Galli, L.E., and Pessina, D. (2021). Agricultural Tractor Roll-Over Related Fatalities in Italy: Results from a 12 Years Analysis. Sustainability, 13.","DOI":"10.3390\/su13084536"},{"key":"ref_8","unstructured":"Roos, E., and Selitski, O.H. (2023). Recommendations for Improving the Use of Risk Matrices in Coarse Risk Analyses, Lund University, Division of Risk Management and Societal Safety. Available online: https:\/\/www.risk.lth.se."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Leslie, D. (2019). Understanding Artificial Intelligence Ethics and Safety: A Guide for the Responsible Design and Implementation of AI Systems in the Public Sector, The Alan Turing Institute.","DOI":"10.2139\/ssrn.3403301"},{"key":"ref_10","unstructured":"Zhou, J., and Chen, F. (2021). Artificial Intelligence in Agriculture, Data Science Institute, University of Technology Sydney."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.aac.2022.10.001","article-title":"Understanding the potential applications of artificial intelligence in agriculture sector","volume":"2","author":"Javaid","year":"2023","journal-title":"Adv. Agrochem."},{"key":"ref_12","unstructured":"Johnson, C.W. (2018). The Increasing Risks of Risk Assessment: On the Rise of Artificial Intelligence and Non-Determinism in Safety-Critical Systems, Safety-Critical Systems Club, University of Glasgow."},{"key":"ref_13","unstructured":"Braband, J., and Sch\u00e4be, H. (2019). On Safety Assessment of Artificial Intelligence, Siemens Mobility GmbH and T\u00dcV Rheinland."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.ssci.2019.05.027","article-title":"Safety assessment in megaprojects using artificial intelligence","volume":"118","author":"Ayhan","year":"2019","journal-title":"Saf. Sci."},{"key":"ref_15","first-page":"7","article-title":"Precision Agriculture and Sustainability","volume":"80","author":"Bongiovanni","year":"2004","journal-title":"Agric. Syst."},{"key":"ref_16","first-page":"8133","article-title":"Automated Yield Prediction in Vineyard Using RGB Images Acquired by a UAV","volume":"59","author":"Berton","year":"2025","journal-title":"OENO One"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/s13634-021-00734-6","article-title":"A robot vision navigation method using deep learning in edge computing environment","volume":"2021","author":"Li","year":"2021","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"309","DOI":"10.3390\/automation4040018","article-title":"Autonomous Navigation and Crop Row Detection in Vineyards Using Machine Vision with 2D Camera","volume":"4","author":"Mendez","year":"2023","journal-title":"Automation"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"107034","DOI":"10.1016\/j.aap.2023.107034","article-title":"The usefulness of artificial intelligence for safety assessment of different transport modes","volume":"186","author":"Tselentis","year":"2023","journal-title":"Accid. Anal. Prev."},{"key":"ref_20","unstructured":"Lambert, M., and Grimbuhler, S. (2015, January 23\u201325). R\u00f4le de la perception de la s\u00e9curit\u00e9 dans la performance s\u00e9curitaire: \u00c9tude de cas des viticulteurs de la r\u00e9gion Bordelaise. Proceedings of the Actes du 50e Congr\u00e8s Int. de la Soci\u00e9t\u00e9 d\u2019Ergonomie de Langue Fran\u00e7aise, Paris, France."},{"key":"ref_21","first-page":"55","article-title":"Considering Severity of Safety-Critical System Outcomes in Risk Analysis: An Extension of Fault Tree Analysis","volume":"Volume 683","year":"2023","journal-title":"Advances in Safety Management and Human Factors, Proceedings of the AHFE 2023, Honolulu, HI, USA, 4\u20136 December 2023"},{"key":"ref_22","unstructured":"(2023). Establishing Risk Matrix Standard Criteria for Use in the Continuous Manufacturing of Pharmaceuticals. J. Pharm. Innov., 18, 45\u201356."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1007\/BF02295996","article-title":"Note on the sampling error of the difference between correlated proportions or percentages","volume":"12","author":"McNemar","year":"1947","journal-title":"Psychometrika"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual Comparisons by Ranking Methods","volume":"1","author":"Wilcoxon","year":"1945","journal-title":"Biom. Bull."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"107584","DOI":"10.1016\/j.compag.2022.107584","article-title":"Vision-based Navigation and Guidance for Agricultural Autonomous Vehicles and Robots: A Review","volume":"205","author":"Bai","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_26","unstructured":"(1998). Functional Safety of Electrical\/Electronic\/Programmable Electronic Safety-Related Systems (Standard No. IEC 61508)."},{"key":"ref_27","unstructured":"(Official Gazette of the Italian Republic, 2008). Legislative Decree No. 81 of 9 April 2008\u2014Consolidated Act on Occupational Health and Safety, Official Gazette of the Italian Republic, No. 101."},{"key":"ref_28","unstructured":"European Union (1989). Council Directive 89\/391\/EEC of 12 June 1989 on the Introduction of Measures to Encourage Improvements in the Safety and Health of Workers at Work. Off. J. Eur. Communities, 183, 1\u20138."},{"key":"ref_29","unstructured":"European Union (1989). Council Directive 89\/654\/EEC of 30 November 1989 Concerning the Minimum Safety and Health Requirements for the Workplace. Off. J. Eur. Communities, 393, 1\u201312."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kapse, S., Wu, R., and Thamsuwan, O. (2024). Addressing Ergonomic Challenges in Agriculture through AI-Enabled Posture Classification. Appl. Sci., 14.","DOI":"10.3390\/app14020525"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Bennetot","year":"2020","journal-title":"Inf. Fusion"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/21\/6749\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T17:07:18Z","timestamp":1762362438000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/21\/6749"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,4]]},"references-count":31,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["s25216749"],"URL":"https:\/\/doi.org\/10.3390\/s25216749","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,4]]}}}