{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T09:53:54Z","timestamp":1780566834685,"version":"3.54.1"},"reference-count":44,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T00:00:00Z","timestamp":1621209600000},"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 existing deep learning-based Personal Protective Equipment (PPE) detectors can only detect limited types of PPE and their performance needs to be improved, particularly for their deployment on real construction sites. This paper introduces an approach to train and evaluate eight deep learning detectors, for real application purposes, based on You Only Look Once (YOLO) architectures for six classes, including helmets with four colours, person, and vest. Meanwhile, a dedicated high-quality dataset, CHV, consisting of 1330 images, is constructed by considering real construction site background, different gestures, varied angles and distances, and multi PPE classes. The comparison result among the eight models shows that YOLO v5x has the best mAP (86.55%), and YOLO v5s has the fastest speed (52 FPS) on GPU. The detection accuracy of helmet classes on blurred faces decreases by 7%, while there is no effect on other person and vest classes. And the proposed detectors trained on the CHV dataset have a superior performance compared to other deep learning approaches on the same datasets. The novel multiclass CHV dataset is open for public use.<\/jats:p>","DOI":"10.3390\/s21103478","type":"journal-article","created":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T05:45:13Z","timestamp":1621230313000},"page":"3478","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":198,"title":["Fast Personal Protective Equipment Detection for Real Construction Sites Using Deep Learning Approaches"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1365-9846","authenticated-orcid":false,"given":"Zijian","family":"Wang","sequence":"first","affiliation":[{"name":"School of Civil Engineering, Central South University, Changsha 410075, China"},{"name":"School of Aerospace, Transport and Manufacturing, Cranfield University, Bedfordshire MK43 0AL, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimin","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Civil Engineering, Central South University, Changsha 410075, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0674-3123","authenticated-orcid":false,"given":"Lichao","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Aerospace, Transport and Manufacturing, Cranfield University, Bedfordshire MK43 0AL, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arjun","family":"Thirunavukarasu","sequence":"additional","affiliation":[{"name":"BAM Nuttall, St James House, Knoll Road, Camberley GU15 3XW, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3079-7773","authenticated-orcid":false,"given":"Colin","family":"Evison","sequence":"additional","affiliation":[{"name":"BAM Nuttall, St James House, Knoll Road, Camberley GU15 3XW, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2383-5724","authenticated-orcid":false,"given":"Yifan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Aerospace, Transport and Manufacturing, Cranfield University, Bedfordshire MK43 0AL, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,17]]},"reference":[{"key":"ref_1","unstructured":"U.S. Bureau of Labor Statistics (2020, May 10). Industries at A Glance: Retail, Available online: https:\/\/www.bls.gov\/iag\/tgs\/iag23.htm."},{"key":"ref_2","unstructured":"Ministry of Housing and Urban-Rural Development (2020, May 10). The Report of Fatal Accidents in China\u2019s Building Construction Activities in 2018, Available online: http:\/\/www.mohurd.gov.cn\/wjfb\/201903\/t20190326_239913.html."},{"key":"ref_3","unstructured":"Fatal Injuries in Great Britain (2020, June 10). Technical Report, Available online: https:\/\/www.hse.gov.uk\/statistics\/fatals.htm."},{"key":"ref_4","unstructured":"OSHA (2020, May 10). Worker Safety Series Construction, Available online: https:\/\/www.osha.gov\/Publications\/OSHA3252\/3252.html."},{"key":"ref_5","unstructured":"Hume, A., and Mills, N.J. (1995). Industrial head injuries and the performance of the helmets. Biomech. Impacts, 217\u2013231. Available online: https:\/\/doi.org\/http:\/\/www.ircobi.org\/wordpress\/downloads\/irc1995\/pdf_files\/1995_15.pdf."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.aap.2014.08.011","article-title":"The effect of hardhats on head and neck response to vertical impacts from large construction objects","volume":"73","author":"Suderman","year":"2014","journal-title":"Accid. Anal. Prev."},{"key":"ref_7","unstructured":"Safety Helmet Colours (2020, June 05). Technical Report, Available online: https:\/\/assets.publishing.service.gov.uk\/government\/uploads\/system\/uploads\/attachment_data\/file\/573103\/B31_Safety_Helmet_Colours_Sept_16_V2.pdf."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.autcon.2015.09.009","article-title":"Workforce location tracking to model, visualize and analyze workspace requirements in building information models for construction safety planning","volume":"60","author":"Zhang","year":"2015","journal-title":"Autom. Constr."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.autcon.2013.08.009","article-title":"Mobile passive Radio Frequency Identification (RFID) portal for automated and rapid control of Personal Protective Equipment (PPE) on construction sites","volume":"36","author":"Kelm","year":"2013","journal-title":"Autom. Constr."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1061\/(ASCE)CO.1943-7862.0001629","article-title":"Real-Time Alarming, Monitoring, and Locating for Non-Hard-Hat Use in Construction","volume":"145","author":"Zhang","year":"2019","journal-title":"J. Constr. Eng. Manag."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/j.aei.2015.02.001","article-title":"Computer vision techniques for construction safety and health monitoring","volume":"29","author":"Seo","year":"2015","journal-title":"Adv. Eng. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.autcon.2013.05.001","article-title":"A vision-based motion capture and recognition framework for behavior-based safety management","volume":"35","author":"Han","year":"2013","journal-title":"Autom. Constr."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"04014004","DOI":"10.1061\/(ASCE)CP.1943-5487.0000282","article-title":"Modeling tower crane operator visibility to minimize the risk of limited situational awareness","volume":"28","author":"Cheng","year":"2014","journal-title":"J. Comput. Civ. Eng."},{"key":"ref_14","unstructured":"Zhu, Z., Park, M.W., and Elsafty, N. (2015, January 8\u201310). Automated monitoring of hardhats wearing for onsite safety enhancement. Proceedings of the 11th Construction Specialty Conference, Vancouver, UK."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Rubaiyat, A.H., Toma, T.T., Kalantari-Khandani, M., Rahman, S.A., Chen, L., Ye, Y., and Pan, C.S. (2016, January 13\u201316). Automatic detection of helmet uses for construction safety. Proceedings of the 2016 IEEE International Conference on Web Intelligence Workshops, Omaha, NE, USA.","DOI":"10.1109\/WIW.2016.045"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2015\/721380","article-title":"Hard-Hat Detection for Construction Safety Visualization","volume":"2015","author":"Shrestha","year":"2015","journal-title":"J. Constr. Eng."},{"key":"ref_17","unstructured":"Du, S., Shehata, M., and Badawy, W. (2011, January 11\u201313). Hard hat detection in video sequences based on face features, motion and color information. Proceedings of the 2011 3rd International Conference on Computer Research and Development, Shanghai, China."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Nath, N.D., and Behzadan, A.H. (2020). Deep Learning Detection of Personal Protective Equipment to Maintain Safety Compliance on Construction Sites. Construction Research Congress 2020: Computer Applications, American Society of Civil Engineers.","DOI":"10.1061\/9780784482865.020"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wu, H., and Zhao, J. (2018). Automated Visual Helmet Identification Based on Deep Convolutional Neural Networks, Elsevier Masson SAS.","DOI":"10.1016\/B978-0-444-64241-7.50378-5"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Pradana, R.D.W., Adhitya, R.Y., Syai\u2019in, M., Sudibyo, R.M., Abiyoga, D.R.A., Jami\u2019in, M.A., Subiyanto, L., Herijono, B., Wahidin, A., and Budianto, A. (2019, January 16\u201318). MIdentification System of Personal Protective Equipment Using Convolutional Neural Network (CNN) Method. Proceedings of the 2019 IEEE International Symposium on Electronics and Smart Devices, Rourkela, India.","DOI":"10.1109\/ISESD.2019.8909629"},{"key":"ref_21","unstructured":"Akbarzadeh, M., Zhu, Z., and Hammad, A. (2020). Nested Network for Detecting PPE on Large Construction Sites Based on Frame Segmentation. Creative Construction e-Conference 2020, Budapest University of Technology and Economics."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102894","DOI":"10.1016\/j.autcon.2019.102894","article-title":"Automatic detection of hardhats worn by construction personnel: A deep learning approach and benchmark dataset","volume":"106","author":"Wu","year":"2019","journal-title":"Autom. Constr."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, S., and Demachi, K. (2020). A Vision-Based Approach for Ensuring Proper Use of Personal Protective Equipment (PPE) in Decommissioning of Fukushima Daiichi Nuclear Power Station. Appl. Sci., 10.","DOI":"10.3390\/app10155129"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Xie, Z., Liu, H., Li, Z., and He, Y. (2018, January 14\u201316). A convolutional neural network based approach towards real-time hard hat detection. Proceedings of the 2018 IEEE International Conference on Progress in Informatics and Computing, Suzhou, China.","DOI":"10.1109\/PIC.2018.8706269"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Redmon, J., and Farhadi, A. (2017, January 21\u201326). YOLO9000: Better, faster, stronger. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref_27","unstructured":"Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"ref_28","unstructured":"Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv."},{"key":"ref_29","unstructured":"Ultralytics (2020, May 15). yolov5. Available online: https:\/\/github.com\/ultralytics\/yolov5."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Mark Liao, H.Y., Wu, Y.H., Chen, P.Y., Hsieh, J.W., and Yeh, I.H. (2020, January 14\u201319). CSPNet: A New Backbone that can Enhance Learning Capability of CNN. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref_31","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Advances in Neural Information Processing Systems 32, Curran Associates, Inc."},{"key":"ref_32","unstructured":"njvisionpower (2020, May 10). Safety-Helmet-Wearing-Dataset. Available online: https:\/\/github.com\/njvisionpower\/Safety-Helmet-Wearing-Dataset."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Qipeng, D., Ping, K., Li, F., He, M., and Yu, G. (2020, January 18\u201320). Method of Safety Helmet Wearing Detection based on Key-Point Estimation without Anchor. Proceedings of the 2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), Chengdu, China.","DOI":"10.1109\/ICCWAMTIP51612.2020.9317480"},{"key":"ref_34","unstructured":"Tzutalin (2020, May 20). LabelImg. Available online: https:\/\/github.com\/tzutalin\/labelImg."},{"key":"ref_35","unstructured":"Alexey, A.B. (2020, May 10). Darknet. Available online: https:\/\/github.com\/AlexeyAB\/darknet#how-to-train-to-detect-your-custom-objects."},{"key":"ref_36","unstructured":"Viola, P., and Jones, M. (2001, January 8\u201314). Rapid object detection using a boosted cascade of simple features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, HI, USA."},{"key":"ref_37","unstructured":"Dalal, N., and Triggs, B. (2005, January 20\u201326). Histograms of oriented gradients for human detection. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA."},{"key":"ref_38","unstructured":"Wang, H., Li, Z., Ji, X., and Wang, Y. (2017). Face r-cnn. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Chen, W., Huang, H., Peng, S., Zhou, C., and Zhang, C. (2020). YOLO-face: A real-time face detector. Vis. Comput., 1\u20139.","DOI":"10.1007\/s00371-020-01831-7"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Padilla, R., Netto, S.L., and da Silva, E.A.B. (2020, January 4\u20136). A Survey on Performance Metrics for Object-Detection Algorithms. Proceedings of the 2020 International Conference on Systems, Signals and Image Processing, Marrakech, Morocco.","DOI":"10.1109\/IWSSIP48289.2020.9145130"},{"key":"ref_41","unstructured":"Rafaelpadilla (2020, May 30). Object Detection Metrics. Available online: https:\/\/github.com\/rafaelpadilla\/Object-Detection-Metrics."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"103085","DOI":"10.1016\/j.autcon.2020.103085","article-title":"Deep learning for site safety: Real-time detection of personal protective equipment","volume":"112","author":"Nath","year":"2020","journal-title":"Autom. Constr."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016). Ssd: Single shot multibox detector. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-46448-0_2"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/10\/3478\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:02:28Z","timestamp":1760162548000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/10\/3478"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,17]]},"references-count":44,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["s21103478"],"URL":"https:\/\/doi.org\/10.3390\/s21103478","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,17]]}}}