REAL-TIME PERSONAL PROTECTIVE EQUIPMENT AND WAREHOUSE SAFETY DETECTION WITH DEEP LEARNING-BASED WORKPLACE CAMERA

Yıl 2024, Cilt: 11 Sayı: 24, 402 - 414, 31.12.2024

Abdil Karakan , Yüksel Oğuz

https://doi.org/10.54365/adyumbd.1470598

Öz

The majority of work accidents can be prevented with simple precautions. The most important of these is the personal protective equipment that employees must use. In the study, personal protective equipment and warehouse security were detected in real time with images taken from a workplace camera. For this purpose, a data set was created from images taken from the workplace camera. This data set consists of 6125 photographs. Additionally, grayscale, tilt addition, blurring, variability addition, noise addition, image brightness change, color vibrancy change, perspective change, resizing and position change have been added to the photographs. With these additions, the error that may occur due to any distortion that may occur from the camera is minimized. With the changes made to the photographs, the number of photographs forming the data set increased to 21079. The created data set was run on YOLOv8 architecture. In the study, 9 types of personal protective equipment and warehouse safety were determined: helmet, shoes, vest, on the road, not on the road, without vest, without shoes, apron and without helmet. As a result of the study, average stability was 97.3%, mAP was 93.8% and recall was 91.7%.

Anahtar Kelimeler

Deep learning, Personal protective equipment, Real-time object detection, YOLO architecture, Warehouse security.

DERIN ÖĞRENME TABANLI İŞYERI KAMERASI ILE GERÇEK ZAMANLI KIŞISEL KORUYUCU EKIPMAN VE DEPO GÜVENLIĞI TESPITI

Öz

İş kazalarının büyük bir çoğunluğu basit tedbirlerle önlenebilecek seviyededir. Bunların başında çalışanların kullanması gereken kişisel koruyucu ekipmanları gelmektedir. Yapılan çalışmada bir iş yeri kamerasından alınan görüntüler ile gerçek zamanlı olarak kişisel koruyucu ekipmanlarının tespiti gerçekleştirilmiştir. Bunun için iş yeri kamerasından alınan görüntülerden bir veri seti oluşturulmuştur. Bu veri seti 6125 tane fotoğraftan oluşmaktadır. Ayrıca fotoğraflar üzerinde gri tonlama, eğim eklenmesi, bulanıklaştırma, değişkenlik eklenmesi, gürültü eklenmesi, görüntü parlaklığı değişikliği, renk canlılığı değişikliği, perspektif değişikliği, boyutlandırma ve konum değişikliği eklenmiştir. Bu eklemeler ile kameradan meydana gelebilecek herhangi bir bozulmaya karşı oluşacak hata en aza indirilmiştir. Fotoğraflar üzerinde yapılan değişiklikler ile veri setini oluşturan fotoğraf sayısı 21079’a yükselmiştir. Oluşturulan veri seti YOLOv5 mimarisinde çalıştırılmıştır. Çalışmada kask, ayakkabı, yelek, yolda, yolda değil, yeleksiz, ayakkabısız, apron ve kasksız olmak üzere 9 çeşit kişisel koruyucu ekipmanın tespiti gerçekleştirilmiştir. Çalışma sonucunda ortalama doğruluk 97.3%, mAP 93.8% ve recall 91.7% gerçekleşmiştir.

Anahtar Kelimeler

Derin öğrenme, Kişisel koruyucu ekipman, Gerçek zamanlı nesne algılama, YOLO mimarisi, Depo güvenliği.

Kaynakça

• Ammad S, Alaloul W.S, Saad S, Qureshi A.H. Personal protective equipment (PPE) usage in construction projects: A scientometric approach. Journal of Building Engineering 2021, 35. http://dx.doi.org/10.1016/j.jobe.2020.102086
• MacFalane E, Chapman A, Benke G, Meaklim J, Sim M, MacNeil J. Training and other predictors of personal protective equipment use in Australian grain farmers using pesticides, Occup Environ Med. 2008; 65: 141-146. http://dx.doi.org/10.1136/oem.2007.034843
• Davidescu A.A. Work flexibility, job satisfaction, and job performance among Romanian employees–implications for sustainable human resource management. Sustainability 2020; 12: 6086. http://dx.doi.org/10.3390/su12156086.
• Greubel J, Higher risks when working unusual times? A cross-validation of the effects on safety, health, and work–life balance. International Archives of Occupational and Environmental Health 2016; 89: 8. http://dx.doi.org/10.1007/s00420- 016-1157-z.
• Haar J.M. Outcomes of work-life balance on job satisfaction, life satisfaction and mental health: A study across seven cultures. Journal of Vocational Behavior 2014; 85: 361–373. http://dx.doi.org/10.1016/j.jvb.2014.08.010.
• Delhi V.S.K, Sankarlal R, Thomas A. Detection of personal protective equipment (PPE) compliance on construction site using computer vision based deep learning techniques. Frontiers in Built Environment 2020; 6. http://dx.doiorg/10.3389/fbuil.2020.00136
• Tutak M. Evaluating differences in the level of working conditions between the european union member states using topsis and k-means methods. Decision Making Applications in Management and Engineering 2020; 5: 2. http://dx.doi.org/10.31181/dmame0305102022t, 2620–0104.
• Ammad S, Alaloul W.S, Saad S, Qureshi A.H. Personal protective equipment (PPE) usage in construction projects: A scientometric approach. Journal of Building Engineering 2021; 35. http://dx.doi.org/10.1016/j.jobe.2020.102086
• Li H, Luo X, Siebert J. Investigation of the causality patterns of non-helmet use behavior of construction workers. Automation in Construction 2017; 80: 95-103. http://dx.doi.org/10.1016/j.autcon.2017.02.006
• Goodrum P.M, McLaren M.A, Durfee A. The application of active radio frequency identification technology for tool tracking on construction job sites, Autom. Constr. 2006; 15: 292–302. https://doi.org/10.1016/j.autcon.2005.06.004.
• Jaselskis E, Haas C.T, Goodrum P.M. Construction transportation-related RFID research and applications. Transportation Research Circular Research Opportunities in Radio Frequency Identification Transportation Applications 2007; 9–24. https://doi.org/10.1007/978-3-031-36922-3_18
• Kelm A, Meins-Becker L.A, Platz D, Khazaee M.J, Costin A, Helmus M, Teizer J. Mobile passive Radio Frequency Identification (RFID) portal for automated and rapid control of Personal Protective Equipment (PPE) on construction sites. Automation in Construction2013; 36: 38–52. https://doi.org/10.101 6/j.autcon .2013.08.009.
• Barro-Torres S, Fernandez-Carames T.M, Perez-Iglesias H.J, Escudero C.J. Real-time personal protective equipment monitoring system, Computer Communications 2022; 36: 42–50. https://doi.org/10.1016/j.comcom.2012.01.005.
• Hayward S, Lopik K, West A. A holistic approach to health and safety monitoring: Framework and technology perspective. Internet of Things 2022; 20. https://doi.org/10.3390/fi16020040
• Wuand M.H, Zhao J. Automated visual helmet identification based on deep convolutional neural networks, Proceedings of the 13th International Symposium on Process Systems Engineering, San Diego, USA, 2018. https://doi.org/10.1016/B978-0-444-64241-7.50378-5.
• Rubaiyat A.H.M, Toma T.T, Kalantari-Khandani M, Rahman S.A, Chen L, Pan C.S. Automatic detection of helmet uses for construction safety, Proceedings of the 2016 IEEE ACM International Conference on Web Intelligence Workshops, Omaha, USA, 2016. https://doi.org/10.1109/WIW.2016.045.
• Fangbo Z., Huailin Z, Zhen N. Safety helmet detection based on YOLOv5, 2021 IEEE International Conference on Power Electronics, Computer Applications, Shenyang, China, 2021, pp. 6-11. https://doi.org/10.1109/ICPECA51329.2021.9362711.
• Fan W, Guoqing J, Mingyu G, Zhiwei H.E, Yuxiang Y. Helmet detection based on improved YOLO V3 deep model, 2019 IEEE 16th International Conference on Networking, Sensing and Control, Banff, Canada, 2019, pp. 363-368, https://doi.org/10.1109/ICNSC.2019.8743246.
• Madhuchhanda D, Oishila B. Sanjay Automated helmet detection for multiple motorcycle riders using CNN, 2019 IEEE Conference on Information and Communication Technology, Allahabad, India, 2019. https://doi.org/10.1109/CICT48419.2019.9066191.
• Wei J, Shiquan X, Zhen L, Yang Z, Hai M, Shujie L, Ye Y. Real-time automatic helmet detection of motorcyclists in urban traffic using improved YOLOv5 detector. IET Image Processing 2021, 15; 3623-3637. https://doi.org/10.1049/ipr2.12295.
• Shilei T, Gonglin L, Ziqiang J, Li H. Improved YOLOv5 network model and application in safety helmet detection, 2021 IEEE International Conference on Intelligence and Safety for Robotics, Tokoname, Japan, 2021. https://doi.org/10.1109/ISR50024.2021.9419561.
• Rui G, Yixuan M, Wanhong H. An improved helmet detection method for YOLOv3 on an unbalanced dataset, 2021 3rd International Conference on Advances in Computer Technology, Information Science and Communication, Shanghai, China, 2021. https://doi.org/10.1109/CTISC52352.2021.00066.
• Yange L, Han W, Zheng H, Jianling H, Weidong W. Deep learning-based safety helmet detection in engineering management based on convolutional neural networks. Hindawi Advances in Civil Engineering 2020. https://doi.org/10.1155/2020/9703560.
• Chang X, Liu M. Fault treeanalysis of unreasonably wearing helmets for builders, Journal of Jilin Jianzhu University 2018; 35: 67–71. https://doi.org/10.1088/1742-6596/1684/1/012013.
• Huang L, Fu M. He D. Jiang Z. Detection algorithm of safety helmet wearing based on deep learning, Concurr. Comput 2021; 33: 13. https://doi.org/10.1002/cpe.6234.
• Li Y, Wei H, Han Z, Huang J., Wang W. Deep learning-based safety helmet detection in engineering management based on convolutional neural networks, Advances in Civil Engineering, pp. 1–10, 2020. https://doi.org/10.1155/2020/9703560.
• Kamboj N, Powar N. Safety helmet detection in industrial environment using deep learning, 9th International Conference on Information Technology Convergence and Services, Vancouver, Canada, 2017. https://doi.org/10.5121/csit.2020.100518.
• Long X, Cui W, Zheng Z. Safety helmet wearing detection based on deep learning, 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference, Chengdu, China, 2019. https://doi.org/10.1109/ITNEC.2019.8729039.
• Zhou F, Zhao H, Nie Z. Safety helmet detection based on YOLOv5, 2021 IEEE International Conference on Power Electronics, Computer Applications. Shenyang, China, 2021. https://doi.org/10.1109/ICPECA51329.2021.9362711.
• Tan S, Lu G, Jiang Z, Huang L. Improved YOLOv5 network model and application in safety helmet detection, 2021 IEEE International Conference on Intelligence and Safety for Robotics, Nagoya, Japan, 2021. https://doi.org/10.1109/ISR50024.2021.9419561.
• Yung N.D.T, Wong W.K, Juwono F.H, Sim Z.A. Safety helmet detection using deep learning: Implementation and comparative study using YOLOv5, YOLOv6, and YOLOv7, International Conference on Green Energy, Computing and Sustainable Technology. Miri Sarawak, Malaysia, 2022. https://doi.org/10.1109/GECOST55694.2022.10010490.
• Korkmaz A, Ağdaş T. Deep learning-based automatic helmet detection system in construction site cameras. Bitlis Eren University Journal of Science 2023; 12: 773-782. https://doi.org/10.17798/bitlis.1297952.
• Türkdamar M.U, Taşyürek M, Öztürk C. Helmet dedectionon the construction site transfer learning and without transfer learning deep networks. Niğde Öner Halisdemir Journal of Engineering Science 2023; 12: 039-051. https://doi.org/10.289448/ngmuh.1173944.
• Wu F, Guoqing J, Mingyu G, Yuxiang Y. Helmet detection based on improved YOLOv3 Deep Model, 2019 IEEE 16th International Conference on Networking, Sensing and Control (ICNSC), Canada, 2019. https://doi.org/10.1109/ICNSC.2019.8743246
• Jia W, Xu S, Liang Z, Zhao Y, Min H, Li S, Yu Y. Real‐time automatic helmet detection of motorcyclists in urban traffic using improved YOLOv5 detector. IET Image Processing, 2021, 15(14), 3623-3637.https://doi.org/10.1049/ipr2.12295.
• Natha D. N, Behzadan A. H, Stephanie G. Deep learning for site safety: Real-time detection of personal protective equipment Automation in Construction, 2020, 112, 103085. https://doi.org/10.1016/j.autcon.2020.103085
• Wu F, Guoqing J, Mingyu G, Yuxiang Y. Helmet detection based on improved YOLOv3 Deep Model, 2019 IEEE 16th International Conference on Networking, Sensing and Control (ICNSC), Canada, 2019. https://doi.org/10.1109/ICNSC.2019.8743246