Personal Protective Equipment Detection System for Workers
Author(s): Dr. Yogendra V Pati1, Aditya Aher2, Dhanashri Dagade3, Madhumita Mahata4, Meghashree Pawar5
Affiliation: 1,2,3,4,5 Assoc.Prof, Computer Engineering, Marathwada Mitramandal�s Institute of Technology
Page No: 1-7-
Volume issue & Publishing Year: Volume 1 Issue 1,June 2024
Journal: International Journal of Modern Engineering and Management | IJMEM
ISSN NO: 3048-8230
DOI:
Abstract:
The safety and well-being of workers across various industries is of paramount importance, with Personal Protective Equipment (PPE) serving as a critical component in safeguarding their health. This abstract introduces a novel Personal Protective Equipment Detection System (PPEDS), designed to enhance workplace safety through advanced computer vision technology. The PPEDS is engineered to identify and monitor the correct usage of PPE among workers in real-time, thereby mitigating workplace accidents and ensuring adherence to safety regulations. Utilizing state-of-the-art image recognition algorithms and machine learning models, the PPEDS analyzes video feeds from strategically placed surveillance cameras to detect and track various types of PPE, such as helmets, safety goggles, face masks, gloves, reflective vests, and ear protection devices. The system is capable of determining whether workers are equipped with the appropriate PPE for their specific tasks and can generate alerts and notifications when non-compliance is detected. Key features of the PPEDS include real-time detection capabilities, customizable rule settings and alerts, comprehensive data logging and reporting, integration with existing safety systems, educational support for workers, and stringent privacy safeguards. By implementing the PPEDS, organizations can significantly reduce the incidence of workplace accidents, improve compliance with safety standards, and ultimately protect workers' lives in hazardous environments.
Keywords:
Image Recognition, PPE detection, industrial Safety, Real time detection.
Reference:
[1] C.-C. Hung, G. Ananthanarayanan, P. Bodik, L. Golubchik, M. Yu,P. Bahl, and M.Philipose,‘‘VideoEdge:Processingcamerastreamsusinghierarchicalclusters,’’inProc.IEEE/ACMSymp.EdgeComputing.(SEC),Oct.2018,pp.115–131. [2] L.Ciampi,C.Gennaro,F.Carrara,F.Falchi,C.Vairo,andG.Amato,‘‘Multi-cameravehiclecounting using edge-AI,’’ Expert Syst.Appl.,vol. 207,Nov.2022,Art.no.117929B. Smith, “An approach to graphs of linear forms (Unpublished work style),” unpublished. [3] R.Rajavel,S.K.Ravichandran,K.Harimoorthy,P.Nagappan,andK.R.Gobichettipalayam,‘‘IoT-basedsmarthealthcarevideosurveillancesystemusingedgecomputing,’’ J. Ambient Intel. Hum. Compute., vol. 13,no. 6, pp. 3195–3207, Jun.2022. [4] S.Liu,L.Liu,J.Tang,B.Yu,andW.Shi,‘‘Edgecomputingforautonomousdriving:Opportunitiesandchallenges,’’Proc.IEEE,vol.107,no.8,pp.1697–1716,Jun.2019. [5] A. Ndikumana, N. H. Tran, D. H. Kim, K. T. Kim, and C. S. Hong, ‘‘Deep learningbased caching for self-driving cars in multi-access edge computing,’’ IEEE Trans. Intel.Transp.Syst.,vol.22,no.5,pp.2862–2877,May2020. [6] The Potential of Artificial Intelligence for Tourism: A Review of the Literature by Buhalis and Foerste (2020) [7] The Impact of Artificial Intelligence on Tourist Behavior: A Case Study of Online Travel Agencies by Xiang et al.