• Pratik U. Haribhakta
• Shubham B. Raut
• Bramhadev G. Garud
• Prof.Priti Chorade

This research focuses on the instance segmentation of soft aspects on individuals, such clothing and personal protective equipment, in a risky industry. We propose to pre-train a mask segmentation network utilising soft biometric item classes from the Open Images V5 and DeepFashion2 datasets in order to recognise and segment personal protective equipment in the workplace. The preliminary results of our proposed model achieve a mean average precision with modest optimisation, which results in extremely effective segmentation of welding masks, high visibility vests, construction helmets, and ear protection in the workplace. The results of this research can be applied to improve workplace safety in high-risk industries by providing a way to ensure that personal protective equipment (PPE) is used appropriately while protecting employee privacy.

Computer Vision, Yolo, Personal Protective Equipment, Data Pre-processing, Safety Equipment, Object Recognition, Workplace Safety.

"PERSONAL PROTECTIVE EQUIPMENT DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 2, page no.g117-g119, February-2024, Available :http://www.jetir.org/papers/JETIR2402616.pdf

"PERSONAL PROTECTIVE EQUIPMENT DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 2, page no. ppg117-g119, February-2024, Available at : http://www.jetir.org/papers/JETIR2402616.pdf