The AI-powered Worker Safety Gear Detection System which employs real- time monitoring to verify adherence to workplace safety regulations. Using computer vision and deep learning algorithms, the system engages in automatic detection of adequate Personal Protective Equipment (PPE) such as helmets, vests and gloves at worksites. In entry points, AI-powered cameras inspect workers to ensure compliance and permit or deny access based on detection results. When inside, zone-wise surveillance constantly tracks workers in riskprone places to catch safety infractions. When a violation is detected, the system issues real-time notices through automated speaker announcements alerting workers and supervisors. The local server processes the video feeds through the YOLOv8 deep learning model, enabling fast detections without the need for cloud services. Furthermore, violations recorded are stored in a single central database to provide informative reports to reading officers on compliance and risk management. By incorporating AI-driven automation, this system decreases manual oversight, improves the accuracy of safety enforcement, and promotes a safe and compliant industrial workspace. In the long run, this forward-thinking method reduces workplace accidents, enhances operational efficiency, and provides a safer working environment for all workers.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

AI-Powered Workers Safety Gear Detection

  • S. Ravikumar,
  • G. Yazhini,
  • D. Venkata Ganesh,
  • Nithish Varma Vanamala

摘要

The AI-powered Worker Safety Gear Detection System which employs real- time monitoring to verify adherence to workplace safety regulations. Using computer vision and deep learning algorithms, the system engages in automatic detection of adequate Personal Protective Equipment (PPE) such as helmets, vests and gloves at worksites. In entry points, AI-powered cameras inspect workers to ensure compliance and permit or deny access based on detection results. When inside, zone-wise surveillance constantly tracks workers in riskprone places to catch safety infractions. When a violation is detected, the system issues real-time notices through automated speaker announcements alerting workers and supervisors. The local server processes the video feeds through the YOLOv8 deep learning model, enabling fast detections without the need for cloud services. Furthermore, violations recorded are stored in a single central database to provide informative reports to reading officers on compliance and risk management. By incorporating AI-driven automation, this system decreases manual oversight, improves the accuracy of safety enforcement, and promotes a safe and compliant industrial workspace. In the long run, this forward-thinking method reduces workplace accidents, enhances operational efficiency, and provides a safer working environment for all workers.