In industrial environments, the movement of heavy equipment poses significant risks to personnel. This paper presents a line-of-fire detection system that uses real-time video feeds, object detection, and motion tracking to identify and alert when individuals are in the path of moving equipment, specifically pipes. The system uses machine learning models for person detection and pipe segmentation, combined with an alert mechanism, to enhance safety measures.
Safetyin industrial settings, particularly in environments with heavy machinery, protects personnel and equipment. Among the various hazards that workers may encounter on-site, moving machinery stands out as a critical concern. Operational equipment create zones where personnel are in the direct path of potential danger, including moving parts, flying debris, or unintended equipment movements. The line of fire refers to any zone where there is a high risk of injury because of the presence and operation of moving machinery or equipment.
Real-time monitoring of line-of-fire risks represents a significant advancement in industrial safety. This paper presents a smart safety monitoring system to prevent accidents in environments with moving machinery at use on various global rigs. Existing equipment and machine learning is used to create an integrated system for detecting and warning people in the line of fire.
The objective is to identify the path on the rig floor for equipment movement from the rotary area and to identify if any people are breaching the line of fire. If any noncompliance occurs, an event is captured as a violation and logged for warning and alert purposes.