Publication

Abstract : In the fourth industrial revolution, more people were working in production sites, including traffic areas, chemical plants, nuclear reactors, and building sites, raising worries about worker safety. The Head is the most important part of the body, and there have not been many studies done on detecting helmet use across a variety of units in hazardous environments. This research constructed a revolutionary deep learning mechanism called YOLOv8.0 that integrates object detection, key point localization, and basic rule-based reasoning to solve this problem. Moreover, it presents an active helmet-wearing detection method and a dataset created from scratch for multifunctional use applications. The three research questions that guide the process are, (i) Is it possible to identify certain classes in any video?, (ii) Can the model be used to identify helmets across numerous sites, and (iii) Can detections be made in challenging environmental circumstances in real-time? first created a dataset in Yolo format and augmented the photos to produce a second, more generic dataset. Next, the proposed datasets on 5 different versions of the YOLOv8.0 pre-trained model because YOLOv8.0 is an anchor-free mechanism; it detects object’s centers straightly rather than its redeem through a known anchor box. On the augmented dataset original dataset, the YOLOv8l version received the best mAP score among the other versions, scoring approximately 95% and 81% respectively.