Object Detection for Safe Working Environments using YOLOv4 Deep Learning Model

Abstract

The health and safety of employees in workplaces maintains its importance since the concept of production emerged. Recent developments in computer vision and deep learning have made it widespread to be used in work environments as a secondary tool in ensuring occupational safety from surveillance videos. Thus, an important performance is achieved by minimizing human-induced errors in working environments. In this study, a method based on the YOLOv4 deep learning model is proposed to control the use of personal protective equipment from videos and to detect unsafe movements in the working environments of facilities operating in the field of industrial production. In the study, a dataset is created with videos collected from different working environments. In the study, later, on the prepared video dataset, the detection of personal protective equipment such as helmets, vests, masks, gloves, eyeglasses used by workers in factories operating in industrial areas and whether they use the appropriate equipment correctly is determined using the YOLOv4 framework. In the experimental studies conducted within the scope of the study, the mean average precision (mAP) value is achieved as 91.18% as a result of the training performed in the YOLOv4 network. In addition, results of 0.89, 0.91, 0.90, 70.35 and 1.1147 are obtained for other measurement metrics such as precision, recall, F1-score, intersection over union (IoU), and average loss, respectively. As a result, in the proposed study, instant inspection of the videos collected from the cameras installed in the factories, the meaning of the scene and the control of safe working environments are successfully achieved.

A Research on Determining the Degree of Risk by Using ResNet

“…A framework was designed to detect PPE usage in construction workers based on visuals, enabling realtime understanding of whether construction workers adhere to safety rules (Delhi et al, 2020). Onal and Dandıl (2021) employed the YOLOv4 deep learning algorithm to detect whether workers in industrial production facilities were using appropriate equipment correctly within their working environments. These studies collectively showcase the utilization of image processing and deep learning techniques for enhancing safety measures, monitoring PPE usage, and ensuring compliance with safety regulations across various industries.…”

Glove Detection System on Laboratory Members Using Yolov4

“…YOLOv4 (You Only Look Once version 4) is an object recognition model designed to identify objects in images or videos quickly and accurately [18]. It further develops the "one-stage object detection" approach, prioritizing speed and efficiency.…”

Convolutional Neural Network for Identification of Personal Protective Equipment Usage Compliance in Manufacturing Laboratory

“…The development of CNN science and applications is still being researched in order to advance related science and knowledge. Two basic parameters used in CNN for this case are accuracy and detection speed (Önal & Dandıl, 2021). Some examples of applications in previous studies are Krizhevsky et al (2017) YOLO is an object detection system based on CNN which has become very popular in direct object detection because it is carried out in only 1 stage of the process (Redmon et al;2016).…”

“…Both precision and recall, the value is above 90% which is enough to improve construction site security supervision. Similar to the research described above, the research conducted by Önal & Dandıl (2021) in the work environment in the form of industrial production facilities (factories) also focuses on developing PPE detection models, but with the YOLOv4 algorithm. The aim of the study was to build a model to control the use of PPE (hard hats, vests, masks, gloves, and protective eyewear) from video datasets and to detect unsafe movements in factories.…”