Detection of Personal Protective Equipment (PPE) Compliance on Construction Site Using Computer Vision Based Deep Learning Techniques

Construction safety is a matter of great concern for both practitioners and researchers world-wide. Even after enough risk assessments and implementations of adequate controls on the work environments, construction workers are still subject to safety hazards. The need for personal protective equipment (PPE) becomes important in this context. Automatic and real-time detection of non-compliance of workers towards PPE is an important concern. The developments in the field of computer vision and data analytics, especially using deep learning algorithms have the potential to address this challenge in construction. Through this study a framework is developed to sense in real time, the safety compliance of construction workers with respect to PPE, thereby allowing to integrate this framework into the safety workflow of an organization. The study makes use Convolutional Neural Networks model developed by applying transfer learning to a base version of YOLOv3 deep learning network. Based on the presence of hardhat and safety jacket, the model predicts the compliance in four categories such as NOT SAFE, SAFE, NoHardHat and NoJacket. A data set of 2509 images collected from video recordings from several construction sites and web-based collection has been used to train the model. The model reported an F1 score of 0.96 with an average precision and recall rates at 96% on test data set. Once a non “SAFE” category is detected by the model, an alarm and a time-stamped report are also incorporated to enable a real-time integration and adoption on the construction sites. Overall, the study provides evidence on the feasibility and utility of computer vision-based techniques in automating the safety related compliance processes at construction sites.