Development of an AI-based Smart Construction Safety Inspection Protocol

Abstract

The safety of workers at construction sites is one of the most important aspects that should be considered while performing their required tasks. Many rules and regulations have been implemented to reduce injuries and fatalities in the jobsites. However, the number of accidents continues to increase. For instance, an accident category of fall-from-height is considered as the top cause of injuries and fatalities. Thus, this thesis developed a novel technique that monitors the workers whether they are complying with a safety standard of the Personal Fall Arrest System (PFAS). This was done by integrating the powerful features of Artificial Intelligence (AI) and the monitoring properties of the Unmanned Air vehicles (UAV) also known as drones. This research establishes a real time detection algorithm based on a Convolutional Neural Network (CNN) model in order to detect two main components of the PFAS that are, safety harness and life-line in addition to a standard safety measure of using a safety helmet. The YOLOv3 algorithm is adopted for a deep learning network used to train the desired model. The model achieved an accuracy rate of 91.26% and around 99% precision. Moreover, the overall recall of the model was 90.2%. After evaluating the deep learning model performance, the developed technology was set into the validation stage using the drone. The validation was performed in two phases: lab experiments, and real construction site. Integrating both technologies was beneficial in detecting violations in minimal time of an average of 12 seconds, which allowed the safety in charge to react accordingly. The obtained results verify the effectiveness of the proposed system in construction sites to control potential violations and to avoid unnecessary accidents.

Date of Award	May 2022
Original language	American English