Analysis of Occupational Safety and Health at the Construction Site Based on Images Acquired from Various Sources Using Artificial Intelligence

Occupational health and safety on construction sites is a key aspect of protecting the health and lives of workers. With the advancement of technology, new methods are emerging to monitor and analyze working conditions, including the use of artificial intelligence to detect hazards automatically. This study focuses on analyzing images, primarily from various sources that collect photographic documentation related to occupational health and safety, and the application of artificial intelligence algorithms to process them. The focus of this study is the classification model, which is created to represent the operation of systems based on AI. This classification model determines whether a worker is wearing a helmet (classified as safe) or not (classified as dangerous). Analysis of the photos was conducted using image recognition algorithms to automatically identify hazards, such as the absence of appropriate equipment, inadequate security, or violations of health and safety procedures. The primary objective of this work is to evaluate the extent to which the application of artificial intelligence to analyze images from various platforms can enhance inspection and prevention activities in the field of occupational health and safety. The research will enable the preparation of guidelines for implementing best practices on construction sites, thereby enhancing safety and reducing the risk of accidents, while facilitating compliance with regulations. This study provides valuable insights into the feasibility, benefits, and challenges of using AI-based image analysis for OSH in construction. The findings are intended to assist primarily safety officers and construction managers in making informed decisions regarding the adoption of AI in safety monitoring and compliance enforcement.