Marika Nappi
Prompt-Based Object Detection for Real-Time Industrial Safety Monitoring.
Rel. Bartolomeo Montrucchio. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering), 2026
Abstract
Ensuring worker safety is a critical requirement in industrial environments, where complex operational conditions, dynamic workflows, and the presence of heavy machinery increase the risk of accidents and non-compliance with safety regulations. Traditional manual monitoring approaches are often insufficient due to limited human attention, delayed response times, and challenges in consistently enforcing safety protocols across large industrial sites. In recent years, computer vision techniques have emerged as effective tools for supporting automated monitoring systems, enabling continuous supervision of workspaces and the timely detection of hazardous situations. In particular, the identification of the absence, improper use, or misuse of personal protective equipment (PPE) can significantly reduce safety incidents.
Deep learning-based object detection models allow accurate recognition of workers, tools, machinery, and relevant objects in video streams, providing a foundation for real-time safety analysis
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Informazioni aggiuntive
Corso di laurea
Classe di laurea
Aziende collaboratrici
URI
![]() |
Modifica (riservato agli operatori) |
