Towards Knowledge Formalization and Sharing in a Cognitive Vision Platform for Hazard Control (CVP-HC)

Abstract

<p>Hazards can be found in all work environments and may cause injuries, illnesses, or fatalities. In this context, controlling of risks and safety management has become indispensable to guarantee the laborers wellbeing in worksites. Aiming to achieve a systematic, explicit and comprehensive system for managing safety risks, a Cognitive Vision Platform for Hazard Control (CVP-HC) has been proposed. This platform is designed to automatically detect unsafe activities and improve the decision making process when they occur in different workplace scenarios, while attending specific safety requirements of organizations by adapting its behavior accordingly. To meet generality, the CVP-HC utilizes the Set of Experience Knowledge Structure (SOEKS) and Decisional DNA (DDNA) to administrate knowledge. To ensure scalability and adaptability, a loosely coupled communication model, the publishing/subscribe interaction scheme is used over the Robot Operating System (ROS) framework.</p>