We propose a cognitive vision-based system for the intelligent monitoring of tokamaks during plasma operation, based on multi-sensor data analysis and symbolic reasoning. The practical purpose is to detect and characterize in real time abnormal events such as hot spots measured through infrared images of the in-vessel components in order to take adequate decisions. Our system is made intelligent by the use of a priori knowledge of both contextual and perceptual information for ontology-driven event modeling and task-oriented event recognition. The system is made original by combining both physics-based and perceptual information during the recognition process. Real time reasoning is achieved thanks to task-level software optimizations. The framework is generic and can be easily adapted to different fusion device environments. This paper presents the developed system and its achievements on real data of the Tore Supra tokamak imaging system.