Cognitive Vision is concerned with methods and techniques that enable construction of vision systems that can perform task oriented categorization and recognition of objects and events in the context of an embodied agent. In other words, cognitive vision is computer vision endowed with high level semantic understanding of an inhabited environment.

Cognitive Robotics is concerned with the theory and the implementation of robots that reason, act and perceive in changing, incompletely known, unpredictable environments. Such robots must have higher level cognitive functions that involve reasoning, for example, about goals, actions, when to perceive and what to look for etc. Thus within the realm of cognitive robotics, computer vision and qualitative spatial reasoning work hand in glove to generate spatio-temporal model from observations for such agents leading to a Cognitive Vision system.