An active memory model for cognitive computer vision systems
Sven Wachsmuth, Sebastian Wrede, Marc Hanheide, Christian Bauckhage · Lincoln Repository (University of Lincoln) · 2005
Computer vision is becoming an integral part in human-machine interfaces as research increasingly aims at a seamlessand natural interaction between a user and an application system. Gesture recognition, context awareness, and groundingconcepts in the commonly perceived environment as well as in the interaction history are key abilities of such systems.Simultaneously, recent computer vision research has indicated that integrated systems which are embedded in the worldand interact with their environment seem a prerequisite for solving more general vision tasks. Cognitive computer visionsystems which enable the generation of knowledge on the basis of perception, reasoning, and extension of prior modelsare a major step towards this goal. For these, the integration, interaction and organization of memory becomes a keyissue in system design. In this article we will present a computational framework for integrated vision systems that iscentered around an active memory component. It supports a fast integration and substitution of system components,various means of interaction patterns, and enables a system to reason about its own memory content. This frameworkwill be exemplified by means of a cognitive human-machine interface in an Augmented Reality scenario. The system isable to acquire new concepts from interaction and provides a context aware scene augmentation for the user.