Cognitive model for image sensor motion control

This paper presents a neurobiology and cognitive psychology inspired model, implemented using a neural-network-like parallel computational strategy. The goal of the model is to show how a visual cortex inspired system can control camera alignment using a given camera hardware setup, in a similar way to the brain’s controlling eye movements. The system (computational model and camera hardware) are integrated into an experimental environment, the Intelligent Space, a room of ubiquitous computing. The intelligent space is based on several Distributed Intelligent Network Devices (DIND). A DIND has a sensor input, integrated intelligence and a communication interface. The model presented in this paper serves as the integrated intelligence component of a particular DIND. The proposed model implemented in a parallel hardware performs real time operation.

[1]  Joo-Ho Lee,et al.  Intelligent Space — concept and contents , 2002, Adv. Robotics.

[2]  Hideki Hashimoto,et al.  Self-identification of distributed intelligent networked device in intelligent space , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[3]  Hideki Hashimoto,et al.  Building topological maps by looking at people: an example of cooperation between intelligent spaces and robots , 1997, Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Innovative Robotics for Real-World Applications. IROS '97.

[4]  H. Hashimoto,et al.  Intelligent space - how to make spaces intelligent by using DIND? , 2002, IEEE International Conference on Systems, Man and Cybernetics.

[5]  Xiangli Li,et al.  Multilevel logic multiplier using VLSI neural network , 2003, IEEE International Conference on Industrial Technology, 2003.