Vision-based intelligent human-computer interactions with multiple agent collaboration

The system architecture of an agent-based collaborative information processing is presented with applications in mixed reality in this chapter. We model system elements as agents with different processes, data, and applications. Various types of agents and mixed-agent groups are discussed, and the combination of agents as agent-groups are designed to perform the tasks including sensing, user-identification, feature learning and target of interest differentiation, 3D modeling, mixed reality fusion, and interaction. We design an agent-based collaboration strategy with concurrent operation coordination using a serial logic scheduling strategy. The integrity of the system and the correctness of scheduling is guaranteed by using lock-based coordinationwith timeouts strategy. Meanwhile, we present an example of stereo pattern analysis with agent-based system design for applications in mixed reality interaction. Depth and texture are chosen as two primary factors for the pattern-context-aware computing. The process for the pattern analysis could recognize potentially interested patterns by processing the optimal belief context. The strategy enables the system aware of the uncertainty in the pattern. An enhanced learning approach is introduced to allow the system to process the ambiguous pattern and to refine the confidence. An example is given to show the feasibility of the proposed agent-based design scheme. It can be seen that the potential patterns can be differentiated and rebuilt as an extracted stereo model with the context-awareness. The discussion on potential applications for the intelligent driving systems is presented.