Model-based alignment using evolutionary computation and particle filter in a non-messy place

In this paper, we propose a model-based alignment system using evolutionary computation and particle filter for augmented reality (AR). AR is a technique to overlay useful virtual information on the real world. To realize the AR, alignment between real space and virtual space is a serious problem. In particular, an initial frame alignment for realtime tracking is needed in the prior knowledge based alignment. Therefore, we propose an alignment method using evolutionary computation for the initial frame alignment. In this paper, we use the multiple evolutionary computation methods for designing an effective method of alignment system. Moreover, we conduct tracking of the alignment target using particle filter based on the initial frame alignment results. By using this system, a model-based alignment can be conducted in a non-messy place such as being hard to acquire many feature points.