Scene scheduling strategy based on neural network

Real time display of the virtual scene is the important research topic of virtual reality,and the optimal scene scheduling strategy is one of the methods to solve this problem. According to the characteristics of the virtual assembly, this article established a Markov model of the change of viewpoint state, used the RBF neural network to dig the rules of viewpoint change during the assembly process, proposed scene scheduling strategy based on the neural network, and employed this strategy to preview and access the scene ahead of time which was going to display in the assembly process. This strategy intellectualizes the scheduling and raises the efficiency of the scene scheduling, so as to achieve the goal to display scene in real time. At the same time this scheduling strategy can be also applied to other domains in the virtual reality , like the scene roaming etc.