To reduce the computation of Gauss mixture model effectively and improve the accuracy of shadow elimination in moving object detection, an algorithm which updated the model selectively and eliminated the shadow by the change of brightness was proposed. Firstly, the weight of the Gauss distribution and the rate of those that did not belong to the background were compared before updating the Gauss distribution, if the former was larger, then did not update it, otherwise, updated it; Secondly, the range of brightness change was chosen to be a threshold factor of shadow detection, so that the threshold could be adjusted adaptively according to the change of brightness. Finally, compared this algorithm with the traditional ones through experiments on indoor and outdoor videos, the experimental results show that the time consumption of the algorithm is about one-third of the traditional ones, the accuracy of shadow eliminating is improved and the efficiency of the algorithm is confirmed.

Real-time rendering based training system for fire includes three parts: Modeling and displaying for 3-Dimensional architecture map and interaction with users, fire hazards simulation, supervising for life saving and decision-making for succor. This paper presents approaches to the implementation of virtual training system for fire using some algorithms of real-time rendering, AI and PR, combining with hazards model of fire. On second thoughts, we advance a method, which uses virtual reality method, to implement a software system of fire hazard and training. We combine OpenGL with DirectX to realize C-S based virtual training system for fire in Windows.