中文摘要：

研究了基于Kalman滤波理论的有色噪声滤波，探讨了其在序列图像背景重建中的应用。首先针对光线变化对背景的影响，建立背景的二阶滤波方程和观测方程，然后给出有色噪声滤波模型，利用Kalman滤波器对背景进行预测更新。试验结果表明，该方法能迅速更新背景，对光线变化具有良好的适应能力。

英文摘要：

The problem of the colored noise filtering based on Kalman filter theory is studied and a method for rebuilding background image is discussed. Considering the effect of the change of illumination condition on background, the two-order filter equation and the measurement equation of the background are established, then a kind of Kalman filtering model for the colored noise is given, Kalman filter is used to predict and update background. Experiments show that the method can update the background quickly, thus having good adaptability to the light change.