动态纹理背景的建模  

Modeling dynamic textured background

作　　者：何莎[1] 费树岷[1] 

机构地区：[1]东南大学自动化学院,南京210096

出　　处：《计算机应用》2009年第B12期241-243,共3页journal of Computer Applications

摘　　要：针对室外条件下动态纹理背景,采用自回归运动平均(ARMA)模型建立背景模型,并引入快速增量主元分析(IPCA)算法对模型进行降维,并辨识其中参数,实现最大似然估计。运用增量主元分析算法,不需要估算协方差矩阵,直接可以递增地得到特征向量和奇异值,计算出样本序列的主要元素。完成参数辨识后,ARMA模型可以合成无限长度的预测图像序列。最后,仿真实验证明了算法的有效性。A dynamic textured background in real world situations was modeled by an Antoregressive Moving Average （ARMA） model. Then a fast Incremental Principal Component Analysis （IPCA） algorithm was introduced to reduce dimensionality and identify, and compute the principal components of a sequence of samples incrementally without estimating the covariance matrix. Once learned, a model had predictive power and can be used for extrapolating synthetic sequences with infinite length. Preliminary experiments with this method have achieved promising results.

关 键 词：动态纹理 背景建模 自回归运动平均模型 增量主元分析 子空间系统辨识 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]