一种多特征联合的运动目标检测算法

Moving Object Detection Algorithm on Multi-feature Combination

高斯混合模型已经成为对视频利用背景减除法进行运动目标检测的最多的一种背景建模模型,也成为一种标准模型。首先对高斯混合模型的理论框架及其性能进行了分析,分析了高斯混合模型仍需要解决的问题,并提出一种高斯混合模型联合多特征的运动目标检测算法,实验表明该算法具有较好的目标检测效果以及环境自适应性。

Gaussian mixture modeling is the most used method for background modeling of the implementation of background subtraction in video sequences,and has become the standard method.The theory framework and function of Gauss mixture model are analyzed.The problems of Gauss mixture model which still need to be solved are analyzed,and a Gauss mixture model combined with multiple features is proposed,the experiments show that the algorithm has better effect of object detection and environmental adaptability.