基于混合高斯模型和三帧差法的背景建模  

Background Modeling Based on Gaussian Mixture Model and Three Frame Difference

作　　者：李亚南[1] 周勇[1] 田瑞娟[1] 

机构地区：[1]中国兵器工业第五八研究所军品部,四川绵阳621000

出　　处：《兵工自动化》2015年第4期33-35,共3页Ordnance Industry Automation

摘　　要：针对混合高斯模型存在的不足,提出一种改进的基于混合高斯模型的背景建模方法。为每一个背景像素建立多维混合高斯模型,融入三帧差分法实时判定背景区域和运动区域,为背景显露区中的像素点选择较大的更新频率,并通过实验进行验证分析。实验结果表明:该方法相比高斯背景建模具有更好的环境适应性和鲁棒性,能消除背景中的"鬼影",适用于实时的目标检测和跟踪。Aiming at the shortage of Gaussian mixture model, an improved background modeling method based on Gaussian mixture model is put forwards. It constructed a mixture Gaussian model for each background pixel, the three-frame differencing is used to judge background area and movement area in real time. Choose larger upgrade frequency for pixel point in background display area. Then verify and analyze it by test. The test results show that, compared with Gaussian background model, the method has better environment adaptability and robustness, it can eliminate ＂shadow＂ in background and can be use for object detection and tracing in real time.

关 键 词：混合高斯模型 帧差 背景建模 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]