摘要： 针对自适应混合高斯背景模型执行速度慢、检测前景时容易产生“鬼影”等问题，提出一种改进的混合高斯背景建模方法。该方法通过对高斯分布权值和生存时间的限制，建立高斯分布退出机制，使模型能根据场景自适应选择每个像素的高斯分布个数，从而去除多余高斯分布，加快算法执行速度。在模型更新过程中，通过融入帧间差分，将每帧图像分成运动像素、背景像素及非真实运动像素，并通过对非真实运动像素赋予较大学习率来加速移出背景的恢复，从而避免“鬼影”和拖影现象。实验结果表明，与传统检测方法相比，该方法可以获得更好的目标检测效果。

关键词: 高斯混合模型, 帧间差分, 前景检测, 背景更新, 背景建模

Abstract: In view of Gaussian Mixture Model(GMM) is slow speed of execution and easily lead to “ghosting” and other issues when detecting foreground object. This paper proposes an improved GMM method. Through giving the constraints on the weight of the Gaussian distribution and survival time, it establishes a mechanism for exiting the Gaussian distribution. The model selected the number of Gaussian distribution according to the scene for each pixel number. The model removes the Gaussian distribution of surplus and accelerates the pace of implementation of the algorithm. In the model update process, through integrating with the frame difference, each frame is divided into pixels, background pixels, pixels of non-real movement. Experimental results show the method can get better object detection performance.

Key words: Gaussian Mixture Model(GMM), interframe difference, foreground detection, background updating, background modeling

中图分类号: 

• N945