计算机应用

• 图形与图像处理 • 上一篇    下一篇

自适应混合高斯背景模型的改进

李全民 张运楚   

  1. 山东建筑大学 信息与电气工程学院 山东建筑大学 信息与电气工程学院
  • 收稿日期:2007-02-15 修回日期:2007-04-08 发布日期:2007-08-01 出版日期:2007-08-01
  • 通讯作者: 李全民

Improvement on adaptive mixture Gaussian background model

Quan-min LI Yun-chu ZHANG   

  • Received:2007-02-15 Revised:2007-04-08 Online:2007-08-01 Published:2007-08-01
  • Contact: Quan-min LI

摘要: 对自适应混合高斯背景模型进行了改进,将背景重构和前景消融时间控制机制整合到传统自适应混合高斯背景模型中,以提高运动分割的质量。背景重构算法从含有运动物体的动态场景视频序列中重构静态背景图像,然后用重构的静态背景图像初始化自适应混合高斯背景模型;而前景消融时间控制机制则使运动物体停止时的前景消融时间独立于背景模型的学习速率,从而可以根据需要调节前景消融的持续时间。实验结果表明了算法的有效性。

关键词: 视觉监控, 运动分割, 混合高斯背景模型, 背景重构

Abstract: To improve the quality of motion segmentation, the background reconstruction and foreground mergence time control mechanism were incorporated into the adaptive mixture Gaussian background model. The background reconstruction algorithm constructed a static background image from a video sequence which contained moving objects in the scene, and then the static background image was used to initialize the background model. The foreground mergence time control mechanism was introduced to make the foreground mergence time adjustable and independent of the model's learning rate. The experimental results prove the effectiveness of the algorithm.

Key words: video surveillance, motion segmentation, mixture Gaussian background model, background reconstruction