| 基于像素概率模型的背景分割算法 |
| |
| 引用本文： | 黄文清,汪亚明,赵匀.基于像素概率模型的背景分割算法[J].电子测量与仪器学报,2004,18(3):18-23. |
| |
| 作者姓名： | 黄文清 汪亚明 赵匀 |
| |
| 作者单位： | 浙江大学生物系统工程与食品科学学院,杭州,310029;浙江工程学院信息电子学院,杭州,310033;浙江工程学院信息电子学院,杭州,310033 |
| |
| 基金项目： | 国家自然科学基金 (编号 60 1 0 3 0 1 6)，浙江省自然科学基金 (编号 60 1 0 1 9)，浙江省自然科学基金青年人才培养项目 (编号RC0 2 0 64)资助项目 |
| |
| 摘 要： | 背景分割的目的是提取出图像中感兴趣的前景区域，本文提出了一种基于像素概率模型的背景分割算法，该算法利用高斯混合模型描述每一被观察像素的近期色彩历史，根据分类原则确定当前帧中每一像素的类别，利用在线EM算法更新模型参数。实验结果表明，本文提出的算法可以鲁棒地分割出动态场景中的前景和背景。
|
| 关 键 词： | 像素概率模型 背景分割 高斯分布模型 EM算法 |
Segmenting Background Based on Probability Models of Pixel |
| |
| Huang Wenqing , Wang Yaming Zhao Yun.Segmenting Background Based on Probability Models of Pixel[J].Journal of Electronic Measurement and Instrument,2004,18(3):18-23. |
| |
| Authors: | Huang Wenqing Wang Yaming Zhao Yun |
| |
| Affiliation: | Huang Wenqing 1,2 Wang Yaming 2 Zhao Yun 2 |
| |
| Abstract: | The goal of background segmentation was to extract interesting foreground regions in images. An algorithm of segmenting background based on probability models of pixel was proposed in this paper. Firstly, adaptive pixel models were modeled to describe the recent history of color at each observed pixel. Then each pixel was classified as background or foreground according to principle of classification. Finally, parameters of models were updated using on-line EM algorithm. Experimental results showed that our approach was suitable for segmenting foreground from background in dynamic environments. |
| |
| Keywords: | Probability models of pixel background segmenting Gaussian distribution EM algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
