 |
|
|
|
 |
 |
 |
|
 |
|
 |
|
|
侯志强,韩崇昭.基于像素灰度归类的背景重构算法.软件学报,2005,16(9):1568-1576 |
基于像素灰度归类的背景重构算法 |
A Background Reconstruction Algorithm Based on Pixel Intensity Classification |
投稿时间:2004-04-20 修订日期:2004-11-03 |
DOI: |
中文关键词: 背景差 背景重构 运动检测 图像分割 跟踪 视频监视 |
英文关键词:background subtraction background reconstruction motion detection image segmentation tracking visual surveillance |
基金项目:Supported by the National Grand Fundamental Rescarch 973 Program of China under Grant No.2001CB309403(国家重点基础研究发展规划(973)) |
作者 | 单位 | 侯志强 | 西安交通大学,电子与信息工程学院,综合自动化研究所,陕西,西安,710049 | 韩崇昭 | 西安交通大学,电子与信息工程学院,综合自动化研究所,陕西,西安,710049 |
|
摘要点击次数: 7413 |
全文下载次数: 6058 |
中文摘要: |
背景差法是一种重要的运动检测方法,其难点在于如何进行背景更新.针对该问题,提出一种基于像素灰度归类的背景重构算法,即在假设背景像素灰度以最大概率出现在图像序列的前提下,利用灰度差对相应像素点灰度进行归类,选择频率最高的灰度值作为该点的背景像素值.在背景缓慢变化和突变时,分别利用该算法进行定时和实时背景重构具有时显的优点.仿真结果表明,即使场景中存在运动前景,该算法也能够准确地重构背景,并有效地避免混合现象,从而实现对运动目标的完整提取,以便进一步识别或跟踪. |
英文摘要: |
The background subtraction is an important method to detect the moving objects, and its difficulty is the background update. So a background reconstruction algorithm based on pixel intensity classification is presented in this paper. According to the hypothesis that the background pixel intensity appears in image sequence with maximum probability, the pixel intensity differences between sequential two frames are calculated, and the intensity values at the pixels are classified by means of these differences. For the new algorithm, neither the pre-training of the background without any moving target, nor the models of background and targets are needed. Simulation results indicate that background can be reconstructed correctly by using the new algorithm, so the target can be extracted perfectly and tracked successfully. |
HTML 下载PDF全文 查看/发表评论 下载PDF阅读器 |
|
|
|
|
|
|
 |
|
|
|
|
 |
|
 |
|
 |
|