Computer Engineering and Applications ›› 2013, Vol. 49 ›› Issue (6): 170-174.
Previous Articles Next Articles
LIU Di, GAO Meifeng
Online:
Published:
刘 娣,高美凤
Abstract: In view of existing situation that foreground object detection is imprecise and calculation is large in non-parametric kernel density estimation, the foreground object detection algorithm based on background subtraction image kernel density estimation is proposed. The single-Gaussian model and the non-parametric kernel density estimation are applied to building the initialization scene background. By means of background subtraction image, the non-dynamic background region is filtered. Kernel density estimation is used to estimate the motion object. For the dynamic background region, the algorithm uses non-parametric kernel density estimation algorithm to update it, otherwise, the percent of background and current frame is used to progressively update the non-dynamic background region. The experimental results show that this algorithm can separate foreground object accurately, greatly eliminate the false detection and reduce the calculated amount.
Key words: background subtraction, kernel density estimation, foreground object detection, background updating
摘要: 针对非参数核密度估计算法前景检测不够精确、运算量大的问题,提出了一种基于背景差分图像的核密度估计前景检测方法。该方法结合了单高斯模型和核密度估计模型进行初始背景建模,利用背景差分图像,过滤掉非动态背景区域,对动态背景区域采用核密度估计进行像素分类。同时,对非动态背景区域,采用渐进式更新;对动态背景区域,采用非参数核密度估计进行更新。实验结果表明,该算法能够精确地分割出前景目标,减少了误检噪声,降低了运算量。
关键词: 背景差分, 核密度估计, 前景目标检测, 背景更新
LIU Di, GAO Meifeng. Foreground object detection based on background subtraction image kernel density estimation[J]. Computer Engineering and Applications, 2013, 49(6): 170-174.
刘 娣,高美凤. 基于背景差分的核密度估计前景检测方法[J]. 计算机工程与应用, 2013, 49(6): 170-174.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://cea.ceaj.org/EN/
http://cea.ceaj.org/EN/Y2013/V49/I6/170