Gaussian Mixture Background Modeling Based on CUDA

被引：0

作者：

Ren Hao ^{[1
]}

Lu Xiao-feng ^{[1
]}

Wang Jia ^{[1
]}

Lu Heng-li ^{[1
]}

Fan Tian-xiang ^{[1
]}

机构：

[1] Shanghai Univ, Sch Commun & Informat Engn, Shanghai, Peoples R China

来源：

2011 AASRI CONFERENCE ON APPLIED INFORMATION TECHNOLOGY (AASRI-AIT 2011), VOL 1 | 2011年

关键词：

Background Subtraction; Gaussian Mixture Modeling; GPU; CUBA;

D O I：

暂无

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Pixel-level background modeling is a common computer vision task, and Gaussian mixture modeling (GMM) algorithm is one of the most used methods. Compute Unified Device Architecture (CUBA) is a technology of general-purpose computing on the GPU, which makes users develop GPU program and achieve high-speed parallel computation. In this paper, by harnessing the feature of CUDA, We improved GMM algorithm by parallel processing and memory optimization. Then, the improved GMM algorithm was implemented on GPU. Compared with the traditional approach based on CPU, the experiment results show that the running speed of proposed method has been increased significantly.

引用

页码：305 / 308

页数：4

共 5 条

[1] Kim C, 2008, 10TH INTERNATIONAL CONFERENCE ON ADVANCED COMMUNICATION TECHNOLOGY, VOLS I-III, P1887
[2] NVIDIA Corporation, 2010, CUDA PROGR GUID VERS
[3] Background subtraction techniques: a review
Piccardi, M
[J]. 2004 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOLS 1-7, 2004, : 3099 - 3104
[4] Efficient adaptive density estimation per image pixel for the task of background subtraction
Zivkovic, Z
van der Heijden, F
[J]. PATTERN RECOGNITION LETTERS, 2006, 27 (07) : 773 - 780
[5] Improved adaptive Gaussian mixture model for background subtraction
Zivkovic, Z
[J]. PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, 2004, : 28 - 31

← 1 →