[1]杨宁 杨敏.基于改进的混合高斯模型的运动目标提取[J].计算机技术与发展,2012,(07):20-23.
 YANG Ning,YANG Min.Moving Object Extraction Based on Improved Gaussian Mixture Model[J].,2012,(07):20-23.
点击复制

基于改进的混合高斯模型的运动目标提取()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2012年07期
页码:
20-23
栏目:
智能、算法、系统工程
出版日期:
1900-01-01

文章信息/Info

Title:
Moving Object Extraction Based on Improved Gaussian Mixture Model
文章编号:
1673-629X(2012)07-0020-04
作者:
杨宁 杨敏
南京邮电大学自动化学院
Author(s):
YANG Ning YANG Min
College of Automation, Nanjing University of Posts and Telecommunications
关键词:
背景建模运动目标提取混合高斯模型序列图像分析
Keywords:
background modeling moving object extraction mixture Gaussian model sequential image analysis
分类号:
TP31
文献标志码:
A
摘要:
背景提取技术是图像与视频处理中的关键技术。文中对静态背景下运动目标的提取算法进行了研究。混合高斯算法在近年得到了广泛的关注,但是算法使用固定个数的分布建模,在实际中不能满足最优模型,并且模型对学习率的调整比较敏感。文中提出改进的自适应算法提取前景运动目标,其中主要针对模型中的混合高斯分布的个数及学习判别准则进行了改进。实验证明,该改进算法相比传统算法有着较好的自适应性并且检测效率较高
Abstract:
Background extraction is a key step for image and video processing technology. In this paper, the moving object extraction in the static background is studied. In recent years the Gaussian mixture algorithm received extensive attention. The traditional algorithm model each pixel a fixed number of components, which is not optimal in term of detection and computational time. And the algorithm is sensitive to the adjustment of the learning rate. In this paper ,improved. adaptive algorithm is put forward for moving object extraction. The major improvement is the number of mixture Gaussian components and the discriminant criterion. The experiment results show that the improved algorithm is better than traditional algorithm in both adaptability and computing speed

相似文献/References:

[1]姜忠民 赵建民 朱信忠.基于最大间隔聚类的背景建模方法[J].计算机技术与发展,2009,(10):96.
 JIANG Zhong-min,ZHAO Jian-min,ZHU Xin-zhong.A Background Modeling Method of Maximum Margin Clustering[J].,2009,(07):96.
[2]谢蒙,易法令,杨松润,等.一种新的基于聚类决策的码本更新算法[J].计算机技术与发展,2013,(03):101.
 XIE Meng,YI Fa-ling,YANG Song-run,et al.A New Codebook-updated Algorithm Based on Clustering Decision[J].,2013,(07):101.
[3]王欣宇. 视频监控中特定区域入侵检测算法设计与实现[J].计算机技术与发展,2014,24(10):159.
 WANG Xin-yu. Design and Implementation of Intrusion Detection Algorithm of a Specific Area in Video Surveillance[J].,2014,24(07):159.
[4]蒋翠清,孙富亮,吴艿芯. 基于相对欧氏距离的背景差值法视频目标检测[J].计算机技术与发展,2015,25(01):37.
 JIANG Cui-qing,SUN Fu-liang,WU Nai-xin. Video Object Detection of Background Subtraction Method Based on Relative Euclidean Distance[J].,2015,25(07):37.
[5]万盼盼,张轶. 一种改进的基于背景差分的运动目标检测方法[J].计算机技术与发展,2015,25(02):38.
 WAN Pan-pan,ZHANG Yi. An Improved Method for Moving Object Detection Based on Background Subtraction[J].,2015,25(07):38.
[6]王鹏飞,杨余旺,夏吉安.基于图像背景建模的电火花检测[J].计算机技术与发展,2018,28(03):154.[doi:10.3969/ j. issn.1673-629X.2018.03.033]
 WANG Peng-fei,YANG Yu-wang,XIA Ji-an.Electric Spark Detection Based on Background Generation[J].,2018,28(07):154.[doi:10.3969/ j. issn.1673-629X.2018.03.033]

备注/Memo

备注/Memo:
南京邮电大学攀登计划(NY208050)杨宁(1987-),女,硕士研究生,主要研究方向为计算机视觉;杨敏,博士,副教授,主要从事计算机视觉和图像理解的研究工作
更新日期/Last Update: 1900-01-01