首页 | 本学科首页   官方微博 | 高级检索  
     

基于PCNN的高斯混合模型运动检测改进方法
引用本文:朱望飞,马义德,邱秀清. 基于PCNN的高斯混合模型运动检测改进方法[J]. 兰州大学学报(自然科学版), 2009, 45(2)
作者姓名:朱望飞  马义德  邱秀清
作者单位:兰州大学,信息科学与工程学院电路与系统研究所,兰州,730000;兰州大学,信息科学与工程学院电路与系统研究所,兰州,730000;兰州大学,信息科学与工程学院电路与系统研究所,兰州,730000
摘    要:针对同定摄像机的视频监控系统,提出了一种改进的基于混合高斯模型的运动目标检测方法.改进方法引入PCNN算法,针对模型匹配问题,提出自适应局部阈值算法并结合区域增长思想,利用PCNN的迭代计算,逐步检测出运动目标.实验表明,改进的方法与传统方法相比具有更好的运动目标检测能力,在运动目标和背景的灰度值差别比较小的情况下,能改善其运动目标检测的效果.

关 键 词:运动检测  高斯混合模型  自适应阈值  脉冲耦合神经网络

Improved Gaussian mixture model for moving detection method based on PCNN
ZHU Wang-fei,MA Yi-de,QIU Xiu-qing. Improved Gaussian mixture model for moving detection method based on PCNN[J]. Journal of Lanzhou University(Natural Science), 2009, 45(2)
Authors:ZHU Wang-fei  MA Yi-de  QIU Xiu-qing
Affiliation:1;2;1.School of Information Science and Engineering;Lanzhou University;Lanzhou 730000;China;2.China Huayin Weapons Testing Center;Weinan 714200;Shaanxi;China
Abstract:An improved moving objects detection method was proposed in the paper based on Gaussian mixture model in the case of focusing on a video monitoring system with a static camera.Compared with well-known algorithms,the proposed method had the following two features.First,for matching the existing Gaussian distributions,the adaptive threshold based on neighborhood was attained by PCNN. Second,through circuit calculations of PCNN,moving objects were detected step by step,and the region growing algorithm was used...
Keywords:motion detection  Gaussian mixture model  adaptive threshold  PCNN  
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号