首页 | 本学科首页   官方微博 | 高级检索  
     

一种基于粒子滤波的任意姿态头部椭圆轮廓跟踪方法
引用本文:邹伟,朱智平,李园,原魁. 一种基于粒子滤波的任意姿态头部椭圆轮廓跟踪方法[J]. 高技术通讯, 2009, 19(12). DOI: 10.3772/j.issn.1002-0470.2009.12.014
作者姓名:邹伟  朱智平  李园  原魁
作者单位:中国科学院自动化研究所高技术创新中心,北京,100190
基金项目:国家自然科学基金,863计划 
摘    要:结合粒子滤波思想,给出了一种适用于复杂背景和较远距离下跟踪任意姿态人体头部椭圆轮廓的方法.该方法采用双重随机采样策略,即在预测值附近通过均匀采样产生初始粒子以保证其多样性,在权值更新后对具有较高权值的粒子进行高斯采样以保证重采样过程的快速收敛性.在权值更新过程中,利用分块颜色直方图实现模板椭圆同粒子椭圆之间的颜色匹配,利用最大梯度距离测度(DMG)对粒子椭圆的边缘拟合程度进行度量,最后利用D-S证据思想对上述两种测度进行融合.实验结果不仅验证了此方法对于复杂背景和人体头部的任意姿态具有较强的鲁棒性和有效性,而且证实,此方法也适用于相对较远的距离范围.

关 键 词:头部椭圆轮廓  粒子滤波  双重随机采样  最大梯度距离测度(DMG)  分块直方图

A method for tracking elliptical contour of arbitrary-pose head based on particle filter
Zou Wei,Zhu Zhiping,Li Yuan,Yuan Kui. A method for tracking elliptical contour of arbitrary-pose head based on particle filter[J]. High Technology Letters, 2009, 19(12). DOI: 10.3772/j.issn.1002-0470.2009.12.014
Authors:Zou Wei  Zhu Zhiping  Li Yuan  Yuan Kui
Affiliation:Zou Wei,Zhu Zhiping,Li Yuan,Yuan Kui (Hi-tech Innovation Centre,Institute of Automation,Chinese Academy of Sciences,Beijing 100190)
Abstract:Based on particle filters, a head elliptical contour tracking method applicable to complex background, large distance range and arbitrary pose is proposed in this paper. The method applies the strategy of dual stochastic sampling: the uniform sampling around predicted value is utilized to produce initial particles, which can ensure particles' diversity; after weights updated, the Gaussian sampling is adopted to resample the particles to achieve high convergence. In weights updating, color matching between t...
Keywords:head elliptical contour  particle filter  dual stochastic sampling  distance to maximum gradient point (DMG)  block histogram
本文献已被 CNKI 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