基于视频的人体行走状态分析  

Person Walking States Analysis Based on Video

作　　者：徐光宇[1] 崔荣一[1] 

机构地区：[1]延边大学计算机科学与技术系智能信息处理研究室,吉林延吉133002

出　　处：《延边大学学报（自然科学版）》2010年第4期365-369,共5页Journal of Yanbian University（Natural Science Edition）

基　　金：延边大学研究生院科研项目(延大研科合字(2010)第30号)

摘　　要：提出了一种基于多视角的人体行走状态分析方法.首先,利用基于自适应背景更新的背景差分法检测出运动人体;其次,利用4向链码提取人体上半身质心运动轨迹的周期;最后,通过训练不同运动状态的周期得到对应的模糊集,根据隶属度函数判别慢走、走和跑3种运动状态.实验结果表明,该方法能够准确分析人体运动速度并判断其运动状态,并且对背景噪声、视角变化有良好的鲁棒性.An approach for analyzing person states based on multi-viewing-angle was proposed.Firstly,moving person was detected using self-adaptive background updating algorithm.Then,the centroid in the upper part of the human body was searched and its moving period was extracted by four directions chain code.Finally,fuzzy set of walking states was obtained by the training set period,and three kinds walking states of promenade,walking and running were analyzed by membership function.The experimental results show that the person speed and walking states are exactly analyzed by the proposed method,and it is reasonably robust in background noise and varying view angles.

关 键 词：视频图像序列 运动人体检测 质心提取 速度估计 隶属度函数 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]