Moment Gait Energy Image Based Human Recognition at a Distance

MA Qin-Yong; WANG Shen-Kang; NIE Dong-Dong; QIU Jian-Feng

您当前的位置：

首页 >

文章列表页 >

Moment Gait Energy Image Based Human Recognition at a Distance

更新时间：2025-07-16

- Moment Gait Energy Image Based Human Recognition at a Distance
- Acta Electronica Sinica Vol. 35, Issue 11, Pages: 2078-2082(2007)
- 作者机构：
  
  1. 浙江大学计算机科学与技术学院,浙江,杭州,310027
  2. 上海交通大学计算机科学与工程系,上海,200240
  3. 浙江大学计算机科学与技术学院浙江杭州,310027
  4. 上海交通大学计算机科学与工程系上海,200240
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391
- Published：2007
- 稿件说明：
移动端阅览
MA Qin-Yong, WANG Shen-Kang, NIE Dong-Dong, et al. Moment Gait Energy Image Based Human Recognition at a Distance[J]. Acta Electronica Sinica, 2007, 35(11): 2078-2082.
DOI：

MA Qin-Yong, WANG Shen-Kang, NIE Dong-Dong, et al. Moment Gait Energy Image Based Human Recognition at a Distance[J]. Acta Electronica Sinica, 2007, 35(11): 2078-2082. DOI：

摘要

提出了一种基于瞬时步态能量图的远距离身份识别算法.首先根据摆动距离计算出步态周期

并指定步态周期中的关键时刻.步态序列中一个关键时刻的所有侧面轮廓图的平均值构成一个平均瞬时图.一个关键时刻的瞬时步态能量图的计算利用了当前关键时刻以及其他关键时刻的平均瞬时图.提高了每个关键时刻侧面轮廓图像的质量

并比单纯使用步态能量图的方式增加了步态的运动信息.随后计算出所有关键时刻侧面轮廓图相对于瞬时步态能量图的偏移的累积图像

与步态能量图共同作为描述一个对象的特征向量.最后

使用最近邻算法进行步态特征分类.在USF步态数据库上对该算法进行实验

并与基线算法以及另外两个新的步态识别算法进行比较

结果显示该算法达到了更高的总体识别率.

Abstract

A moment gait energy image (MGEI) based gait recognition algorithm is presented.Gait period is estimated from swing distances

and key moments of a gait cycle are specified.The mean of all the silhouette images at a key moment is called the mean moment image.The MGEI at each key moment is calculated from all the mean moment images in gait period.It improves silhouette's quality by gait probability distribution at each key moment

and provides more motion features than the basic gait energy image (GEI).Then a method of gait feature extraction is proposed based on MGEI.The deviations of silhouette images from MGEI at every key moment are cumulated into an image

which is utilized together with GEI to represent a subject.The nearest neighbor classifier is adopted to recognize subjects.The proposed algorithm is evaluated on USF dataset

and the performance is compared with the baseline algorithm and two other new algorithms.Experimental result shows that this algorithm achieves higher overall recognition rate then the other algorithms.

关键词

Keywords

references

Views

1428

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Dynamic Continuous Emotional Recognition of EEG Based on Improved TCNN Algorithm

Research on Lightweight Sensing Technology Based on Single Antenna and Multiple Subcarriers

Method of Security Situation Assessment Based on Improved Random Forest for Industrial Internet

Research on the Generation of Adversarial Samples Based on the Attribution of Principal Features

Related Author

JIE Li-lin

LIU Yong

WANG Ming-xun

ZOU Yang-meng

XU Yi-lu

LU Yu-ming

JIANG Yu

WANG Jia-dong

Related Institution

School of Instrument Science and Optoelectronic Engineering, Nanchang Hangkong University

School of Aviation Services and Music, Nanchang Hangkong University

School of Software, Jiangxi Agricultural University

School of Aeronautical Manufacturing and Mechanical Engineering, Nanchang Hangkong University

School of Cyber Science and Engineering, Southeast University

⁰