摘要
步态识别是一种新的生物识别技术,它通过人行走的姿势来实现对人身份的鉴别。提出了一种新的基于人体轮廓宽度特征的步态识别方法,将视频序列中检测出的步态轮廓提取三种宽度特征并计算步态序列中宽度的变化特征,从而构成描述步态序列的特征向量。实验表明提出的方法具有较好的识别性能,是一种有效的步态识别方法。
Gait recognition,a new biometrics recognition technology,can discriminate individuals by the way they walk.A novel gait recognition method based on the silhouette width features is proposed in this paper.Firstly,three kinds of silhouette width features are extracted from the detected gait silhouette in video sequence.Secondly,the presented approach computes the changing width features in the gait sequence.Finally,experimental results show that this approach is valid and has encouraging recognition performance.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第24期4-6,14,共4页
Computer Engineering and Applications
基金
国家自然科学基金(the National Natural Science Foundation of China under Grant No.60672074)
江苏省自然科学基金(the NaturalScience Foundation of Jiangsu Province of China under Grant No.BK2006569)
关键词
步态识别背景减除特征提取轮廓宽度
gait recognition
background subtraction
feature extraction
silhouette width
