摘要
提出了基于线性判别分析(LDA)和支持向量机(SVM)的步态识别方法。应用背景差方法分割出运动人体轮廓,对人体轮廓进行水平和垂直投影,将垂直和水平投影向量合成为一维步态数据向量。通过线性判别分析对步态数据进行特征提取和压缩,对得到的识别量应用支持向量机进行步态的分类和识别。应用上述方法在CMU步态数据库上进行了实验,实验结果表明本文所提的步态识别方法具有较高的识别性能。
A new gait recognition method based on linear discriminant analysis (LDA) and support vector machine (SVM) is presented in this paper. Body silhouette extraction is achieved by background subtraction. The body silhouette is projected along its columns and rows to obtain horizontal and vertical projection vectors, which are then combined into one dimensional data vector. Linear discriminant analysis is applied to reduce data dimension, and gait recognition is performed by support vector machine finally. We evaluate the proposed gait recognition method on the Carnegie Mellon University (CMU) gait database, and the experimental results demonstrate that our approach has encouraging recognition performance.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2005年第2期160-164,共5页
Pattern Recognition and Artificial Intelligence
基金
北京市现场总线及自动化技术重点实验室开放课题资助项目(No.20020308)
关键词
步态识别
支持向量机
线性判别分析
特征提取
计算机视觉
Gait Recognition
Support Vector Machine
Linear Discriminant Analysis
Feature Extraction
Computer Vision
