基于PCA和SVM的步态识别

提出了一种新颖的沿中线投影得到特征的步态识别方法。首先，应用背景差方法分割出运动人体轮廓，对外轮廓沿人体中线投影可以得到前后两个向量，合成1D向量作为步态特征。然后，通过主成分分析对得到的一维向量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。实验中，该方法取得了很好的识别性能。

Gait Recognition Based on PCA and SVM

A new gait recognition method based on Midline extraction is achieved by background subtraction. The body projection is presented in this paper. First, body silhouette silhouette is projected along its midline to obtain the foreand-aft Midline Projection Vectors, which are then combined into one dimensional data vector as the gait feature. Then, PCA is applied to reduce data dimension, and gait classification and recognition are performed by support vector machine finally. The result of the experiment demonstrates that the approach has encouraging recognition performance.