摘要： 提出了基于傅立叶描述子的步态识别方法。用背景差方法得到运动人体的轮廓,通过步态周期分析提取步态序列的关键帧。利用傅立叶描述子处理关键帧的轮廓线序列,并进行数据维数压缩,得到匹配模板。用最近邻法进行分类和识别。应用上述方法在Soton步态数据库上进行了实验。结果表明所提的步态识别方法具有较高的识别性能。

关键词: 步态识别, 傅立叶描述子, 图像处理, 计算机视觉, 模式识别

Abstract: A new gait recognition method based on Fourier descriptors is presented. Body silhouettes are extracted by background subtraction, and cyclic gait analysis is performed to extract key frames. The body contours are processed by Fourier descriptors with data dimension being reduced, and templates are created. The recognition is achieved by nearest neighbor algorithm. This paper evaluates the proposed gait recognition method on the Soton gait database, and the experimental results demonstrate that the approach has a good recognition performance.

中图分类号: 

• TP391.41