节点文献
基于连续HMM与静态外观信息模型融合的步态识别
Gait Recognition Based on HMM and Static Appearance Information
【摘要】 利用步态轮廓图像下肢左右边界的距离矢量对步态轮廓图像进行描述,采用步态图像两脚的宽度进行准周期性分析.利用隐马尔可夫模型并融合步态的静态外观信息模型进行步态时变数据匹配识别.算法在CMU数据库上进行实验取得了较高的正确识别率.
【Abstract】 The paper attempts to describe gait contour by using the distance between the legs and feet on the edge,to make quasi-periodic analysis on width of the foot of gait image.And to solve the problems resulting from image sequence of different gait cycle by using fusion of HMM and static cues of body biometrics at a decision level.By utilizing the algorithm in the paper,the experiments with CMU databases have achieved comparatively high correction identification ratio.
【关键词】 步态识别;
特征提取;
HMM;
信息融合;
【Key words】 gait recognition; feature extraction; hidden Markov model; information fusion;
【Key words】 gait recognition; feature extraction; hidden Markov model; information fusion;
- 【文献出处】 微电子学与计算机 ,Microelectronics & Computer , 编辑部邮箱 ,2009年03期
- 【分类号】TP391.41
- 【被引频次】6
- 【下载频次】132