基于特征融合的步态识别算法研究

根据人体步态变化特点,提出一种基于特征融合和神经网络的步态识别算法。首先采用时域差分法对运动人体轮廓进行分割,然后分别提取空间特征和频率特征,将两步态特征融合在一起,从而实现步态的分类和识别。在CASIA步态数据库上进行仿真实验,仿真结果表明,该方法不仅克服了单一特征提取方法存在的缺陷,同时提高了步态识别正确率。

Research on Gait Recognition Algorithm Based on Feature Fusion

According to the characteristics of human gait changes, this paper proposes a gait recognition algorithm based on feature fusion and neural network. Firstly, time domain finite difference method is used to extract body silhouette, and then to extract spatial features and frequency characteristics, and two kinds of feature are fused, so as to realize the classification and recognition of gait. The algorithm is tested by CASIA gait database, the simulation results show that, the proposed method not only overcomes the defects of single feature extraction method, but also improves gait recognition correct rate.