姿态特征结合2维傅里叶变换的步态识别  

Gait recognition using pose features and 2D Fourier transform

作　　者：王新年[1] 胡丹丹 张涛[2] 白桂欣 Wang Xinnian;Hu Dandan;Zhang Tao;Bai Guixin(Dalian Maritime University,Dalian 116026,China;Liaoning Normal University,Dalian 116029,China)

机构地区：[1]大连海事大学,大连116026 [2]辽宁师范大学,大连116029

出　　处：《中国图象图形学报》2021年第4期796-814,共19页Journal of Image and Graphics

基　　金：大连市科技创新基金项目(2019J12GX036)。

摘　　要：目的针对现有步态识别方法易受携带物品、衣服变化等影响的问题,提出了将无肩姿态能量图、步态参数等姿态特征与步态参数的2维傅里叶变换相结合的步态识别算法。方法基于姿态关节点序列提出忽略肩膀宽度信息的无肩姿态能量图,用以减弱衣服变化的影响;由于下肢受衣物及背包影响较小,提取3个或3个以上的下肢关节点局部结构参数,即提取中臀点与左右膝关节点、中臀点与左右踝关节点构成的两个三角形面积以及所有下肢关节点构成的多边形面积作为步态参数,增强下肢参数在步态识别中的作用;人在行走时,单肢体的运动具有一定的周期性,且肢体之间运动具有一定的协调性,用步态参数的2维幅度谱来表示单肢体运动的周期性与肢体之间运动的协调性,以提高步态参数的可区别性;在现有典型步态特征的基础上,融合本文提出的无肩姿态能量图、步态参数及其2维傅里叶变换幅度谱,采用多特征表示步态的方法,充分利用各特征的优点,提出加权平均与最大池化相结合的两层分数融合策略进行步态识别,提高了步态识别算法在携带物品、衣服变化和跨视角等条件下的正确率。结果实验结果表明,在中国科学院自动化研究所发布的步态数据集CASIA-B上,本文方法在相同视角条件下,正常状态、背包状态和穿大衣状态的平均识别率分别为99.56%、99.23%和94.25%;在跨视角条件下,正常状态、背包状态和穿大衣状态的平均识别率分别为91.32%、85.34%和69.51%。与典型算法相比,穿大衣状态的识别率有显著提升。结论本文方法采用加权平均与最大池化相结合的两层分数融合策略,综合利用各特征的优点及其适用场景,有效提高了步态识别的准确率,特别是减弱了衣服厚度、样式等变化对步态识别的影响。Objective Gait recognition aims to identify and verify individuals on the basis of walking postures. The performance of existing gait recognition methods is easily influenced by factors such as viewing variances, clothing changes, and types of objects carried by a person. Furthermore, none of these methods consider that the coordination and periodicity of human walking are also important features for gait recognition. Therefore, we propose the pose energy map without considering shoulders(PEMoS) to reduce the effect of clothing changes and 2D Fourier transform magnitude spectrum of gait parameters(2DFoMS) to enhance the effect of the coordination and periodicity of human movements. As these features have a close relationship with the human pose, we call them pose features. Moreover, the proposed pose features are fused together with other excellent features such as Gait Set to improve the overall performance of gait recognition.Method Clothing changes can affect the detected positions of body joints, especially the shoulder joints. Therefore, we propose PEMoS,which ignores the shoulder width, to reduce the effect of clothing changes. The construction process of PEMoS is as follows:First, body joints in each frame are detected by pose estimation methods. Second, six upper limb joints, namely, RShoulder(right shoulder), RElbow(right elbow), RWrist(right wrist), LShoulder(loft shoulder), LElbow(left elbow),and LWrist(left wrist), are horizontally shifted with the displacement between the neck joint and the right or left shoulder joint, whereas the rest remain unchanged. Third, the pose binary map is formatted by connecting the corrected joints in a predefined order and width. Then, it is resized to 128 × 88 pixels centering on the MidHip joint. Fourth, PEMoS is computed by averaging pose binary maps within a period that include at least one complete gait cycle. Finally, PEMoS is activated by gamma transformation to improve the performance. 2DFoMS uses the coordination between human movements and the periodicity of

关 键 词：步态识别 姿态特征 无肩姿态能量图 运动的协调性与周期性 局部结构步态参数 步态参数的2维傅里叶变换 两层分数融合策略 

分 类 号：TP391.[自动化与计算机技术—计算机应用技术]