摘要
针对当前基于加速度人体行为识别方法中存在的行为数据易受重力加速度影响以及空间信息欠缺等问题,提出一种基于线性加速度的多节点人体行为识别算法。通过分段双向去除重力加速度算法,去除传感器加速度中的重力加速度得到线性加速度;使用滑动均值滤波器滤除线性加速度与传感器加速度的颤抖运动,并对两种加速度中的冗余动作进行裁剪;分别从两种加速度中提取不同关节点数据间的动态时间规整算法(dynamic time warping,DTW)距离特征以及7种常规时域特征;利用支持向量机对人体行为进行分类。试验结果表明,该方法能有效提高人体行为识别的准确性。
Focused on the issue that the behavior data in the current acceleration-based human behavior recognition method was affected by the gravitational acceleration and the lack of spatial information,a multi-node human behavior recognition algorithm based on linear acceleration was proposed.The linear acceleration was obtained by removing gravitational acceleration using segmented bidirectionally removal of gravitational acceleration algorithm.The tremor motion signal was filtered by a sliding averaging filter for linear acceleration and sensor acceleration,and the redundant actions in the two accelerations were cropped.The dynamic time warping(DTW)distance features between different joint points and seven conventional time domain features were extracted from two accelerations.The support vector machine was employed to recognize the human behavior.Experimental results showed that this method could effectively improve the accuracy of human behavior recognition.
作者
李兴
侯振杰
梁久祯
常兴治
LI Xing;HOU Zhenjie;LIANG Jiuzhen;CHANG Xingzhi(College of Information Science and Engineering,Changzhou University,Changzhou 213164,Jiangsu,China;Changzhou Key Laboratory of Large Plastic Parts Intelligence Manufacturing,Changzhou College of Information Technology, Changzhou 213164,Jiangsu,China)
出处
《山东大学学报（工学版）》
CAS
北大核心
2018年第6期56-66,共11页
Journal of Shandong University（Engineering Science）
基金
国家自然科学基金项目(61063021)
江苏省产学研前瞻性联合研究项目(BY2015027-12)
江苏省物联网移动互联技术工程重点实验室开放课题项目(JSWLW-2017-013)
关键词
多节点
线性加速度
DTW距离特征
支持向量机
multi-node
linear acceleration
DTW distance feature
support vector machine
