首页|基于关节点连接广度矩阵的颈椎康复运动识别

基于关节点连接广度矩阵的颈椎康复运动识别

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
  • 维普
为提高颈椎康复动作识别的准确率与实时性,提出一种基于关节点连接广度矩阵的颈椎康复运动识别方法.在预处理阶段,首先从人体实时视频流数据中进行骨架提取;然后根据人体骨骼运动特点准确提取运动时人体骨架的特征信息,获取局部空间上的变化信息,利用广度优先搜索算法遍历骨架图内关节点,建立关节点连接广度矩阵,根据连接广度信息划分三角子图并为关节点分配权重,提高模型的识别效率;最后提取关节点连接广度矩阵的时空特征,通过SVM分类器完成识别.在颈椎康复运动数据集CRED和MSR Action 3D公开数据集上对该识别方法进行验证,实验结果表明,基于关节点连接广度矩阵的颈椎康复运动识别方法平均耗时为1.20 s,平均帧率为27,平均识别准确率为92.72%,与现有方法相比有一定优势.
Cervical Spine Rehabilitation Action Recognition Based on Joint Connection Breadth Matrix
To improve the accuracy and real-time performance of cervical spine rehabilitation motion recognition,a cervical spine rehabilita-tion action recognition method based on joint point connection breadth matrix is proposed.In the preprocessing stage,the skeleton is first ex-tracted from real-time human video stream data;Then,based on the action characteristics of the human skeleton,the feature information of the human skeleton during action is accurately extracted,and the change information in local space is obtained.The breadth first search algo-rithm is used to traverse the relevant nodes in the skeleton graph,establish the joint point connection breadth matrix,divide the triangular sub-graph based on the connection breadth information,and assign weights to the joint points to improve the recognition efficiency of the model;Fi-nally,the spatiotemporal features of the joint connection breadth matrix are extracted,and recognition is completed through SVM classifiers.The recognition method was validated on the CRED and MSR Action 3D public datasets for cervical rehabilitation movement.The experimental results showed that the average time consumption of the cervical rehabilitation movement recognition method based on the joint point connec-tion breadth matrix was 1.20 seconds,the average frame rate was 27,and the average recognition accuracy was 92.72%,which has certain ad-vantages compared to existing methods.

cervical spine rehabilitation exercisesaction joint connection breadth matrixhuman skeletontriangle subgraphspatial tem-poral features

朱子豪、何宏、汪焰兵、孙浩

展开 >

上海理工大学 健康科学与工程学院,上海 200093

颈椎康复运动 关节点连接广度矩阵 人体骨架 三角子图 时空特征

科技部项目上海市科委项目国家重点研发计划上海高校大学计算机课程教学改革项目(2021)上海理工大学医工交叉重点项目上海理工大学医工交叉重点项目

G2021013008180705030002020YFC200580210203084051022308502

2024

10.11907/rjdk.231043

软件导刊
湖北省信息学会

软件导刊

影响因子：0.524
ISSN：1672-7800
年,卷(期)：2024.23(1)
  • 8