基于OpenPose的人体动作识别对比研究  

Research on human action recognition and contrastbased on OpenPose

作　　者：杨君[1] 张素君 张创豪 黄晶晶 YANG Jun;ZHANG Sujun;ZHANG Chuanghao;HUANG Jingjing(School of Information Science and Engineering,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]武汉科技大学信息科学与工程学院,湖北武汉430081

出　　处：《传感器与微系统》2021年第1期5-8,共4页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(61701354);武汉科技大学大学生科技创新基金资助项目(18ZZA012)。

摘　　要：针对经典的人体动作对比识别方法有安装繁琐,设备需求量大,交互性不强,成本较高,数据量较大等不足,采用OpenPose可以提高动作识别对比的准确度,简易度以及交互性。利用OpenPose算法进行数据分析和挖掘,检测出图像中人体关键点信息并计算距离,再计算出夹角,判断人体动作的不足之处并提示反馈。实验结果表明:该系统安装简单,设备需求量减小、交互性增强、成本降低、数据量减小,对噪声干扰有较强的鲁棒性。Aiming at the shortcomings of classic human motion comparison and recognition method,the cumbersome installation,large demand for equipment,not strong interaction,high cost,and large amount of data,use OpenPose to improve the accuracy,simplicity and interactivity of the comparison of motion recognition.Use the OpenPose algorithm for data analysis and mining,detect the key point information of the human body in image and calculate the distance,then calculate the included angle,determine the inadequacies of the human body movement and prompt feedback.The experimental results show that the system requires simple equipment installation,reducs demand,enhances interactivity,reduces cost and data quantity,and it has strong robustness to noise interference.

关 键 词：计算机视觉 神经网络 OpenPose算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TP212[自动化与计算机技术—计算机科学与技术]