| 卷积神经网络用于关节角度识别与姿势评估 |
| |
| 引用本文： | 赵玉婷,钮建伟,张人杰,刘海笑,冉令华. 卷积神经网络用于关节角度识别与姿势评估[J]. 计算机工程与应用, 2019, 55(16): 209-216. DOI: 10.3778/j.issn.1002-8331.1901-0201 |
| |
| 作者姓名： | 赵玉婷 钮建伟 张人杰 刘海笑 冉令华 |
| |
| 作者单位： | 北京科技大学 机械工程学院,北京,100083;北京航空航天大学 机械工程学院,北京,100083;中国标准化研究院,北京,100191 |
| |
| 基金项目： | 国家重点研发计划;国家自然科学基金;中国标准化研究院院长基金 |
| |
| 摘 要： | 为了快速准确地输出各种工作姿势风险评估结果,提出采用Kinect v2与卷积神经网络识别人体各关节角度,并输出标准姿势风险的评估得分。首先使用亚像素角点提取的棋盘标定算法标定Kinect两个摄像头,其次使用改进后的双边滤波对深度图像去噪,使用卷积神经网络识别人体关节二维位置,结合深度信息获取实际三维坐标并计算人体关节角度,最后输出姿势风险评估得分。通过两种实验分别验证了提出的Kinect角度识别与姿势评估的准确性,表明该方法关节角度识别与姿势风险评估的准确率均较高,是一种低成本、高可靠性的姿势评价方法,具有一定的科学意义和工程应用价值。
|
| 关 键 词： | KINECT 相机标定 深度图像 卷积神经网络 人机交互 |
Convolutional Neural Network for Joint Angle Recognition and Posture Assessment |
| |
| ZHAO Yuting,NIU Jianwei,ZHANG Renjie,LIU Haixiao,RAN Linghua. Convolutional Neural Network for Joint Angle Recognition and Posture Assessment[J]. Computer Engineering and Applications, 2019, 55(16): 209-216. DOI: 10.3778/j.issn.1002-8331.1901-0201 |
| |
| Authors: | ZHAO Yuting NIU Jianwei ZHANG Renjie LIU Haixiao RAN Linghua |
| |
| Affiliation: | 1.School of Mechanical Engineering, University of Science and Technology Beijing, Beijing 100083, China2.School of Mechanical Engineering, Beihang University, Beijing 100083, China3.China National Institute of Standardization, Beijing 100191, China |
| |
| Abstract: | In order to better output various pose risk assessment methods quickly and accurately, this paper proposes to use Kinect v2 and convolutional neural network to identify the joint angles of the human body and output the pose risk assessment score. First, two cameras are calibrated by using the checkerboard calibration algorithm of sub-pixel corner extraction. Second, the improved bilateral filtering is used to denoise the depth image. At the same time, the convolutional neural network is used to identify the two-dimensional position of the human joint, and the depth information is used to obtain the actual three-dimensional coordinates. The joint angle is obtained, and finally the posture risk assessment score is outputted. The accuracy of Kinect recognition angle and posture evaluation scores is verified by two experiments, which indicates that the identification and evaluation accuracy of the proposed method is high and there is a certain degree of generalization. |
| |
| Keywords: | Kinect camera calibration depth image convolutional neural network human-machine interaction |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
|
