+高级检索
首页 > 过刊浏览>2023年第46卷第4期 >108-119. DOI:10.11835/j.issn.1000-582X.2021.214
PDF HTML阅读 XML下载 导出引用 引用提醒
神经心理量表理解力检测的人体姿态特征识别方法
作者:
作者单位:

1.重庆大学 电气工程学院，重庆 400044;2.重庆医科大学附属第一医院 老年病科，重庆 401122

作者简介:

房欣欣（1992—），女，博士研究生，主要从事深度学习应用、电力市场研究，(E-mail）1187919949@qq.com。

通讯作者:

杨知方，男，研究员，博士生导师，主要从事人工智能应用、能源电力优化等研究，(E-mail)yangzfang@126.com。

基金项目:

重庆市在渝院士牵头科技创新引导专项（cstc2019yszx-jscxX0004）；重庆市教委科学技术研究项目(KJQN201900109)。


Human posture feature recognition method for neuropsychological comprehension test
Author:
Affiliation:

1.School of Electrical Engineering, Chongqing University, Chongqing 400044, P. R. China;2.Department of Geriatrics, The First Affiliated Hospital of Chongqing Medical University,Chongqing 401122, P. R. China

Fund Project:

Supported by Science Innovation Programs Led by the Academicians in Chongqing under Project (cstc2019yszx-jscxX0004), and the Science and Technology Research Program of Chongqing Municipal Education Commission (KJQN201900109).

  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [21]
    • |
  • 相似文献 [13]
    • | | |
  • 文章评论
    摘要:

    神经心理测试可以对各认知域受损严重程度做出客观评价，是检测疾病进展、评估药物疗效的有效手段。其中理解力测试部分通过判断受试者是否根据指令要求作出相应动作实现，是老年人认知功能障碍评估的重要部分，有利于痴呆的早预防早干预。文章提出了一套神经心理测试中理解力检测的人体姿态估计视频分析方法，基于Openpose深度卷积网络提取人体关键点坐标，随后基于图像形态学处理技术和Faster R-CNN等技术提出了纸张、牙刷等目标物体关键点二维坐标提取方法，并以量表中动作要求建立人体姿态估计数学模型。通过实验对神经心理测试的6个动作进行识别，结果表明，所提姿态估计数学模型和交互动作识别方法能够有效检测人体姿态动作指令及人与纸张的交互指令。

    Abstract:

    Neuropsychological test can objectively evaluate the severity of cognitive impairment. It is an effective means to detect disease progression and evaluate drug efficacy. Comprehension test is an important part of cognitive impairment assessment for the elderly. The assessment is performed by judging whether the subjects make accurate actions according to the instructions, which is conducive to the early prevention and early intervention of dementia. This study proposed a video analysis method of human posture estimation for comprehension detection in neuropsychological testing. The coordinates of key points of human body were first extracted based on OpenPose. Then, based on the image morphology processing technology and Fast R-CNN, a two-dimensional coordinate extraction method was proposed for the key points of the specified target objects, such as paper and toothbrush. Also, the mathematical model of human posture estimation was established. Six actions of neuropsychological test were tested to verify the effectiveness of the proposed method. The results show that the proposed mathematical model of posture estimation and interactive action recognition method can effectively detect human posture action commands and interactive instructions.

    参考文献
    [1] Jia J P, Wang F, Wei C B, et al. The prevalence of dementia in urban and rural areas of China[J]. Alzheimer's & Dementia, 2014, 10(1):1-9.
    [2] Wasenmüller O, Stricker D. Comparison of Kinect V1 and V2 depth images in terms of accuracy and precision[C]. Asian Conference on Computer Vision Workshop. Springer, 2016, 34-45.
    [3] Wang W J, Chang J W, Haung S F, et al. Human posture recognition based on images captured by the Kinect sensor[J]. International Journal of Advanced Robotic Systems, 2016, 13(2): 54.
    [4] Hsu S C, Huang J Y, Kao W C, et al. Human body motion parameters capturing using kinect[J]. Machine Vision and Applications, 2015, 26(7): 919-932.
    [5] 李昕迪, 王云龙, 何艳, 等. 基于Kinect的人体单关节点修复算法研究[J]. 自动化技术与应用, 2016, 35(4):100-102, 124.Li X D, Wang Y L, He Y, et al. Research on the algorithm of human single joint point repair based on Kinect[J]. Techniques of Automation and Applications, 2016, 35(4), 100-102, 124.(in Chinese)
    [6] 沈秉乾, 武志勇, 贺前华, 等. 人体姿势状态判决的跌倒检测方法[J]. 计算机应用, 2014(Z1):223-227, 264.Shen B Q, Wu Z Y, He Q H, et al. Falling detection method based on human body posture judgment[J]. Journal of Computer Applications, 2014(Z1): 223-227, 264. (in Chinese)
    [7] 汪大峰. 视频监控中跌倒行为识别[J]. 电子设计工程, 2016, 24(22): 122-126.Wang D F. Abnormal behavior recognition of fall in surveillance video[J]. Electronic Design Engineering, 2016, 24(22):122-126. (in Chinese)
    [8] 张程, 祝凯, 赵德鹏, 等. 基于人体骨架的跌倒行为识别研究[J]. 电子技术与软件工程, 2020(23): 85-86.Zhang C, Zhu K, Zhao D P, et al. Fall behavior recognition based on human skeleton[J]. Electronic Technology & Software Engineering, 2020(23): 85-86. (in Chinese)
    [9] 唐心宇, 宋爱国. 人体姿态估计及在康复训练情景交互中的应用[J]. 仪器仪表学报, 2018, 39(11): 195-203.Tang X Y, Song A G. Human pose estimation and its implementation in scenario interaction system of rehabilitation training[J]. Chinese Journal of Scientific Instrument, 2018, 39(11): 195-203. (in Chinese)
    [10] 王怀宇, 林艳萍, 汪方. 基于OPENPOSE的三维上肢康复系统[J]. 机电一体化, 2018, 24(9):31-37.Wang H Y, Lin Y P, Wang F. Three-dimensional upper limb rehabilitation system based on OPENPOSE[J]. Mechatronics, 2018, 24(9):31-37. (in Chinese)
    [11] 白敬, 宋爱国, 李会军, 等. 基于工作空间测量的居家脑卒中患者上肢康复训练评估系统[J]. 仪器仪表学报, 2018, 39(4): 74-81Bai J, Song A G, Li H J, et al. Upper extremity rehabilitation training and assessment system for home stroke patients based on workplace measurement[J]. Chinese Journal of Scientific Instrument, 2018, 39(4): 74-81. (in Chinese)
    [12] 徐彬, 郑燕萍, 曹高兴. 面向无人驾驶的行人三维姿态估计方法[J]. 科学技术与工程, 2018, 18(34): 85-91.Xu B, Zheng Y P, Cao G X. 3D pose estimation method of pedestrians for driverless vehicles[J]. Science Technology and Engineering, 2018,18(34):85-91. (in Chinese)
    [13] Qiao S, Wang Y, Li J. Real-time human gesture grading based on OpenPose[C]. International Congress on Image and Signal Processing. IEEE, 2017:1-6.
    [14] Cao Z, Simon T, Wei S E, et al. Realtime multi-person 2D pose estimation using part affinity fields[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2017:7291-7299.
    [15] Lin T Y, Maire M, Belongie S, et al. Microsoft coco: Common objects in context[C]. In European Conference on Computer Vision. Springer, Cham: 740-755.
    [16] 司守奎, 孙玺菁. 数学建模算法与应用[M]. 北京: 国防工业出版社, 2011.Si S K, Sun X J. Mathematical modeling algorithms and applications[M]. Beijing: National Defense Industry Press, 2011. (in Chinese)
    [17] Ren S, He K, Girshick R, Sun J. Faster r-cnn: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6):1137-1149.
    [18] Rajendran S P, Shine L, Pradeep R, et al. Fast and accurate traffic sign recognition for self driving cars using retinanet based detector[C]//2019 International Conference on Communication and Electronics Systems (ICCES). IEEE, 2019: 784-790.
    [19] 曹建秋, 王华清, 蓝章礼. 基于改进YCrCb颜色空间的肤色分割[J]. 重庆交通大学学报(自然科学版), 2010, 29(3): 488-492.Cao J Q, Wang H Q, Lan Z L. Skin Color Division Base on Modified YCrCb Color Space[J]. Journal of Chongqing Jiaotong University (Natural Science), 2010, 29(3): 488-492. (in Chinese)
    [20] 张莹. 开闭运算在消除图象噪声中的应用研究[J]. 潍坊学院学报, 2002(2): 65-66.Zhang Y. The application of opening-closing operation to eliminate lmage noise[J]. Journal of Weifang University, 2002(2):65-66. (in Chinese)
    [21] 陈柏生. 一种二值图像连通区域标记的新方法[J].计算机工程与应用, 2006, 42(25):46-47.Chen B. A new algorithm for binary connected components labeling[J]. Computer Engineering and Applications, 2006.42(25) :46-47. (in Chinese)
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

房欣欣,王兵凯,孔航,葛学人,杨知方,余娟,吕洋,陈晨曦,李文沅.神经心理量表理解力检测的人体姿态特征识别方法[J].重庆大学学报,2023,46(4):108-119.

复制
分享
文章指标
  • 点击次数:374
  • 下载次数: 506
  • HTML阅读次数: 66
  • 引用次数: 0
历史
  • 收稿日期:2021-05-21
  • 在线发布日期: 2023-05-12
文章二维码
您是第11237504 位访问者
主管单位：中华人民共和国教育部
主办单位：重庆大学
地址：重庆市沙坪坝正街174号
电话：
重庆大学学报 ® 2025 版权所有