人体下肢应激微反应自动识别

王昊鹏; 冯显英; 张明亮

doi:10.3788/OPE.20172511.2947

您当前的位置：

首页 >

文章列表页 >

人体下肢应激微反应自动识别

信息科学 | 更新时间：2020-07-07

- 人体下肢应激微反应自动识别
- Automatic recognition of micro-expressions action for human lower limb
- 光学精密工程 2017年25卷第11期页码：2947-2957
- 作者机构：
  
  1.山东警察学院, 山东济南 250014
  2.山东大学高效洁净机械制造教育部重点实验室, 山东济南 250061
  3.山东行政学院, 山东济南 250014
- 作者简介：
  
  [ "王昊鹏(1981-), 男, 山东济南人, 博士后, 讲师, 2004年、2008年、2014年于山东大学分别获得学士、硕士、博士学位, 主要从事智能检测与控制方面的研究。E-mail:whp-whp-whp@163.com" ]
  [ "冯显英(1965-), 男, 山东济宁人, 博士, 教授, 1987年、1992年、1998年于山东工业大学分别获得学士、硕士、博士学位, 主要从事数字化制造技术、智能检测与控制方面的研究。E-mail:fxying@sdu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金资助项目(51405194);山东省自然科学基金资助项目(ZR2016EEP13);山东省自然科学基金资助项目(ZR2013CQ025);山东省高等学校科技计划资助项目(J16LN16)
- DOI：10.3788/OPE.20172511.2947
  中图分类号： TP391.4
- 收稿日期：2017-02-08，
  
  录用日期：2017-5-12，
  
  纸质出版日期：2017-11-25
- 稿件说明：
移动端阅览
王昊鹏, 冯显英, 张明亮. 人体下肢应激微反应自动识别[J]. 光学精密工程, 2017,25(11):2947-2957.

Hao-peng WANG, Xian-ying FENG, Ming-liang ZHANG. Automatic recognition of micro-expressions action for human lower limb[J]. Optics and precision engineering, 2017, 25(11): 2947-2957.
王昊鹏, 冯显英, 张明亮. 人体下肢应激微反应自动识别[J]. 光学精密工程, 2017,25(11):2947-2957. DOI： 10.3788/OPE.20172511.2947.

Hao-peng WANG, Xian-ying FENG, Ming-liang ZHANG. Automatic recognition of micro-expressions action for human lower limb[J]. Optics and precision engineering, 2017, 25(11): 2947-2957. DOI： 10.3788/OPE.20172511.2947.

摘要

由于现有的动作识别方法不能直接用于人体微反应动作识别，本文基于人体下肢微反应动作特点，构建了一种时空金字塔韦伯局部描述子并设计了基于字典学习的人体下肢微反应自动识别算法。该方法利用时空金字塔韦伯局部描述子提取每一类人体下肢微反应动作特征，使用主成分分析法对特征降维；然后，建立每一类动作子字典并将子字典串联形成总的动作字典；最后，通过实验分析了金字塔级数

，降维后每类动作特征维数

PCA

，每类动作子字典原子个数

Atom

，以及稀疏阈值

等参数对识别结果的影响，并确定最优参数值

=3，

PCA

=30，

Atom

=40，

=10。实验结果表明，提出的算法对10种人体下肢微反应动作的识别率均在0.83~0.91之间，平均识别率达到0.86，高于其他动作识别算法。设计的算法更适用于人体下肢微反应动作分类，并可有效提高分类识别率。

Abstract

Because the existing motion recognition method couldnot be directly used in human micro-expression action recognition. A spatio-temporal pyramid Weber Local Descriptor (STPWLD) was constructed and an automatic recognition algorithm of human lower limb micro-expression action based on dictionary learning according to characterize human lower limb micro-expression action was designed. With the method

the features of human lower limb micro-expression action was extracted by the STPWLD. Then

the dimensions of STPWLD feature were reduced by the principal component analysis. Furthermore

the sub-dictionaries of human lower limb micro-expressions action was established and these sub-dictionaries were connected in series to construct a general action dictionary. Finally

the influence of the parameters of the algorithm on the recognition results was analyzed

and the optimal value of these parameters was determined. It shows that the optimal value of pyramid scales is 3

the optimal feature dimension of each action after dimension reduction is 30

the optimal number of atoms in each action dictionary is 40 and the optimal value of sparse threshold is 10. The experimental results indicate that the recognition rates of the proposed algorithm for 10 kinds of human lower limb micro-expression actions are all between 0.83~0.91

and the average recognition rate is 0.86

higher than that of other algorithms. The algorithm is suitable for the classification of human lower limb micro-expression actions and improves the classification recognition rate effectively.

关键词

Keywords

references

姜振宇.审讯中的应激微反应的应用[J].中国检察官, 2014(18):59-64.

JIANG ZH Y. The application of micro-expressions in the trial[J]. The Chinese Procurators, 2014(18):59-64. (in Chinese)

吴奇, 申寻兵, 傅小兰.微表情研究及其应用[J].心理科学进展, 2010, 18(9):1359-1368.

WU Q, SHENG X B, FU X L. Micro-expression and its applications[J]. Advances in Psychological Science, 2010, 18(9):1359-1368. (in Chinese)

SHEN X B, WU Q, FU X L. Effects of duration of expressions on the recognition of microexpressions[J]. Journal of Zhejiang University Science B, 2012, (13):221-230.

XIE L, LIU X, YANG X J, et al.. Cognitive regulation and emotion modeling for micro-expression[J]. International Journal of Control and Automation, 2016, 9(2):361-372.

TANG A, LU K, WANG Y F, et al.. A real-time hand posture recognition system using deep neural networks[J]. ACM Transactions on Intelligent Systems and Technology, 2015, 6(2):21.

DOAN H G, NGUYEN V T, VU H, et al.. A combination of user-guide scheme and kernel descriptor on RGB-D data for robust and realtime hand posture recognition[J]. Engineering Applications of Artificial Intelligence, 2016, 49:103-113.

MARCOS-RAMIRO A, PIZARRO-PEREZ D, MARRON-ROMERA M, et al , . Body communicative cue extraction for conversational analysis[C]. IEEE Proceedings of 10 th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition , 2013.

YANG NG, LI J T, WANG R. A method of lower limb joint points extraction based on pendulum model under arbitrary gesture walk[J]. Applied Mechanics and Materials, 2014, 556-562:4347-4351.

KWAK N J, SONG T S. Human action recognition using accumulated moving information[J]. International Journal of Multimedia and Ubiquitous Engineering, 2015, 10(10):211-222.

蔡加欣, 冯国灿, 汤鑫, 等.基于姿势字典学习的人体行为识别[J].光学学报, 2014, 34(12):1215002.

CAI J X, FENG G C, TANG X, et al.. Human action recognition by leaning pose dictionary[J]. Acta Optica Sinica, 2014, 34(12):1215002. (in Chinese)

CHEN J, SHAN S G, HE C, et al.. WLD:a robust local image descriptor[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9):1705-1720.

ZHANG ZH, WANG L, ZHU Q, et al.. Pose-invariant face recognition using facial landmarks and Weber local descriptor[J]. Knowledge-Based Systems, 2015, 84:78-88.

ALHUSSEIN M. Automatic facial emotion recognition using weber local descriptor for e-Healthcare system[J]. Cluster Computing, 2016, 19(1):99-108.

ZHAO G Y, PIETIKAINEN M. Dynamic texture recognition using local binary patterns with an application to facial expressions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6):915-928.

张轩阁, 田彦涛, 郭艳君, 等.基于光流与LBP-TOP特征结合的微表情识别[J].吉林大学学报(信息科学版), 2015, 33(5):516-523.

ZHANG X G, TIAN Y T, GUO Y J, et al.. Micro-expression recognition based on feature combination of optical flow and LBP-TOP[J]. Journal of Jilin University (Information Science Edition), 2015, 33(5):516-523. (in Chinese)

王雪虎, 杨健, 艾丹妮, 等.结合先验稀疏字典和空洞填充的CT图像肝脏分割[J].光学精密工程, 2015, 23(9):2687-2697.

WANG X H, YANG J, AI D N, et al.. Liver segmentation in CT image based on priori sparse dictionary and hole filling[J]. Opt. Precision Eng., 2015, 23(9):2687-2697. (in Chinese)

郝云胜, 叶艺山, 邓振淼, 等. FEKO稀疏微多普勒建模及CS重构方法[J].光学精密工程, 2016, 24(6):1482-1489.

HAO Y SH, YE Y SH, DENG ZH M, et al.. FEKO sparse micro-doppler modeling and CS reconstruction method[J]. Opt. Precision Eng., 2015, 24(6):1482-1489. (in Chinese)

高向东, 李国华, 萧振林, 等.焊接缺陷的磁光成像小波多尺度识别及分类[J].光学精密工程, 2016, 24(4):930-936.

GAO X D, LI G H, XIAO ZH L, et al.. Detection and classification of welded defects by magneto-optical imaging based on multi-scale wavelet[J]. Opt. Precision Eng., 2015, 24(4):930-936. (in Chinese)

浏览量

329

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

利用几何特征和时序注意递归网络的动作识别

应用在线随机森林投票的动作识别

基于Kinect数据主成分分析的人体动作识别