基于视觉词袋和三角函数法的动作识别

张欣; 魏熙宁; 王兵

doi:10.3969/j.issn.1000-1565.2018.02.013

河北大学学报(自然科学版) >

2018 , Vol. 38 >Issue 2: 204 - 210

DOI: https://doi.org/10.3969/j.issn.1000-1565.2018.02.013

基于视觉词袋和三角函数法的动作识别

张欣 ,
魏熙宁 ,
王兵

展开

张欣(1966—),男,河北承德人,河北大学教授,博士,主要从事机器视觉方向的研究. E-mail:zhangxin@hbu.edu.cn

收稿日期: 2017-10-11

网络出版日期: 2018-03-25

基金资助

河北省自然科学基金资助项目(F2017201172)

收起

Action recognition based on visual bag of words and trigonometric function method

ZHANG Xin ,
WEI Xining ,
WANG Bing

Expand

1.College of Electronic and Information Engineering, Hebei University, Baoding 071002, China; 2.College of Mathematics and Information Science, Hebei University, Baoding 071002, China

Received date: 2017-10-11

Online published: 2018-03-25

Fold

摘要

为了能够更为迅速与准确地对交警指挥等已知动作进行识别,提出了一种将人体特征点的运动轨迹三角函数化后用视觉词袋进行识别的方法.该方法通过将人体运动肢体的端点定义为特征点后,将特征点的空间位置与时间的关系看作是一组三角函数曲线,用不同的正弦公式的组合代替特征点的运动轨迹,以提取特征;同时此算法利用视觉词袋法,提取人体动作时的特征子通过金字塔模型与视觉词袋词典中的特征进行匹配,再通过抽象隐马尔科夫模型实现动作的预测,从而能够自适应地识别出动作.实验结果表明该算法在针对多个动作时优于传统算法.

关键词： 三角函数; 动作轨迹; 视觉词袋; 隐马尔科夫模型

本文引用格式

张欣 , 魏熙宁 , 王兵 . 基于视觉词袋和三角函数法的动作识别[J]. 河北大学学报(自然科学版), 2018 , 38(2) : 204 -210 . DOI: 10.3969/j.issn.1000-1565.2018.02.013

参考文献

[1] TURAGD P,CHELLAPPA R,SUBRAHMANIAN V S,et al.Machine recognition of human activities: a survey[J].IEEE Transactions on Circuits and Systems for Video Technology,2008,18(11):1473-1488.
[2] GUO X L,YANG T T.Gesture recognition based on HMMFNN model using a Kinect[J].Journal on Multimodal User Interface,2016,17:1-7.DOI:https://doi.org/10.1007/s12193-016-0215-x.
[3] 谈家谱,徐文胜.基于Kinect的指尖检测与手势识别方法[J].计算机应用,2015,35:1795-1800.DOI:10.11772/j.issn.1001-9081.2015.06.1795. TIAN J P,XU W S.Fingertip detection and gesture recognition method based on Kinect[J].Journal of Computer Applications,2015,35:1795-1800,DOI:10.11772/j.issn.1001-9081.2015.06.1795.
[4] 劭洁,汪伟明.基于肢体动作序列与三维纹理特征的情绪识别[J].计算机应用研究,2018,35(12).优先出版. SHAO J,WANG W M.Emotion recognition based on three-dimensional texture features of body action sequence[J].Application Research of Computers,2018,35(12).Precedence Issue.
[5] 黄飞跃,徐光佑.视角无关的动作识别[J].软件学报,2008,19(17):1623-1634.DOI:10.3724/1001.2008.01623. HUANG F Y,XU G Y.Viewpoint independent action recognition[J].Journal of Software, 2008,19(7):1623-1634.DOI:10.3724/1001.2008.01623.
[6] 胡琼,秦磊,黄庆明.基于视觉的人体动作识别综述[J].计算机学报,2013,36(12):2513-2524.DOI:10.3724/SP.J.1016.2013.02512. HU Q,QIN L,HUANG Q M.A survey on visual human action recognition[J].Chinese Journal of Computers,2013,36(12):2513-2524.DOI:10.3724/SP.J.1016.2013.02512.
[7] 王玲,吕江靖,程诚,等.一种基于视觉词袋模型的人脸识别方法[J].视频应用与工程,2015,39(17):112-120.DOI:10.16280/j.videoe.2015.17.027. WANG L,LÜ J J,CHENG C,et al.Face recognition method based on bag of visual words[J].Video Application & Project,2015,39(17):112-120.DOI:10.16280/j.videoe.2015.17.027.
[8] 黄坤,王倪传.基于视觉词袋模型的人耳识别[J].计算机系统应用,2014,23(12):176-181. HUANG K,WANG N Z.Human ear recognition based on visual bag-of-words model[J].Computer System Application,2014,23(12):176-181.
[9] HUANG Y,WU Z,WANG L,et al.Feature coding in image classification:a comprehensive study[J].IEEE Trans: Pattern Analysis and Machine Intelligence,2014,36(2):493-506.DOI: 10.1109/TPAMI.2013.113.
[10] HUNG H B,SVETHA V,GEOFF W.Tracking and surveillance in wide-area spatial environments using the abstract hidden markov model[J].Journal of Artificial Intelligence Research,2001,15(01):451-499.
[11] 张永,杨浩.基于优化视觉词袋模型的图像分类法[J].计算机应用,2017,37(8):2244-2247.DOI:10.11772/j.issn.1001-9081.2017.08.2244. ZHANG Y,YANG H.Image classification method based on bag-of-visual words model[J].Journal of Computer Applications,2017,37(8):2244-2247.DOI:10.11772/j.issn.1001-9081.2017.08.2244.
[12] OSENTOSKI S,MANFREDI V,MAHADEVAN S.Learning hierarchical models of activity[J].The IEEE RSJ International Conference on Intelligent Robots and Systems,Sendai Japan, 2004,1:891-986.DOI:10.1109/IROS.2004.1389465.
[13] 钱堃,马旭东,袋先中.基于抽象隐马尔可夫模型的运动行为识别方法[J].模式识别与人工智能,2009,22(3):433-439. QIAN K,MA X D,DAI X Z.Motion activity recognition based on abstract hidden markov model[J].PR&AI,2009,22(3):433-439.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

参考文献