Spatio-temporal pyramid for action recognition based on depth sequences

doi:10.3778/j.issn.1002-8331.1604-0136

Computer Engineering and Applications ›› 2017, Vol. 53 ›› Issue (19): 211-215.DOI: 10.3778/j.issn.1002-8331.1604-0136

Previous Articles Next Articles

Spatio-temporal pyramid for action recognition based on depth sequences

ZOU Xiangyang1，2, HOU Yunjiang1

1.Air Force Airborne Academy, Guilin, Guangxi 541003, China
2.College of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin, Guangxi 541004, China

Online:2017-10-01 Published:2017-10-13

基于深度序列的时空金字塔的动作识别

邹向阳1，2，侯云江1

1.空军空降兵学院，广西桂林 541003
2.桂林电子科技大学电子工程与自动化学院，广西桂林 541004

Abstract

Abstract: An efficient human action recognition method is put forward. Three views of depth sequences are transformed into Depth Motion Outline Sequence（DMOS） by using the method of interframe differentiation. Then a spatio-temporal pyramid is proposed to subdivide the DMOS on temporal and spatial level. A feature fusion scheme is presented to concatenate the Histograms of Oriented Gradients（HOG） features which have extracted from the subdivided DMOS. Finally linear SVM to classification is used. Through using the MSR Action 3D data sets, this method is evaluated with different parameters of spatial-temporal pyramid. Experimental results show that this method has higher recognition rate than the similar algorithm.

Key words: action recognition, Depth Motion Outline Sequence（DMOS）, spatio-temporal pyramid, Histogram of Oriented Gradient（HOG）, linear SVM classifier

摘要： 提出一种高效的人体动作识别方法。通过帧间差分法将深度序列的三视图转化为深度运动轮廓序列（DMOS），然后利用时空金字塔对DMOS进行时间维和空间维细分，将细分后得到的空间网格的局部方向梯度直方图（HOG）进行特征融合，并使用线性SVM分类。最后采用MSR Action 3D数据集对提出的算法在不同时空金字塔参数下的识别率和处理速度进行了评估，结果表明该方法在同类算法中具有更高的识别率。

关键词: 动作识别, 深度运动轮廓序列, 时空金字塔, HOG特征, 线性SVM分类器

ZOU Xiangyang1，2, HOU Yunjiang1. Spatio-temporal pyramid for action recognition based on depth sequences[J]. Computer Engineering and Applications, 2017, 53(19): 211-215.

邹向阳1，2，侯云江1. 基于深度序列的时空金字塔的动作识别[J]. 计算机工程与应用, 2017, 53(19): 211-215.

[1]	WANG Ziru, LI Zhenmin. Transferable Dictionary Learning Fused Data Augmentation [J]. Computer Engineering and Applications, 2021, 57(23): 193-199.
[2]	CHEN Yanjie, SHU Dawei, YANG Jijiang, WANG Huan, WANG Qing, LEI Yi. Review of AI Diagnosis System of Developmental Coordination Disorder [J]. Computer Engineering and Applications, 2021, 57(2): 28-36.
[3]	ZHOU Xiaojing, CHEN Junhong, YANG Zhenguo, LIU Wenyin. Manipulation Action Recognition Based on Gesture Feature Fusion [J]. Computer Engineering and Applications, 2021, 57(14): 169-175.
[4]	LIU Jing, YANG Xu, LIU Dongjingdian, NIU Qiang. Multi-person Smoking Action Recognition Algorithm Based on Human Joint Points [J]. Computer Engineering and Applications, 2021, 57(1): 234-241.
[5]	LI Yuanxiang, XIE Linbo. Human Action Recognition Based on Depth Motion Map and Dense Trajectory [J]. Computer Engineering and Applications, 2020, 56(3): 194-200.
[6]	SANG Haifeng, TIAN Qiuyang. Rapid Action Recognition System for Human-Computer Interaction [J]. Computer Engineering and Applications, 2019, 55(6): 101-107.
[7]	PENG Yuan, DUAN Xianhua, WANG Wanyao, LU Wenchao. Multi-Cue Feature Fusion Based Image Classification [J]. Computer Engineering and Applications, 2019, 55(20): 164-169.
[8]	GE Yun1, JING Guodong2. Human Action Recognition Based on Convolution Neural Network Combined with Multi-Scale Method [J]. Computer Engineering and Applications, 2019, 55(2): 100-103.
[9]	HAN Xixi, WEI Min, XU Xiyi, LI Qiaoyue, CHEN Xi, ZHU Hancheng. Traffic Sign Recognition Algorithm Based on Multiple-Feature Fusion [J]. Computer Engineering and Applications, 2019, 55(18): 195-200.
[10]	YANG Shiqiang, LUO Xiaoyu, LI Xiaoli, YANG Jiangtao, LI Dexin. Human Action Recognition Based on DBN-HMM [J]. Computer Engineering and Applications, 2019, 55(15): 169-176.
[11]	ZHAO Xiaoli, TIAN Lihua, LI Chen. Action recognition method based on sparse coding local spatio-temporal descriptors [J]. Computer Engineering and Applications, 2018, 54(7): 29-35.
[12]	GAO Dapeng, ZHU Jiangang. Atom action recognition by multi-dimensional adaptive 3D convolutional neural networks [J]. Computer Engineering and Applications, 2018, 54(4): 174-178.
[13]	ZHU Dayong1，2, GUO Xing1，2, WU Jianguo1，2. Action recognition method using kinect 3D skeleton data [J]. Computer Engineering and Applications, 2018, 54(20): 152-158.
[14]	YU Li1, LIU Kun2, YU Shengtao3. Remote sensing aircraft recognition based on densely connected convolution neural network [J]. Computer Engineering and Applications, 2018, 54(19): 179-185.
[15]	LU Tianran, YU Fengqin, YANG Huizhong, CHEN Ying. Human action recognition based on dense trajectories with saliency detection [J]. Computer Engineering and Applications, 2018, 54(14): 163-167.

Spatio-temporal pyramid for action recognition based on depth sequences

基于深度序列的时空金字塔的动作识别

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics