[1]张懿扬,陈 志 *,岳文静,等.基于时空图卷积网络的视频中人物姿态分类[J].计算机技术与发展,2021,31(10):70-75.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 012]
　ZHANG Yi-yang,CHEN Zhi*,YUE Wen-jing,et al.Human Pose Classification in Video Based on Spatial Temporal Graph Convolutional Networks[J].,2021,31(10):70-75.[doi:10. 3969 / j. issn. 1673-629X. 2021. 10. 012]
点击复制

基于时空图卷积网络的视频中人物姿态分类()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年10期
页码:
70-75
栏目:
图形与图像
出版日期:
2021-10-10

文章信息/Info

Title:
Human Pose Classification in Video Based on Spatial Temporal Graph Convolutional Networks
文章编号:
1673-629X(2021)10-0070-06
作者:
张懿扬1 ; 陈 志1 * ; 岳文静2 ; 张怡静3
1. 南京邮电大学 计算机学院,江苏 南京 210023;
2. 南京邮电大学 通信与信息工程学院,江苏 南京 210023;
3. 南京邮电大学 物联网学院,江苏 南京 210023
Author(s):
ZHANG Yi-yang1 ; CHEN Zhi1* ; YUE Wen-jing2 ; ZHANG Yi-jing3
1. School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;
2. School of Telecommunications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;
3. School of Internet of Things,Nanjing University of Posts and Telecommunications,Nanjing 210023,China
关键词:
人物姿态分类; 特征融合; 时空图卷积网络; 骨骼关键点; 特征冗余
Keywords:
human pose classification; feature fusion; spatial temporal graph convolutional networks; skeletal key point; feature redundancy
分类号:
TP391.41
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 10. 012
摘要:
为解决视频中人物姿态分类问题, 提出了一种基于时空图卷积网络的改进模型。 该模型首先结合人体的骨架关键点序列来构建视频中人体运动的时空特征图,将输入的视频人体骨骼关键点进行预处理,对空间节点依照人体运动规律进行子网划分,构造关节序列的时空图;继而对得到的时间特征图与空间特征图确定特征权重与卷积核,并进行级联特征融合;最后根据输入输出通道层数量搭建由图卷积网络与时序卷积网络构成的网络训练模型,基于时空特征图构型划分进行时序卷积与图卷积操作,由模型的全连接层得到分类结果。 实验结果表明,上述改进模型能够准确得到视频中人物姿态的分类结果,并改善了卷积网络在训练中的特征冗余问题,有效地提高人物姿态分类的鲁棒性。
Abstract:
In order to solve the classification problem of human pose in videos, an improved model based on spatial temporal graph convolution network? ? ?is proposed. In this model,firstly the human skeleton key point sequences are combined to construct a spatial -temporal feature map of human motion in the video. Open pose is used to preprocess the input skeleton key point data in the video,and sub nets are divided from spatial construction according to the rule of human motion to obtain a spatial-temporal feature map of the joint sequence. Then feature weights and convolution kernel are determined for the obtained spatial-temporal feature maps,and feature fusion is carried out in cascade. Finally,according? ?to the number of input and output channel layers,a training model composed of the graph convolution network and the temporal convolutional network is built. The temporal convolution and the graph convolution are performed based on the configuration division of the spatial-temporal characteristic graph,and the classification results can be obtained from the full connection layer of the model. The experiment shows that the improved model can accurately obtain the classification results of the characters in the video,and improve the feature redundancy of the convolutional network in the training,thus effectively improving the robustness of the classification of characters.

相似文献/References:

[1]周伟 武港山.基于显著图的花卉图像分类算法研究[J].计算机技术与发展,2011,(11):15.
　ZHOU Wei,WU Gang-shan.Research on Saliency Map Based Flower Image Classification Algorithm[J].,2011,(10):15.
[2]黎粤华,单磊,田仲富,等. 基于多特征融合的视频烟雾检测[J].计算机技术与发展,2016,26(01):129.
　LI Yue-hua,SHAN Lei,TIAN Zhong-fu,et al. Video Smoke Detection Based on Multi Feature Fusion Technology[J].,2016,26(10):129.
[3]刘加运,李玉惠,李勃,等. 一种多维特征融合的车辆对象同一性匹配方法[J].计算机技术与发展,2016,26(04):167.
　LIU Jia-yun,LI Yu-hui,LI Bo,et al. A Vehicle Object Identity Matching Method of Multidimensional Feature Combination[J].,2016,26(10):167.
[4]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(10):19.
[5]张雅倩,曾卫明,石玉虎.基于特征融合与稀疏表示的人耳识别[J].计算机技术与发展,2017,27(12):7.
　ZHANG Ya-qian,ZENG Wei-min,SHI Yu-hu.Ear Recognition Based on Feature Fusion and Sparse Representation[J].,2017,27(10):7.
[6]谭程午,夏利民,王 嘉.基于融合特征的群体行为识别[J].计算机技术与发展,2018,28(01):17.[doi:10.3969/ j. issn.1673-629X.2018.01.004]
　TAN Cheng-wu,XIA Li-min,WANG Jia.Recognition of Human Group Action Based on Fusion Features[J].,2018,28(10):17.[doi:10.3969/ j. issn.1673-629X.2018.01.004]
[7]王 敏,陈立潮,曹建芳,等.Hadoop 下自适应随机权值多特征融合图像分类[J].计算机技术与发展,2018,28(11):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
　WANG Min,CHEN Li-chao,CAO Jian-fang,et al.Multi-feature Fusion Image Classification of Adaptive Random Weight Based on Hadoop[J].,2018,28(10):30.[doi:10.3969/ j. issn.1673-629X.2018.11.007]
[8]韩欣欣,叶奇玲.基于 SIFT 和 HOG 特征融合的人体行为识别方法[J].计算机技术与发展,2019,29(06):71.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 015]
　HAN Xin-xin,YE Qi-ling.Human Action Recognition Based on Feature Fusion of SIFT and HOG[J].,2019,29(10):71.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 015]
[9]宋相法,吕 明.融合三维骨架和深度图像特征的人体行为识别[J].计算机技术与发展,2019,29(07):55.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 011]
　SONG Xiang-fa,LYU Ming.Human Activity Recognition Based on Fusing 3D Skeleton and Depth Image Feature[J].,2019,29(10):55.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 011]
[10]王泽泓,刘厚泉.基于迁移学习与自适应特征融合的建筑物识别[J].计算机技术与发展,2019,29(12):40.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 007]
　WANG Ze-hong,LIU Hou-quan.Building Recognition Based on Transfer Learning and Adaptive Feature Fusion[J].,2019,29(10):40.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 007]

更新日期/Last Update: 2021-10-10