基于姿态时空特征的人体行为识别方法
Human Action Recognition Based on Pose Spatio-Temporal Features
查看参考文献25篇
文摘
|
为了高效、准确地获取视频中的人体行为和运动信息,提出一种基于人体姿态的时空特征的行为识别方法.首先在获取视频中各帧图像的人体关节位置的基础上,提取关节信息描述姿态变化,具体包括在空间维度上提取每帧图像的关节位置关系、时间维度上计算关节空间关系的变化,二者共同构成姿态时空特征描述子;然后利用Fisher向量模型对不同类型的特征描述子分别进行编码,得到固定维度的Fisher向量;最后对不同类型的Fisher向量加权融合后进行分类.实验结果表明,该方法能够有效地识别视频中的人体复杂动作行为,提高行为识别率. |
其他语种文摘
|
In order to extract human motion information efficiently and improve the accuracy of action recognition from videos, an approach for action recognition based on human pose spatio-temporal features is proposed. Firstly, with the joint positions of human body in each frame of the video acquired, we extracted pose information by handcrafted features. Specifically, the positions of joints and relatives in the spatial dimension, as well as the change of that in the temporal dimension were calculated. The two together constituted human pose spatiotemporal feature descriptors. Then the Fisher Vector model was utilized to compute fixed dimension Fisher vector for each descriptor separately. Lastly, features were weighted to fusion for classification. Experimental results show that the proposed algorithm can effectively improve action recognition performance. |
来源
|
计算机辅助设计与图形学学报
,2018,30(9):1615-1624 【核心库】
|
DOI
|
10.3724/sp.j.1089.2018.16848
|
关键词
|
行为识别
;
姿态时空特征
;
Fisher向量
;
加权融合
|
地址
|
中国科学院国家空间科学中心, 中国科学院复杂航天系统电子信息技术重点实验室, 北京, 101499
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
1003-9775 |
学科
|
自动化技术、计算机技术 |
基金
|
装备预研领域基金
|
文献收藏号
|
CSCD:6324284
|
参考文献 共
25
共2页
|
1.
胡琼. 基于视觉的人体动作识别综述.
计算机学报,2013,36(12):2512-2524
|
被引
50
次
|
|
|
|
2.
Dalal N. Histograms of oriented gradients for human detection.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005:886-893
|
被引
52
次
|
|
|
|
3.
Dalal N. Human detection using oriented histograms of flow and appearance.
Proceedings of the 9th European Conference on Computer Vision, Part II,2006:428-441
|
被引
1
次
|
|
|
|
4.
Laptev I. Learning realistic human actions from movies.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2008:1-8
|
被引
9
次
|
|
|
|
5.
Wang H. Dense trajectories and motion boundary descriptors for action recognition.
International Journal of Computer Vision,2013,103(1):60-79
|
被引
80
次
|
|
|
|
6.
Wang H. Action recognition with improved trajectories.
Proceedings of IEEE International Conference on Computer Vision,2013:3551-3558
|
被引
11
次
|
|
|
|
7.
秦华标. 基于复合时空特征的人体行为识别方法.
计算机辅助设计与图形学学报,2014,26(8):1320-1325
|
被引
7
次
|
|
|
|
8.
Jhuang H. Towards understanding action recognition.
Proceedings of the IEEE Conference on Computer Vision,2013:3192-3199
|
被引
1
次
|
|
|
|
9.
Simonyan K. Two-stream convolutional networks for action recognition in videos.
Proceedings of Advances in Neural Information Processing Systems,2014:568-576
|
被引
11
次
|
|
|
|
10.
Wang L M. Action recognition with trajectory-pooled deep-convolutional descriptors.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015:4305-4314
|
被引
3
次
|
|
|
|
11.
Feichtenhofer C. Convolutional two-stream network fusion for video action recognition.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:1933-1941
|
被引
30
次
|
|
|
|
12.
Cheron G. P-CNN: pose-based CNN features for action recognition.
Proceedings of the IEEE Conference on Computer Vision,2015:3218-3226
|
被引
1
次
|
|
|
|
13.
Tran D. Learning spatiotemporal features with 3D convolutional networks.
Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition,2014:4489-4497
|
被引
1
次
|
|
|
|
14.
Cao C Q. Action recognition with joints-pooled 3D deep convolutional descriptors.
Proceedings of the 25th International Joint Conference on Artificial Intelligence,2016:3324-3330
|
被引
1
次
|
|
|
|
15.
Shotton J. Real-time human pose recognition in parts from single depth images.
Communications of the ACM,2013,56(1):116-124
|
被引
82
次
|
|
|
|
16.
Chu X. Structured feature learning for pose estimation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:4715-4723
|
被引
4
次
|
|
|
|
17.
Chatfield K. The devil is in the details: an evaluation of recent feature encoding methods.
Proceedings of the British Machine Vision Conference,2011:76.1-76.12
|
被引
3
次
|
|
|
|
18.
Oneata D. Action and event recognition with fisher vectors on a compact feature set.
Proceedings of the IEEE Conference on Computer Vision,2013:1817-1824
|
被引
1
次
|
|
|
|
19.
Fan R E. LIBLINEAR: a library for large linear classification.
The Journal of Machine Learning Research,2008,9(8):1871-1874
|
被引
147
次
|
|
|
|
20.
Du Y. Hierarchical recurrent neural network for skeleton based action recognition.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015:1110-1118
|
被引
19
次
|
|
|
|
|