Action recognition by extracting pyramidal motion features from skeleton sequences
Action recognition by extracting pyramidal motion features from skeleton sequences
复制标题
通过从骨架序列中提取金字塔运动特征进行动作识别
DOI:
10.1007/978-3-662-46578-3_29
复制
发表时间:
2015
期刊:
影响因子:
--
通讯作者:
Lv Chen
中科院分区:
文献类型:
--
作者:
Lu Guoliang;Zhou Yiqi;Li Xueyong;Lv Chen
Human action recognition has been a long-standing problem in computer vision. Computational efficiency is an important aspect in the design of an action-recognition based practical system. This paper presents a framework for efficient human action recognition. The novel pyramidal motion features are proposed to represent skeleton sequences via computing position offsets in 3D skeletal body joints. In the recognition phase, a Naive-Bayes-Nearest-Neighbors (NBNN) classifier is used to take into account the spatial independence of body joints.We conducted experiments to systematically test our framework on the public UCF dataset. Experimental results show that, compared with thestate-of-the-artapproaches, the presented framework is more effective and more accurate for action recognition, and meanwhile it has a high potential to be more efficient in computation.
登录
查看更多内容
DOI:
10.1016/j.patrec.2012.10.023
发表时间:
2013-11
期刊:
Pattern Recognit. Lett.
影响因子:
--
作者:
Guoliang Lu;Mineichi Kudo;J. Toyama
通讯作者:
Guoliang Lu;Mineichi Kudo;J. Toyama
DOI:
10.1016/j.jvcir.2013.03.001
发表时间:
2014
期刊:
J. Vis. Commun. Image Represent.
影响因子:
--
作者:
Xiaodong Yang;Yingli Tian
通讯作者:
Xiaodong Yang;Yingli Tian
影响因子:
19.5
作者:
Ellis, Chris;Masood, Syed Zain;Sukthankar, Rahul
通讯作者:
Sukthankar, Rahul
DOI:
10.1109/tcsvt.2008.2005612
发表时间:
2008-11
影响因子:
8.4
作者:
Zhongna Zhou;X. Chen;Y. Chung;Zhihai He;T. Han;J. Keller
通讯作者:
Zhongna Zhou;X. Chen;Y. Chung;Zhihai He;T. Han;J. Keller
影响因子:
4.7
作者:
Poppe, Ronald
通讯作者:
Poppe, Ronald