Title :
Features extraction of 3D motion data based on spatial time axis
Author :
Jian, Xiang ; Hongli, Zhu
Author_Institution :
Sch. of Inf. & Electron. Eng., ZheJiang Univ. of Sci. & Technol., Hangzhou
Abstract :
Feature extraction is the basis of processing human motion data correctly. In this paper, a new extraction method based on 3D features is proposed. Space transformations on time axis of each human joint are extracted, which describe 3D relationships of each joint and represent a part of the whole motion independently. So completely motion features are computed by merging these features. Experiment results show that our approaches are effective for motion data analysis.
Keywords :
feature extraction; image motion analysis; 3D features; 3D motion data; features extraction; human motion data; space transformation; spatial time axis; Cities and towns; Data engineering; Data mining; Educational institutions; Feature extraction; Humans; Joints; Merging; Motion analysis; Space technology; 3D Human Motion; Feature Extraction; Joint;
Conference_Titel :
Control Conference, 2008. CCC 2008. 27th Chinese
Conference_Location :
Kunming
Print_ISBN :
978-7-900719-70-6
Electronic_ISBN :
978-7-900719-70-6
DOI :
10.1109/CHICC.2008.4605216
