Tang, J.K.T. and Leung, H. and Komura, T. and Shum, Hubert (2008) Emulating Human Perception of Motion Similarity. Journal of Computer Animation and Virtual World, 19 (3-4). pp. 211-221. ISSN 1546-4261Full text not available from this repository. (Request a copy)
Evaluating the similarity of motions is useful for motion retrieval, motion blending, and performance analysis of dancers and athletes. Euclidean distance between corresponding joints has been widely adopted in measuring similarity of postures and hence motions. However, such a measure does not necessarily conform to the human perception of motion similarity. In this paper, we propose a new similarity measure based on machine learning techniques.We make use of the results of questionnaires from subjects answering whether arbitrary pairs of motions appear similar or not. Using the relative distance between the joints as the basic features, we train the system to compute the similarity of arbitrary pair of motions. Experimental results show that our method outperforms methods based on Euclidean distance between corresponding joints. Our method is applicable to content-based motion retrieval of human motion for large-scale database systems. It is also applicable to e-Learning systems which automatically evaluates the performance of dancers and athletes by comparing the subjects’ motions with those by experts.
The full-text for this journal article can be accessed via the Official URL.
|Uncontrolled Keywords:||3D human motion similarity, human perception, pattern recognition|
|Subjects:||Q Science > QA Mathematics > QA75 Electronic computers. Computer science|
|Divisions:||Academic Departments > Worcester Business School|
|Depositing User:||Hubert Shum|
|Date Deposited:||10 May 2011 13:06|
|Last Modified:||26 Jul 2015 10:04|
Actions (login required)