A new similarity measure based on machine learning techniques that conforms to the human perception of motion similarity.
Description
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. Using the relative distance between the joints as the basic features, we train the system to compute the similarity of arbitrary pairs of motions. Experimental results show that our method outperforms methods based on Euclidean distance.
Team Members
- Jeff, Kai-Tai Tang — itjeff@cityu.edu.hk
- Howard Leung — howard@cityu.edu.hk
- Taku Komura
- Hubert Pak-Ho Shum