Motion Images: An Effective Representation of Motion Capture Data for Similarity Search

Investor logo

Warning

This publication doesn't include Faculty of Sports Studies. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

ELIÁŠ Petr SEDMIDUBSKÝ Jan ZEZULA Pavel

Year of publication 2015
Type Article in Proceedings
Conference Proceedings of 8th International Conference on Similarity Search and Applications (SISAP 2015), LNCS 9371
MU Faculty or unit

Faculty of Informatics

Citation
Doi http://dx.doi.org/10.1007/978-3-319-25087-8_24
Field Informatics
Keywords motion capture data; motion similarity; visualization; motion image; action classification
Description The rapid development of motion capturing technologies has caused a massive usage of human motion data in a variety of fields, such as computer animation, gaming industry, medicine, sports and security. These technologies produce large volumes of complex spatio-temporal data which need to be effectively compared on the basis of similarity. In contrast to a traditional way of extracting numerical features, we propose a new idea to transform complex motion data into RGB images and compare them by content-based image retrieval methods. We see transformed RGB images as suitable application-independent features for their ability to preserve key aspects of performed motions. To demonstrate the usability of this idea, we evaluate a preliminary experiment that classifies 1,034 motions into 14 categories with the 87.4% precision.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info