Automatic generation of metadata is an important component of multimedia search-by-content systems as it both avoids the need for manual annotation as well as minimising subjective descriptions and human errors. This paper explores the automatic attachment of basic descriptions (or dasiaTagspsila) to human motion held in a motion-capture database on the basis of a dynamic time warping (DTW) approach. The captured motion is held in the Acclaim ASF/AMC format commonly used in game and movie motion capture work and the approach allows for the comparison and classification of motion from different subjects. The work analyses the bone rotations important to a small set of movements and results indicate that only a small set of examples is required to perform reliable motion classification. Abstract-Automatic generation of metadata is an important component of multimedia search-by-content systems as it both avoids the need for manual annotation as well as minimising subjective descriptions and human errors. This paper explores the automatic attachment of basic descriptions (or 'Tags') to human motion held in a motion-capture database on the basis of a Dynamic Time Warping (DTW) approach. The captured motion is held in the Acclaim ASF/AMC format commonly used in game and movie motion capture work and the approach allows for the comparison and classification of motion from different subjects. The work analyses the bone rotations important to a small set of movements and results indicate that only a small set of examples is required to perform reliable motion classification.
Disciplines
Physical Sciences and Mathematics
I. INTRODUCTIONThe use of human motion capture in games and movies is increasingly common and has been significantly simplified by the advent of powerful real-time rendering capabilities on even low-end computers. The availability of motion-capture data now makes it possible to find or generate high quality sequences of required motions relatively easily. However, one significant and outstanding issue in the area is the efficient search and accompanying automatic classification of motion capture sequences.In the literature, there are several suggested solutions for fast and accurate motion matching within a large motion capture database. Notable examples include [1] and [2], where the focus is on providing fast retrieval methods for visually similar motions in large motion capture databases. However, the metric of "visually similar motion" is subjective and the general motion searching method requires the use of example motions for matching.In light of recent advancement in metadata technologies, we suggest that the automated tagging of motion sequences would enable a useful initial step in motion capture database searches. The aim is to reduce the set of possible motion sequences on the basis of a prior grouping of the sequences according to similarity. This allows a user to select an example motion sequence from amongst an appropriate subset of sequences chosen on the basis of metadata. The seco...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.