Informace o publikaci

Fast Subsequence Matching in Motion Capture Data

Logo poskytovatele
Autoři

SEDMIDUBSKÝ Jan ZEZULA Pavel ŠVEC Jan

Rok publikování 2017
Druh Článek ve sborníku
Konference 21st European Conference on Advances in Databases and Information Systems
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
Doi http://dx.doi.org/10.1007/978-3-319-66917-5_5
Obor Informatika
Klíčová slova subsequence matching; motion capture data; content-based retrieval; similarity measure; segmentation; indexing
Popis Motion capture data digitally represent human movements by sequences of body configurations in time. Subsequence matching in such spatio-temporal data is difficult as query-relevant motions can vary in lengths and occur arbitrarily in a very long motion. To deal with these problems, we propose a new subsequence matching approach which (1) partitions both short query and long data motion into fixed-size segments that overlap only partly, (2) uses an effective similarity measure to efficiently retrieve data segments that are the most similar to query segments, and (3) localizes the most query-relevant subsequences within extended and merged retrieved segments in a four-step postprocessing phase. The whole retrieval process is effective and fast in comparison with related work. A real-life 68-minute data motion can be searched in about 1s with the average precision of 87.98% for 5-NN queries.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.

Další info