Similarity Searching in Long Sequences of Motion Capture Data

D 2016

Similarity Searching in Long Sequences of Motion Capture Data

SEDMIDUBSKÝ, Jan, Petr ELIÁŠ and Pavel ZEZULA

Basic information

Original name

Similarity Searching in Long Sequences of Motion Capture Data

Authors

SEDMIDUBSKÝ, Jan (203 Czech Republic, guarantor, belonging to the institution), Petr ELIÁŠ (203 Czech Republic, belonging to the institution) and Pavel ZEZULA (203 Czech Republic, belonging to the institution)

Edition

Cham (ZG), Proceedings of 9th International Conference on Similarity Search and Applications (SISAP 2016), LNCS 9939, p. 271-285, 15 pp. 2016

Publisher

Springer International Publishing AG

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/16:00088023

Organization unit

Faculty of Informatics

ISBN

978-3-319-46758-0

ISSN

DOI

http://dx.doi.org/10.1007/978-3-319-46759-7_21

UT WoS

000389801100021

Keywords in English

motion capture data; similarity search; subsequence search; multi-level segmentation

Abstract

V originále

Motion capture data digitally represent human movements by sequences of body configurations in time. Searching in such spatio-temporal data is difficult as query-relevant motions can vary in lengths and occur arbitrarily in the very long data sequence. There is also a strong requirement on effective similarity comparison as the specific motion can be performed by various actors in different ways, speeds or starting positions. To deal with these problems, we propose a new subsequence matching algorithm which uses a synergy of elastic similarity measure and multi-level segmentation. The idea is to generate a minimum number of overlapping data segments so that there is at least one segment matching an arbitrary subsequence. A non-partitioned query is then efficiently evaluated by searching for the most similar segments in a single level only, while guaranteeing a precise answer with respect to the similarity measure. The retrieval process is efficient and scalable which is confirmed by experiments executed on a real-life dataset.

Links

GBP103/12/G084, research and development project

Name: Centrum pro multi-modální interpretaci dat velkého rozsahu

Investor: Czech Science Foundation

Citovat

SEDMIDUBSKÝ, Jan, Petr ELIÁŠ and Pavel ZEZULA. Similarity Searching in Long Sequences of Motion Capture Data. In L. Amsaleg et al. Proceedings of 9th International Conference on Similarity Search and Applications (SISAP 2016), LNCS 9939. Cham (ZG): Springer International Publishing AG, 2016, p. 271-285. ISBN 978-3-319-46758-0. Available from: https://dx.doi.org/10.1007/978-3-319-46759-7_21.

@inproceedings{1349484,
   author = {Sedmidubský, Jan and Eliáš, Petr and Zezula, Pavel},
   address = {Cham (ZG)},
   booktitle = {Proceedings of 9th International Conference on Similarity Search and Applications (SISAP 2016), LNCS 9939},
   doi = {http://dx.doi.org/10.1007/978-3-319-46759-7_21},
   editor = {L. Amsaleg et al.},
   keywords = {motion capture data; similarity search; subsequence search; multi-level segmentation},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Cham (ZG)},
   isbn = {978-3-319-46758-0},
   pages = {271-285},
   publisher = {Springer International Publishing AG},
   title = {Similarity Searching in Long Sequences of Motion Capture Data},
   year = {2016}
}

TY  - JOUR
ID  - 1349484
AU  - Sedmidubský, Jan - Eliáš, Petr - Zezula, Pavel
PY  - 2016
TI  - Similarity Searching in Long Sequences of Motion Capture Data
PB  - Springer International Publishing AG
CY  - Cham (ZG)
SN  - 9783319467580
KW  - motion capture data
KW  - similarity search
KW  - subsequence search
KW  - multi-level segmentation
N2  - Motion capture data digitally represent human movements by sequences of body configurations in time. Searching in such spatio-temporal data is difficult as query-relevant motions can vary in lengths and occur arbitrarily in the very long data sequence. There is also a strong requirement on effective similarity comparison as the specific motion can be performed by various actors in different ways, speeds or starting positions. To deal with these problems, we propose a new subsequence matching algorithm which uses a synergy of elastic similarity measure and multi-level segmentation. The idea is to generate a minimum number of overlapping data segments so that there is at least one segment matching an arbitrary subsequence. A non-partitioned query is then efficiently evaluated by searching for the most similar segments in a single level only, while guaranteeing a precise answer with respect to the similarity measure. The retrieval process is efficient and scalable which is confirmed by experiments executed on a real-life dataset.
ER  -

SEDMIDUBSKÝ, Jan, Petr ELIÁŠ and Pavel ZEZULA. Similarity Searching in Long Sequences of Motion Capture Data. In L. Amsaleg et al. \textit{Proceedings of 9th International Conference on Similarity Search and Applications (SISAP 2016), LNCS 9939}. Cham (ZG): Springer International Publishing AG, 2016, p.~271-285. ISBN~978-3-319-46758-0. Available from: https://dx.doi.org/10.1007/978-3-319-46759-7\_{}21.

Detailed Information on Publication Record