A Key-Pose Similarity Algorithm for Motion Data Retrieval

D 2013

A Key-Pose Similarity Algorithm for Motion Data Retrieval

SEDMIDUBSKÝ, Jan, Jakub VALČÍK a Pavel ZEZULA

Základní údaje

Originální název

A Key-Pose Similarity Algorithm for Motion Data Retrieval

Autoři

SEDMIDUBSKÝ, Jan (203 Česká republika, garant, domácí), Jakub VALČÍK (203 Česká republika, domácí) a Pavel ZEZULA (203 Česká republika, domácí)

Vydání

Switzerland, Proceedings of 12th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2013), LNCS 8192, od s. 669-681, 13 s. 2013

Nakladatel

Springer International Publishing

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Polsko

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Impakt faktor

Impact factor: 0.402 v roce 2005

Kód RIV

RIV/00216224:14330/13:00065724

Organizační jednotka

Fakulta informatiky

ISBN

978-3-319-02894-1

ISSN

DOI

http://dx.doi.org/10.1007/978-3-319-02895-8_60

UT WoS

000332973500060

Klíčová slova anglicky

motion capture data; motion retrieval; subsequence retrieval; similar sub-motions

Štítky

best, core_B, DISA, firank_B

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 28. 4. 2014 00:25, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

Analysis of human motion data is an important task in many research fields such as sports, medicine, security, and computer animation. In order to fully exploit motion databases for further processing, effective and efficient retrieval methods are needed. However, such task is difficult primarily due to complex spatio-temporal variances of individual human motions and the rapidly increasing volume of motion data. In this paper, we propose a universal content-based subsequence retrieval algorithm for indexing and searching motion data. The algorithm is able to examine database motions and locate all their sub-motions that are similar to a query motion example. We illustrate the algorithm usability by indexing motion features in form of joint-angle rotations extracted from a real-life 68-minute human motion database. We analyse the algorithm time complexity and evaluate retrieval effectiveness by comparing the search results against user-defined ground truth. The algorithm is also incorporated in an online web application facilitating query definition and visualization of search results.

Návaznosti

GBP103/12/G084, projekt VaV

Název: Centrum pro multi-modální interpretaci dat velkého rozsahu

Investor: Grantová agentura ČR, Centrum pro multi-modální interpretaci dat velkého rozsahu

VG20122015073, projekt VaV

Název: Efektivní vyhledávání v rozsáhlých biometrických datech (Akronym: EFBIO)

Investor: Ministerstvo vnitra ČR, Efektivní vyhledávání v rozsáhlých biometrických datech

Citovat

SEDMIDUBSKÝ, Jan, Jakub VALČÍK a Pavel ZEZULA. A Key-Pose Similarity Algorithm for Motion Data Retrieval. In J. Blanc-Talon et al. (Eds.). Proceedings of 12th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2013), LNCS 8192. Switzerland: Springer International Publishing, 2013, s. 669-681. ISBN 978-3-319-02894-1. Dostupné z: https://dx.doi.org/10.1007/978-3-319-02895-8_60.

@inproceedings{1117913,
   author = {Sedmidubský, Jan and Valčík, Jakub and Zezula, Pavel},
   address = {Switzerland},
   booktitle = {Proceedings of 12th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2013), LNCS 8192},
   doi = {http://dx.doi.org/10.1007/978-3-319-02895-8_60},
   editor = {J. Blanc-Talon et al. (Eds.)},
   keywords = {motion capture data; motion retrieval; subsequence retrieval; similar sub-motions},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Switzerland},
   isbn = {978-3-319-02894-1},
   pages = {669-681},
   publisher = {Springer International Publishing},
   title = {A Key-Pose Similarity Algorithm for Motion Data Retrieval},
   year = {2013}
}

TY  - JOUR
ID  - 1117913
AU  - Sedmidubský, Jan - Valčík, Jakub - Zezula, Pavel
PY  - 2013
TI  - A Key-Pose Similarity Algorithm for Motion Data Retrieval
PB  - Springer International Publishing
CY  - Switzerland
SN  - 9783319028941
KW  - motion capture data
KW  - motion retrieval
KW  - subsequence retrieval
KW  - similar sub-motions
N2  - Analysis of human motion data is an important task in many research fields such as sports, medicine, security, and computer animation. In order to fully exploit motion databases for further processing, effective and efficient retrieval methods are needed. However, such task is difficult primarily due to complex spatio-temporal variances of individual human motions and the rapidly increasing volume of motion data. In this paper, we propose a universal content-based subsequence retrieval algorithm for indexing and searching motion data. The algorithm is able to examine database motions and locate all their sub-motions that are similar to a query motion example. We illustrate the algorithm usability by indexing motion features in form of joint-angle rotations extracted from a real-life 68-minute human motion database. We analyse the algorithm time complexity and evaluate retrieval effectiveness by comparing the search results against user-defined ground truth. The algorithm is also incorporated in an online web application facilitating query definition and visualization of search results.
ER  -

SEDMIDUBSKÝ, Jan, Jakub VALČÍK a Pavel ZEZULA. A Key-Pose Similarity Algorithm for Motion Data Retrieval. In J. Blanc-Talon et al. (Eds.). \textit{Proceedings of 12th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2013), LNCS 8192}. Switzerland: Springer International Publishing, 2013, s.~669-681. ISBN~978-3-319-02894-1. Dostupné z: https://dx.doi.org/10.1007/978-3-319-02895-8\_{}60.

Podrobný výpis o publikaci