Effective and Efficient Similarity Searching in Motion Capture
Data

J 2018

Effective and Efficient Similarity Searching in Motion Capture Data

SEDMIDUBSKÝ, Jan, Petr ELIÁŠ and Pavel ZEZULA

Basic information

Original name

Effective and Efficient Similarity Searching in 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

Multimedia Tools and Applications, Springer US, 2018, 1380-7501

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Impact factor

Impact factor: 2.101

RIV identification code

RIV/00216224:14330/18:00100703

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1007/s11042-017-4859-7

UT WoS

000433202100021

Keywords in English

Motion capture data retrieval;Effective similarity measure;Efficient indexing;k-NN query;Motion image;Convolutional neural network;Fixed-size motion feature

Abstract

V originále

Motion capture data describe human movements in the form of spatio-temporal trajectories of skeleton joints. Intelligent management of such complex data is a challenging task for computers which requires an effective concept of motion similarity. However, evaluating the pair-wise similarity is a difficult problem as a single action can be performed by various actors in different ways, speeds or starting positions. Recent methods usually model the motion similarity by comparing customized features using distance-based functions or specialized machine-learning classifiers. By combining both these approaches, we transform the problem of comparing motions of variable sizes into the problem of comparing fixed-size vectors. Specifically, each rather-short motion is encoded into a compact visual representation from which a highly descriptive 4,096-dimensional feature vector is extracted using a fine-tuned deep convolutional neural network. The advantage is that the fixed-size features are compared by the Euclidean distance which enables efficient motion indexing by any metric-based index structure. Another advantage of the proposed approach is its tolerance towards an imprecise action segmentation, the variance in movement speed, and a lower data quality. All these properties together bring new possibilities for effective and efficient large-scale retrieval.

Links

GBP103/12/G084, research and development project

Name: Centrum pro multi-modální interpretaci dat velkého rozsahu

Investor: Czech Science Foundation

MUNI/A/0992/2016, interní kód MU

Name: Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity (Acronym: SKOMU)

Investor: Masaryk University, Category A

Citovat

SEDMIDUBSKÝ, Jan, Petr ELIÁŠ and Pavel ZEZULA. Effective and Efficient Similarity Searching in Motion Capture Data. Multimedia Tools and Applications. Springer US, 2018, vol. 77, No 10, p. 12073-12094. ISSN 1380-7501. Available from: https://dx.doi.org/10.1007/s11042-017-4859-7.

@article{1381296,
   author = {Sedmidubský, Jan and Eliáš, Petr and Zezula, Pavel},
   article_number = {10},
   doi = {http://dx.doi.org/10.1007/s11042-017-4859-7},
   keywords = {Motion capture data retrieval;Effective similarity measure;Efficient indexing;k-NN query;Motion image;Convolutional neural network;Fixed-size motion feature},
   language = {eng},
   issn = {1380-7501},
   journal = {Multimedia Tools and Applications},
   title = {Effective and Efficient Similarity Searching in Motion Capture Data},
   volume = {77},
   year = {2018}
}

TY  - JOUR
ID  - 1381296
AU  - Sedmidubský, Jan - Eliáš, Petr - Zezula, Pavel
PY  - 2018
TI  - Effective and Efficient Similarity Searching in Motion Capture Data
JF  - Multimedia Tools and Applications
VL  - 77
IS  - 10
SP  - 12073-12094
EP  - 12073-12094
PB  - Springer US
SN  - 13807501
KW  - Motion capture data retrieval;Effective similarity measure;Efficient indexing;k-NN query;Motion image;Convolutional neural network;Fixed-size motion feature
N2  - Motion capture data describe human movements in the form of spatio-temporal trajectories of skeleton joints. Intelligent management of such complex data is a challenging task for computers which requires an effective concept of motion similarity. However, evaluating the pair-wise similarity is a difficult problem as a single action can be performed by various actors in different ways, speeds or starting positions. Recent methods usually model the motion similarity by comparing customized features using distance-based functions or specialized machine-learning classifiers. By combining both these approaches, we transform the problem of comparing motions of variable sizes into the problem of comparing fixed-size vectors. Specifically, each rather-short motion is encoded into a compact visual representation from which a highly descriptive 4,096-dimensional feature vector is extracted using a fine-tuned deep convolutional neural network. The advantage is that the fixed-size features are compared by the Euclidean distance which enables efficient motion indexing by any metric-based index structure. Another advantage of the proposed approach is its tolerance towards an imprecise action segmentation, the variance in movement speed, and a lower data quality. All these properties together bring new possibilities for effective and efficient large-scale retrieval.
ER  -

SEDMIDUBSKÝ, Jan, Petr ELIÁŠ and Pavel ZEZULA. Effective and Efficient Similarity Searching in Motion Capture Data. \textit{Multimedia Tools and Applications}. Springer US, 2018, vol.~77, No~10, p.~12073-12094. ISSN~1380-7501. Available from: https://dx.doi.org/10.1007/s11042-017-4859-7.

Detailed Information on Publication Record