Content-Based Management of Human Motion Data: Survey and
Challenges

J 2021

Content-Based Management of Human Motion Data: Survey and Challenges

SEDMIDUBSKÝ, Jan, Petr ELIÁŠ, Petra BUDÍKOVÁ and Pavel ZEZULA

Basic information

Original name

Content-Based Management of Human Motion Data: Survey and Challenges

Authors

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

Edition

IEEE Access, IEEE Xplore Digital Library, 2021, 2169-3536

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10200 1.2 Computer and information sciences

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 3.476

RIV identification code

RIV/00216224:14330/21:00119002

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1109/ACCESS.2021.3075766

UT WoS

000645842300001

Keywords in English

Action detection; content-based processing; deep features; metric learning; motion capture data; skeleton sequences; similarity; sub-sequence search

Abstract

V originále

Digitization of human motion using skeleton representations offers exciting possibilities for a large number of applications but, at the same time, requires innovative techniques for their effective and efficient processing. Content-based processing of skeleton data has developed rapidly in recent years, focusing mainly on specialized prototypes with limited consideration of generic data management possibilities. In this survey article, we synthesize and categorize the existing approaches and outline future research challenges brought by the increasing availability of human motion data. In particular, we first discuss the problems of suitable representation and segmentation of continuous skeleton data obtained from various sources. Then, we concentrate on comparison models for assessing the similarity of time-restricted pieces of motions, as required by any content-based management operation. Next, we review the techniques for evaluating similarity queries over collections of motion sequences and filtering query-relevant parts from continuous motion streams. Finally, we summarize the usability of existing techniques in perspective application domains and discuss the new challenges related to current technological and infrastructural developments. We especially assess the existing techniques from the perspective of scalability and propose future research directions for dealing with large and diverse volumes of skeleton data.

Links

GA19-02033S, research and development project

Name: Vyhledávání, analytika a anotace datových toků lidských pohybů

Investor: Czech Science Foundation

Citovat

SEDMIDUBSKÝ, Jan, Petr ELIÁŠ, Petra BUDÍKOVÁ and Pavel ZEZULA. Content-Based Management of Human Motion Data: Survey and Challenges. IEEE Access. IEEE Xplore Digital Library, 2021, vol. 9, 26 April 2021, p. 64241-64255. ISSN 2169-3536. Available from: https://dx.doi.org/10.1109/ACCESS.2021.3075766.

@article{1773602,
   author = {Sedmidubský, Jan and Eliáš, Petr and Budíková, Petra and Zezula, Pavel},
   article_number = {26 April 2021},
   doi = {http://dx.doi.org/10.1109/ACCESS.2021.3075766},
   keywords = {Action detection; content-based processing; deep features; metric learning; motion capture data; skeleton sequences; similarity; sub-sequence search},
   language = {eng},
   issn = {2169-3536},
   journal = {IEEE Access},
   title = {Content-Based Management of Human Motion Data: Survey and Challenges},
   url = {https://ieeexplore.ieee.org/document/9416451},
   volume = {9},
   year = {2021}
}

TY  - JOUR
ID  - 1773602
AU  - Sedmidubský, Jan - Eliáš, Petr - Budíková, Petra - Zezula, Pavel
PY  - 2021
TI  - Content-Based Management of Human Motion Data: Survey and Challenges
JF  - IEEE Access
VL  - 9
IS  - 26 April 2021
SP  - 64241-64255
EP  - 64241-64255
PB  - IEEE Xplore Digital Library
SN  - 21693536
KW  - Action detection
KW  - content-based processing
KW  - deep features
KW  - metric learning
KW  - motion capture data
KW  - skeleton sequences
KW  - similarity
KW  - sub-sequence search
UR  - https://ieeexplore.ieee.org/document/9416451
N2  - Digitization of human motion using skeleton representations offers exciting possibilities for a large number of applications but, at the same time, requires innovative techniques for their effective and efficient processing. Content-based processing of skeleton data has developed rapidly in recent years, focusing mainly on specialized prototypes with limited consideration of generic data management possibilities. In this survey article, we synthesize and categorize the existing approaches and outline future research challenges brought by the increasing availability of human motion data. In particular, we first discuss the problems of suitable representation and segmentation of continuous skeleton data obtained from various sources. Then, we concentrate on comparison models for assessing the similarity of time-restricted pieces of motions, as required by any content-based management operation. Next, we review the techniques for evaluating similarity queries over collections of motion sequences and filtering query-relevant parts from continuous motion streams. Finally, we summarize the usability of existing techniques in perspective application domains and discuss the new challenges related to current technological and infrastructural developments. We especially assess the existing techniques from the perspective of scalability and propose future research directions for dealing with large and diverse volumes of skeleton data.
ER  -

SEDMIDUBSKÝ, Jan, Petr ELIÁŠ, Petra BUDÍKOVÁ and Pavel ZEZULA. Content-Based Management of Human Motion Data: Survey and Challenges. \textit{IEEE Access}. IEEE Xplore Digital Library, 2021, vol.~9, 26 April 2021, p.~64241-64255. ISSN~2169-3536. Available from: https://dx.doi.org/10.1109/ACCESS.2021.3075766.

Detailed Information on Publication Record