A Real-Time Annotation of Motion Data Streams

D 2017

A Real-Time Annotation of Motion Data Streams

ELIÁŠ, Petr, Jan SEDMIDUBSKÝ and Pavel ZEZULA

Basic information

Original name

A Real-Time Annotation of Motion Data Streams

Authors

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

Edition

Neuveden, 19th IEEE International Symposium on Multimedia, p. 154-161, 8 pp. 2017

Publisher

IEEE Computer Society

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

storage medium (CD, DVD, flash disk)

RIV identification code

RIV/00216224:14330/17:00094976

Organization unit

Faculty of Informatics

ISBN

978-1-5386-2937-6

DOI

http://dx.doi.org/10.1109/ISM.2017.29

UT WoS

000454605200022

Keywords in English

motion capture data; motion data stream; real-time annotation; motion profiles; online segmentation; similarity measure; deep neural network

Abstract

V originále

Current motion-capture technologies produce continuous streams of 3D human joint trajectories. One of the challenges is to automatically annotate such streams of complex spatio-temporal data in real time. In this paper, we propose an efficient approach to label motion stream data in real time with a limited usage of main memory. Based on a set of user-defined motion profiles, each of them specified by multiple representative samples, the currently visible part of an input motion stream is processed by identifying a moderate number of segments of various lengths. These segments are compared to the profiles to measure their similarity. The segments having a high similarity to a given motion profile are annotated with the corresponding label. The proposed approach performs fast, allows profiles to be dynamically changed at runtime, and does not require any learning procedure, in comparison with existing solutions evaluated on real-life data.

Links

GA16-18889S, research and development project

Name: Analytika pro velká nestrukturovaná data (Acronym: Big Data Analytics for Unstructured Data)

Investor: Czech Science Foundation

Citovat

ELIÁŠ, Petr, Jan SEDMIDUBSKÝ and Pavel ZEZULA. A Real-Time Annotation of Motion Data Streams. In 19th IEEE International Symposium on Multimedia. Neuveden: IEEE Computer Society, 2017, p. 154-161. ISBN 978-1-5386-2937-6. Available from: https://dx.doi.org/10.1109/ISM.2017.29.

@inproceedings{1390237,
   author = {Eliáš, Petr and Sedmidubský, Jan and Zezula, Pavel},
   address = {Neuveden},
   booktitle = {19th IEEE International Symposium on Multimedia},
   doi = {http://dx.doi.org/10.1109/ISM.2017.29},
   keywords = {motion capture data; motion data stream; real-time annotation; motion profiles; online segmentation; similarity measure; deep neural network},
   howpublished = {paměťový nosič},
   language = {eng},
   location = {Neuveden},
   isbn = {978-1-5386-2937-6},
   note = {Best Student Paper Award},
   pages = {154-161},
   publisher = {IEEE Computer Society},
   title = {A Real-Time Annotation of Motion Data Streams},
   year = {2017}
}

TY  - JOUR
ID  - 1390237
AU  - Eliáš, Petr - Sedmidubský, Jan - Zezula, Pavel
PY  - 2017
TI  - A Real-Time Annotation of Motion Data Streams
PB  - IEEE Computer Society
CY  - Neuveden
SN  - 9781538629376
N1  - Best Student Paper Award
KW  - motion capture data
KW  - motion data stream
KW  - real-time annotation
KW  - motion profiles
KW  - online segmentation
KW  - similarity measure
KW  - deep neural network
N2  - Current motion-capture technologies produce continuous streams of 3D human joint trajectories. One of the challenges is to automatically annotate such streams of complex spatio-temporal data in real time. In this paper, we propose an efficient approach to label motion stream data in real time with a limited usage of main memory. Based on a set of user-defined motion profiles, each of them specified by multiple representative samples, the currently visible part of an input motion stream is processed by identifying a moderate number of segments of various lengths. These segments are compared to the profiles to measure their similarity. The segments having a high similarity to a given motion profile are annotated with the corresponding label. The proposed approach performs fast, allows profiles to be dynamically changed at runtime, and does not require any learning procedure, in comparison with existing solutions evaluated on real-life data.
ER  -

ELIÁŠ, Petr, Jan SEDMIDUBSKÝ and Pavel ZEZULA. A Real-Time Annotation of Motion Data Streams. In \textit{19th IEEE International Symposium on Multimedia}. Neuveden: IEEE Computer Society, 2017, p.~154-161. ISBN~978-1-5386-2937-6. Available from: https://dx.doi.org/10.1109/ISM.2017.29.

Detailed Information on Publication Record