A Real-Time Annotation of Motion Data Streams

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F17%3A00094976" target="_blank" >RIV/00216224:14330/17:00094976 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ISM.2017.29" target="_blank" >http://dx.doi.org/10.1109/ISM.2017.29</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ISM.2017.29" target="_blank" >10.1109/ISM.2017.29</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A Real-Time Annotation of Motion Data Streams

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

A Real-Time Annotation of Motion Data Streams

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA16-18889S" target="_blank" >GA16-18889S: Analytika pro velká nestrukturovaná data</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

19th IEEE International Symposium on Multimedia

ISBN

9781538629376

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

154-161

Název nakladatele

IEEE Computer Society

Místo vydání

Neuveden

Místo konání akce

Taichung, Taiwan

Datum konání akce

1. 1. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—