Efficient Temporal Consistency for Streaming Video Scene Analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00212529" target="_blank" >RIV/68407700:21230/13:00212529 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ICRA.2013.6630567" target="_blank" >http://dx.doi.org/10.1109/ICRA.2013.6630567</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICRA.2013.6630567" target="_blank" >10.1109/ICRA.2013.6630567</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Efficient Temporal Consistency for Streaming Video Scene Analysis

Popis výsledku v původním jazyce

We address the problem of image-based scene analysis from streaming video, as would be seen from a moving platform, in order to efficiently generate spatially and temporally consistent predictions of semantic categories over time. In contrast to previoustechniques which typically address this problem in batch and/or through graphical models, we demonstrate that by learning visual similarities between pixels across frames, a simple filtering algorithm is able to achieve high performance predictions in an efficient and online/causal manner. Our technique is a meta-algorithm that can be efficiently wrapped around any scene analysis technique that produces a per-pixel semantic category distribution.We validate our approach over three different scene analysis techniques on three different datasets that contain different semantic object categories. Our experiments demonstrate that our approach is very efficient in practice and substantially improves the consistency of the predictions over t

Název v anglickém jazyce

Efficient Temporal Consistency for Streaming Video Scene Analysis

Popis výsledku anglicky

We address the problem of image-based scene analysis from streaming video, as would be seen from a moving platform, in order to efficiently generate spatially and temporally consistent predictions of semantic categories over time. In contrast to previoustechniques which typically address this problem in batch and/or through graphical models, we demonstrate that by learning visual similarities between pixels across frames, a simple filtering algorithm is able to achieve high performance predictions in an efficient and online/causal manner. Our technique is a meta-algorithm that can be efficiently wrapped around any scene analysis technique that produces a per-pixel semantic category distribution.We validate our approach over three different scene analysis techniques on three different datasets that contain different semantic object categories. Our experiments demonstrate that our approach is very efficient in practice and substantially improves the consistency of the predictions over t

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/GBP103%2F12%2FG084" target="_blank" >GBP103/12/G084: Centrum pro multi-modální interpretaci dat velkého rozsahu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2013

Kód důvěrnosti údajů

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

Název statě ve sborníku

ICRA2013: Proceedings of 2013 IEEE International Conference on Robotics and Automation

ISBN

978-1-4673-5641-1

ISSN

1050-4729

e-ISSN

—

Počet stran výsledku

7

Strana od-do

133-139

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Karlsruhe

Datum konání akce

6. 5. 2013

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—