Discriminative Correlation Filter with Channel and Spatial Reliability

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00315732" target="_blank" >RIV/68407700:21230/17:00315732 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/CVPR.2017.515" target="_blank" >http://dx.doi.org/10.1109/CVPR.2017.515</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR.2017.515" target="_blank" >10.1109/CVPR.2017.515</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Discriminative Correlation Filter with Channel and Spatial Reliability

Popis výsledku v původním jazyce

Short-term tracking is an open and challenging problem for which discriminative correlation filters (DCF) have shown excellent performance. We introduce the channel and spatial reliability concepts to DCF tracking and provide a novel learning algorithm for its efficient and seamless integration in the filter update and the tracking process. The spatial reliability map adjusts the filter support to the part of the object suitable for tracking. This allows tracking of non-rectangular objects as well as extending the search region. Channel reliability reflects the quality of the learned filter and it is used as a feature weighting coefficient in localization. Experimentally, with only two simple standard features, HOGs and Colornames, the novel CSR-DCF method &#x2013; DCF with Channel and Spatial Reliability &#x2013; achieves state-of-the-art results on VOT 2016, VOT 2015 and OTB. The CSR-DCF runs in real-time on a CPU.

Název v anglickém jazyce

Discriminative Correlation Filter with Channel and Spatial Reliability

Popis výsledku anglicky

Short-term tracking is an open and challenging problem for which discriminative correlation filters (DCF) have shown excellent performance. We introduce the channel and spatial reliability concepts to DCF tracking and provide a novel learning algorithm for its efficient and seamless integration in the filter update and the tracking process. The spatial reliability map adjusts the filter support to the part of the object suitable for tracking. This allows tracking of non-rectangular objects as well as extending the search region. Channel reliability reflects the quality of the learned filter and it is used as a feature weighting coefficient in localization. Experimentally, with only two simple standard features, HOGs and Colornames, the novel CSR-DCF method &#x2013; DCF with Channel and Spatial Reliability &#x2013; achieves state-of-the-art results on VOT 2016, VOT 2015 and OTB. The CSR-DCF runs in real-time on a CPU.

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/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

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

CVPR 2017: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition

ISBN

978-1-5386-0457-1

ISSN

1063-6919

e-ISSN

—

Počet stran výsledku

10

Strana od-do

4847-4856

Název nakladatele

IEEE Computer Society Press

Místo vydání

—

Místo konání akce

Honolulu

Datum konání akce

21. 7. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000418371404099