High accuracy local stereo matching using DoG scale map

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00312838" target="_blank" >RIV/68407700:21230/17:00312838 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.23919/MVA.2017.7986850" target="_blank" >http://dx.doi.org/10.23919/MVA.2017.7986850</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.23919/MVA.2017.7986850" target="_blank" >10.23919/MVA.2017.7986850</a>

Jazyk výsledku

angličtina

Název v původním jazyce

High accuracy local stereo matching using DoG scale map

Popis výsledku v původním jazyce

Local matching is one of approaches for stereo matching which needs cost aggregation. In Guided Filter based method proposed by Hosni, the cost map is smoothed by Guided Filter using original image as a guiding image. However, the Guided Filter sometimes fails when there are regions whose textures are same but disparities are different. Thus, parameter tuning for filter size of Guided Filter is difficult to obtain the best accuracy. In this paper we propose an algorithm for automatic filter size selection for each pixel of Guided Filter based stereo matching based on the response of the Different of Gaussian (DoG). In our algorithm, we generate the Filter-Size map whose pixel value for each pixel is appropriate filter size. The value of the Filter-Size map is the largest size of the filtering area around the pixel in interest calculated such that more than two edges are not included in filtering area. In our experiments, we evaluated accuracy of Guided Filter based method with our algorithm for selecting filter size compared with the original Guided Filter based method without our algorithm. By using the Middle-bury datasets, the experimental results shows our algorithm's superiority in accuracy.

Název v anglickém jazyce

High accuracy local stereo matching using DoG scale map

Popis výsledku anglicky

Local matching is one of approaches for stereo matching which needs cost aggregation. In Guided Filter based method proposed by Hosni, the cost map is smoothed by Guided Filter using original image as a guiding image. However, the Guided Filter sometimes fails when there are regions whose textures are same but disparities are different. Thus, parameter tuning for filter size of Guided Filter is difficult to obtain the best accuracy. In this paper we propose an algorithm for automatic filter size selection for each pixel of Guided Filter based stereo matching based on the response of the Different of Gaussian (DoG). In our algorithm, we generate the Filter-Size map whose pixel value for each pixel is appropriate filter size. The value of the Filter-Size map is the largest size of the filtering area around the pixel in interest calculated such that more than two edges are not included in filtering area. In our experiments, we evaluated accuracy of Guided Filter based method with our algorithm for selecting filter size compared with the original Guided Filter based method without our algorithm. By using the Middle-bury datasets, the experimental results shows our algorithm's superiority in accuracy.

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

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

Machine Vision Applications (MVA), 2017 15th IAPR International Conference on

ISBN

978-4-901122-16-0

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

258-261

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Nagoya

Datum konání akce

8. 5. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000426950300064