High accuracy local stereo matching using DoG scale map
The result's identifiers
Result code in 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>
Result on the web
<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>
Alternative languages
Result language
angličtina
Original language name
High accuracy local stereo matching using DoG scale map
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Machine Vision Applications (MVA), 2017 15th IAPR International Conference on
ISBN
978-4-901122-16-0
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
258-261
Publisher name
IEEE
Place of publication
Piscataway
Event location
Nagoya
Event date
May 8, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000426950300064