Adaptive Detection of Single-Color Marker with WebGL

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F20%3A50017044" target="_blank" >RIV/62690094:18450/20:50017044 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-030-58465-8_29" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-030-58465-8_29</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-58465-8_29" target="_blank" >10.1007/978-3-030-58465-8_29</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Adaptive Detection of Single-Color Marker with WebGL

Popis výsledku v původním jazyce

This paper presents a method for real-time single-color marker detection. The algorithm is based on our previous work, and the goal of this paper is to investigate and test possible enhancements that can be done, namely color weighting, hue calculation, and modified versions of dilatation and erosion operations. The paper also explains a solution for dynamic color selection, which makes the system more robust to varying lighting conditions by detecting the color hue, saturation, and value under the current conditions. The designed methods are implemented in WebGL, which allows running the developed application on any platform with any operating system, given WebGL is supported by the web browser. Testing of all described and implemented improvements was conducted, and it revealed that using hue weighting has a good effect on the resulting detection. On the other hand, dynamic thresholding of saturation and value components of the HSV color model does not give good results. Therefore, testing for finding the right threshold for these components had to be done. The erosion operation improves the detection significantly while dilatation does not have almost any impact on the result.

Název v anglickém jazyce

Adaptive Detection of Single-Color Marker with WebGL

Popis výsledku anglicky

This paper presents a method for real-time single-color marker detection. The algorithm is based on our previous work, and the goal of this paper is to investigate and test possible enhancements that can be done, namely color weighting, hue calculation, and modified versions of dilatation and erosion operations. The paper also explains a solution for dynamic color selection, which makes the system more robust to varying lighting conditions by detecting the color hue, saturation, and value under the current conditions. The designed methods are implemented in WebGL, which allows running the developed application on any platform with any operating system, given WebGL is supported by the web browser. Testing of all described and implemented improvements was conducted, and it revealed that using hue weighting has a good effect on the resulting detection. On the other hand, dynamic thresholding of saturation and value components of the HSV color model does not give good results. Therefore, testing for finding the right threshold for these components had to be done. The erosion operation improves the detection significantly while dilatation does not have almost any impact on the result.

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

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

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

Název statě ve sborníku

Augmented Reality, Virtual Reality, and Computer Graphics

ISBN

978-3-030-58464-1

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

16

Strana od-do

395-410

Název nakladatele

Springer Nature Switzerland AG 2020

Místo vydání

Berlín

Místo konání akce

Lecce, Italy

Datum konání akce

7. 9. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000713422700029