Using Thresholding Techniques for Object Detection in Infrared Images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60162694%3AG43__%2F14%3A00523130" target="_blank" >RIV/60162694:G43__/14:00523130 - isvavai.cz</a>

Výsledek na webu

<a href="http://vavtest.unob.cz/registr" target="_blank" >http://vavtest.unob.cz/registr</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/MECHATRONIKA.2014.7018315" target="_blank" >10.1109/MECHATRONIKA.2014.7018315</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Using Thresholding Techniques for Object Detection in Infrared Images

Popis výsledku v původním jazyce

The techniques for image format conversion from grayscale to binary could be grouped into two categories: global group and local group. In this paper, we focus on the binarization of a grayscale image using both thresholding techniques. Local binarization methods try to compute thresholds individually for each pixel, using information from the local neighborhood of the pixel. These methods are often slow since the computation of image features from the local neighborhood is to be done for each image pixel. This paper focuses on employing a fast approach to compute local thresholds using the technique of integral sum image. Using this approach we are able to achieve binarization speed close to the global binarization methods. What more, the Otsu methodwas used representing the other techniques in the global category. Global techniques are very fast and they give good results for typical images.

Název v anglickém jazyce

Using Thresholding Techniques for Object Detection in Infrared Images

Popis výsledku anglicky

The techniques for image format conversion from grayscale to binary could be grouped into two categories: global group and local group. In this paper, we focus on the binarization of a grayscale image using both thresholding techniques. Local binarization methods try to compute thresholds individually for each pixel, using information from the local neighborhood of the pixel. These methods are often slow since the computation of image features from the local neighborhood is to be done for each image pixel. This paper focuses on employing a fast approach to compute local thresholds using the technique of integral sum image. Using this approach we are able to achieve binarization speed close to the global binarization methods. What more, the Otsu methodwas used representing the other techniques in the global category. Global techniques are very fast and they give good results for typical images.

Druh

D - Stať ve sborníku

CEP obor

KA - Vojenství

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2014

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 16th International Conference on Mechatronics ? Mechatronika 2014

ISBN

978-80-214-4816-2

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

530-537

Název nakladatele

University of Technology, Brno

Místo vydání

Brno

Místo konání akce

Brno

Datum konání akce

1. 1. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—