Segmentation of astronomical images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00222255" target="_blank" >RIV/68407700:21230/14:00222255 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/60461373:22340/14:43897284

Výsledek na webu

<a href="http://dx.doi.org/10.1117/12.2062009" target="_blank" >http://dx.doi.org/10.1117/12.2062009</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1117/12.2062009" target="_blank" >10.1117/12.2062009</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Segmentation of astronomical images

Popis výsledku v původním jazyce

Object detection is one of the most important procedures in astronomical imaging. This paper deals with segmentation of astronomical images based on random forrest classifier. We consider astronomical image data acquired using a photometric system with B, V, R and I filters. Each image is acquired in more realizations. All image realizations are corrected using master dark frame and master flat field obtained as an average of hundreds of images. Then a profile photometry is applied to find possible position of stars. The classifier is trained by B, V, R and I image vectors. Training samples are defined by user using ellipsoidal regions (20 selections for both classes: object, background). A number of objects and their positions are compared with astronomical object catalogue using Euclidean distance. We can conclude that the performance of the presented technique is fully comparable to other SoA algorithms.

Název v anglickém jazyce

Segmentation of astronomical images

Popis výsledku anglicky

Object detection is one of the most important procedures in astronomical imaging. This paper deals with segmentation of astronomical images based on random forrest classifier. We consider astronomical image data acquired using a photometric system with B, V, R and I filters. Each image is acquired in more realizations. All image realizations are corrected using master dark frame and master flat field obtained as an average of hundreds of images. Then a profile photometry is applied to find possible position of stars. The classifier is trained by B, V, R and I image vectors. Training samples are defined by user using ellipsoidal regions (20 selections for both classes: object, background). A number of objects and their positions are compared with astronomical object catalogue using Euclidean distance. We can conclude that the performance of the presented technique is fully comparable to other SoA algorithms.

Druh

D - Stať ve sborníku

CEP obor

JA - Elektronika a optoelektronika, elektrotechnika

OECD FORD obor

—

Projekt

<a href="/cs/project/GA14-25251S" target="_blank" >GA14-25251S: Nelineární obrazové systémy s prostorově variantní bodovou rozptylovou funkcí</a><br>

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2014

Kód důvěrnosti údajů

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

Název statě ve sborníku

Applications of Digital Image Processing XXXVII

ISBN

978-1-62841-244-4

ISSN

0277-786X

e-ISSN

—

Počet stran výsledku

6

Strana od-do

"921722-1"-"921722-6"

Název nakladatele

SPIE

Místo vydání

Bellingham

Místo konání akce

San Diego, California

Datum konání akce

17. 8. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000344014100057