Publication detail

Multi-focus thermal image fusion

BENEŠ, R. DVOŘÁK, P. FAÚNDEZ ZANUY, M. ESPINOSA-DURÓ, V. MEKYSKA, J.

Original Title

Multi-focus thermal image fusion

Type

journal article - other

Language

English

Original Abstract

This paper proposes a novel algorithm for multi-focus thermal image fusion. The algorithm is based on local activity analysis and advanced pre-selection of images into fusion process. The algorithm improves the object temperature measurement error up to 5C. The proposed algorithm is evaluated by half total error rate, root mean squared error, cross correlation and visual inspection. To the best of our knowledge, this is the first work devoted to multi-focus thermal image fusion. For testing of proposed algorithm we acquire six thermal image set with objects at different focal depth.

Keywords

image fusion, thermal image, activity level, image preselection

Authors

BENEŠ, R.; DVOŘÁK, P.; FAÚNDEZ ZANUY, M.; ESPINOSA-DURÓ, V.; MEKYSKA, J.

RIV year

2013

Released

1. 4. 2013

ISBN

0167-8655

Periodical

PATTERN RECOGNITION LETTERS

Year of study

34

Number

5

State

Kingdom of the Netherlands

Pages from

536

Pages to

544

Pages count

9

BibTex

@article{BUT95194,
  author="Radek {Beneš} and Pavel {Dvořák} and Marcos {Faúndez Zanuy} and Virginia {Espinosa-Duró} and Jiří {Mekyska}",
  title="Multi-focus thermal image fusion",
  journal="PATTERN RECOGNITION LETTERS",
  year="2013",
  volume="34",
  number="5",
  pages="536--544",
  issn="0167-8655"
}