Nalazite se na CroRIS probnoj okolini. Ovdje evidentirani podaci neće biti pohranjeni u Informacijskom sustavu znanosti RH. Ako je ovo greška, CroRIS produkcijskoj okolini moguće je pristupi putem poveznice www.croris.hr
izvor podataka: crosbi

Wildfire smoke-detection algorithms evaluation (CROSBI ID 571117)

Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija

Jakovčević, Toni ; Šerić, Ljiljana ; Stipaničev, Darko ; Krstinić, Damir Wildfire smoke-detection algorithms evaluation // 6th International Conference on Forest Fire Research : proceedings / Viegas, D. (ur.). Coimbra: ADAI/CEIF, 2010. str. 52-1-52-12

Podaci o odgovornosti

Jakovčević, Toni ; Šerić, Ljiljana ; Stipaničev, Darko ; Krstinić, Damir

engleski

Wildfire smoke-detection algorithms evaluation

In recent years the interest for terrestrial wildfire smoke detection systems has increased, particularly those based on video systems sensitive in visible and/or infrared (IR) spectra. Although many video based smoke-detection algorithms have been developed and applied in various experimental or real life applications, the standard method for evaluating their quality has not yet been proposed and the standard databases of smoke and no-smoke images and video sequences suitable for standard algorithms testing have not been defined. This paper proposes such a methodology suitable for smoke-detection algorithms testing and evaluation. Various measures for smoke-detection algorithms evaluation have been introduced and a database suitable for off-line algorithms testing is defined. The evaluation is based on notation of observer, the formal theory of perception and signal detection theory. The referent observer (usually the human referent observer) determines the real state of phenomena. In the case of video based smoke detection algorithms, analysed images are considered as a collection of pixels, where each pixel belongs to one of two sets: smoke or no-smoke, and this process of pixel classification is present on both levels: objective level and perceived (or observer) level. Multiple measures based on these two sets are introduced to describe the quality of the observer regarding single image analysis as well as image sequence analysis.

smoke detection; wildfire; image processing; detection quality; receiver operating characteristics

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

Podaci o prilogu

52-1-52-12.

2010.

objavljeno

Podaci o matičnoj publikaciji

6th International Conference on Forest Fire Research : proceedings

Viegas, D.

Coimbra: ADAI/CEIF

0000-0000

Podaci o skupu

Nepoznat skup

poster

29.02.1904-29.02.2096

Povezanost rada

nije evidentirano