Naslov
Histogram based smoke segmentation: Effect of color space transformation

Autori
Krstinić, Damir

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
MIPRO 2008 - 31st International Convention Proceedings: Computers in Technical Systems and Intelligent Systems / - , 2008, 163-168

Skup
MIPRO 2008

Mjesto i datum
Opatija, Hrvatska, 26.05.2008. - 30.05.2008

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Smoke segmentation, histogram, color space transformation, smoke detection

Sažetak
A focus of this work is a pixel level analyses and segmentation of smoke colored pixels for the automated forest fire detection. Variations in the smoke color tones, environmental illumination, atmospheric conditions and low quality of the images of wide outdoor area make smoke detection a complex task. In order to find an efficient combination of a color space and pixel level smoke segmentation algorithm, several color space transformations are evaluated by measuring separability between smoke and non-smoke classes of pixels. However, exhaustive evaluation of the histogram-based smoke segmentation algorithms in different color spaces suggests that the peak performance is the distinctive feature of the algorithm itself rather than the algorithm-color space combination. The best performing algorithm is implemented as one of the smoke detection methods of the Intelligent Forest Fire Monitoring System deployed at several sites on the coastline of the Republic of Croatia.

Izvorni jezik
Engleski

POVEZANOST RADA