Naslov
Histogram-Based Smoke Segmentation in Forest Fire Detection System

Autori
Krstinić, Damir ; Stipaničev, Darko ; Jakovčević, Toni

Izvornik
Information Technology and Control (1392-124X) 38 (2009), 3; 237-244

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
smoke detection; image segmentation; histogram-based segmentation; colorspace evaluation; classifi er design; Bayes classifi er

Sažetak
A focus of this paper is a pixel level analysis and segmentation of smoke colored pixels for the automated forest fi re 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 fi nd an effi cient 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.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA