Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2010, Vol. 7, No. 2, pp. 35-42
More precise automatic burnt out forest places
space detection using HRV, HRVIR data
V.Y. Efremov
, A.A. Zlatopolsky
, A.A. Mazurov
Space Research Institute, 117997, 84/32 Profsoyuznaya Str, Moscow, Russia
More precise automatic burnt out forest places space detection using high resolution satellite data (SPOT-2 and
SPOT - 4) is developed for the Russian National Forest Fire Protection Agency monitoring service (ISDM Rosleshoz).
Automatic burnt out forest places detection algorithm based on the dark segments analysis is proposed and
discussed in the paper. Fire region is detected beforehand using low resolution IR MODIS data. Test results for the
ISDM Rosleshoz are positive, in general. Main problems and algorithm development area are described.
Keywords: burnt out forest places detection, edge detection, segmentation, histogram analysis, region growing
Full text