FN Archimer Export Format
PT J
TI Seabed segmentation using optimized statistics of sonar textures
BT 
AF KAROUI, I
   FABLET, R
   BOUCHER, J.M.
   AUGUSTIN, Jean-Marie
AS 1:1;2:1;3:1;4:2;
FF 1:;2:;3:;4:PDG-DOP-DCB-NSE-AS;
C1 Ecole Natl Super Telecommun Bretagne, Dept Signal & Commun, F-29238 Brest 3, France.
   IFREMER, Dept Acoust & Seism, F-29280 Brest, France.
C2 TELECOM BRETAGNE, FRANCE
   IFREMER, FRANCE
SI BREST
SE PDG-DOP-DCB-NSE-AS
IN WOS Ifremer jusqu'en 2018
   copubli-france
   copubli-univ-france
IF 2.234
TC 33
UR https://archimer.ifremer.fr/doc/2009/publication-6101.pdf
LA English
DT Article
DE ;level sets;active regions;MMP;segmentation;angular backscattering;feature selection;sonar images;Texture
AB We propose and compare two supervised algorithms of the segmentation of textured sonar images with respect to seafloor types. We characterize sea-floors by a set of empirical distributions estimated on texture responses for a wide set of different filters with various parameterizations and we introduce a novel similarity measure between sonar textures in this feature space. Our similarity measure is defined as a weighted sum of Kullback-Leibler divergences between texture features. The weight setting is twofold. First each filter is weighted according to its discrimination power: the computation of these weights are issued from a margin maximization criterion. Second, an additional weight, evaluated as an angular distance between the incidence angles of the compared texture samples, is considered to take into account sonar image acquisition process that leads to a variability of the backscattered (BS) value and of the texture aspect with the incidence angle range. A Bayesian framework is used in the first algorithm where the conditional likelihoods are expressed using the proposed similarity measure between local pixel statistics and the seafloor prototype statistics. The second method is based in a variational framework as the minimization of a region-based functional that involves the similarity between global region texture based statistics and the predefined prototypes.
PY 2009
PD JUL
SO GEOSCIENCE AND REMOTE SENSING SOCIETY
SN 0196-2892
PU IEEE
VL 47
IS 6
UT 000266409100005
BP 1621
EP 1631
DI 10.1109/TGRS.2008.2006362
ID 6101
ER

EF