The authors present a technique for making use of both sidescan amplitude and bathymetric data provided from sidescan bathymetric sonars for the classification of underwater seabeds. Sidescan amplitude is corrected for physical factors and used to plot ‘processed’ sidescan images. Both amplitude and textural features are derived from these images. Textural features are obtained using 2-D discrete wavelet transforms. Bathymetric images are used to derive features indicating seafloor variability. These features are combined together and the most relevant ones are selected by feature selection algorithms. If grab samples are available, the areas around them are used as training data in a supervised approach. The backpropagation elimination algorithm is used on the training dataset to select relevant features. If training data are not available, an unsupervised approach can be used. The dimensions of the whole dataset are reduced using principal component analysis in this case, and the principal components are used as features. In both cases, clustering techniques are used to cluster the data into sediment classes. The classified points are then plotted against their GIS position in the survey. Classification results correlate with grab sample types from the areas considered (in the supervised case) and with expert observation of sidescan images, where training data is not available.
References
-
-
1)
-
S. Mallat
.
(1998)
A wavelet tour of signal processing.
-
2)
-
H. Barad ,
A.B. Martinez ,
B.S. Bourgeois ,
E.J. Kaminsky
.
Acoustical boundary location through textural analysis of multibeam bathymetric sonar data.
Mar. Technol. Soc. J.
,
1 ,
24 -
30
-
3)
-
I. Daubechies
.
(1992)
Ten lectures on wavelets, CBMS-NSF Regional Conf. Series in Applied Mathematics.
-
4)
-
M. Mignotte ,
C. Collet ,
P. Perez ,
P. Bouthemy
.
Three-class markovian segmentation of high resolution sonar images.
Comput. Vis. Image Underst.
,
3 ,
191 -
204
-
5)
-
Bates, C.R., Moore, G.C., Harries, D.B., Austin, W., Mair, J.: `Broad scale mapping of sublittoral habitats in Loch Laxford, Scotland', F01AA401A, Scottish Natural Heritage Commissional Report, 2002, p. 1–65.
-
6)
-
T. Randen ,
J.H. Husoy
.
Filtering for texture classification: A comparative study.
IEEE Trans. Pattern Anal. Mach. Intell.
,
4 ,
291 -
310
-
7)
-
C.R. Wentworth
.
A scale of grade and class terms for classic sediments.
J. Geol.
,
377 -
392
-
8)
-
R.J. Urick
.
(1967)
Principles of underwater sound for engineers.
-
9)
-
L. Atallah ,
P.J. Probert Smith
.
Wavelet analysis of bathymetricsidescan sonar data for the classification of seafloor sediments in Hopvagen bay - Norway.
Mar. Geophys. Res.
,
431 -
442
-
10)
-
C. Shang ,
K. Brown
.
Feature-based texture classification of sidescan sonar images using a neural network approach.
Electron. Lett.
,
23 ,
2165 -
2167
-
11)
-
G.R. Cochrane ,
K.D. Lafferty
.
Use of acoustic classification of sidescan sonar data for mapping benthic habitat in the Northern Channel Islands, California.
Cont. Shelf Res.
,
683 -
690
-
12)
-
H. Medwin ,
C.S. Clay
.
(1998)
Fundamentals of acoustical oceanography.
-
13)
-
Kingsbury, N.: `The dual tree complex wavelet transform: a new efficient tool for image restoration and enhancement', Proc. European Signal Processing Conf., September 1998.
-
14)
-
D. Alexandrou ,
D. Pantzartzis
.
A methodology for acoustic seafloor classification.
IEEE J. Ocean. Eng.
,
2 ,
81 -
86
-
15)
-
N. Mitchell ,
J.E. Hughes Clarke
.
Classification of seafloor geology using multibeam sonar data from the Scotian shelf.
Mar. Geol.
,
143 -
160
-
16)
-
R.A. Fisher
.
The use of multiple measurements in taxonic problems.
Ann. Eugenics
,
179 -
188
-
17)
-
L. Atallah ,
P.J. Probert Smith
.
Using wavelet analysis to classify and segment sonar signals scattered from underwater sea-beds.
Acta Acust. United With Acust
,
615 -
618
-
18)
-
S. Stanic ,
R.R. Goodman ,
K. Briggs ,
N. Chotiros ,
E. Kennedy
.
Shallow-water bottom reverberation measurements.
IEEE J. Ocean. Eng.
,
3 ,
203 -
209
-
19)
-
P. Cervenka ,
C. de Moustier ,
P.F. Lonsdale
.
Geometric corrections on sidescan sonar images based on bathymetry. Application with SeaMARCII and sea beam data.
Mar. Geophys. Res.
,
365 -
382
-
20)
-
U.C. Herzfeld ,
C.A. Higginson
.
Automated geostatical seafloor classification-principles, parameters, feature vectors and discrimination criteria.
Comput. Geosci.
,
1 ,
35 -
52
-
21)
-
Canepa, G., Pouliquen, E., Pace, N.G., Figoli, A., Franchi, P.: `Validation of a seafloor segmentation algorithm for multibeam data', Proc. ECUA 2002, June 2002, 1, p. 89–94.
-
22)
-
Bates, C.R., Whitehead, E.J.: `Echo plus Measurements in Hopvagen bay, Norway', Presented at the Biennial Scientific Meeting of the Oceanography Society, April 2001.
-
23)
-
P. Scheunders ,
S. Livens ,
G. Van de Wouver ,
P. Vautrot ,
D. Van Dyck
.
Wavelet-based texture analysis.
Int. J. Comput. Sci. Inf. Manage.
-
24)
-
A.C. Bovik ,
M. Clark ,
W.S. Geisler
.
Multichannel texture analysis using localized spatial filters.
IEEE Trans. Pattern Anal. Mach. Intell.
,
1 ,
55 -
73
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-rsn_20040279
Related content
content/journals/10.1049/ip-rsn_20040279
pub_keyword,iet_inspecKeyword,pub_concept
6
6