Abstract
By using sonar imaging, this paper presents a new algorithm for the clustering of seabed types based on the self-organizing feature maps (SOFM) neural network. The theory as well as data processing is studied in detail. Some valuable conclusions and suggestions are given.
Similar content being viewed by others
References
Hughes Clarke J E (1993) The potential for seabed classification using backscatter from shallow water multibeam sonar [C]. The Institute of Acoustics Conference on Acoustic Classification and Mapping of the Seabed, Bath, UK
Hughes Clarke, J E (1994) Towed remote seafloor using the angular response of acoustic backscattering: a case study from multiple overlapping GLORIA data [J]. IEEE Journal of Ocean Engineering, 19(1): 364–374
Pican N, Trucco E, Ross M, et al. (1998) Texture analysis for seabed classification: co-occurrence matrices vs. self-organizing maps[C]. IEEE/OES OCEANS’98 Conference, Nice, France
Tamsett D (1993) Sea-bed characterization and classification from the power spectra of side-scan sonar data[J]. Marine Geophysical Researches, 15: 43–64
Yang Fanlin, Liu Jingnan (2003) Seabed classification using BP neural network based on GA[J]. Acta Oceanologica Sinica, 22(4): 523–531
Zhou Xinghua, Chen Yongqi (2004) Seafloor sediment classification based on multibeam sonar Data [J]. Geo-spatial Information Science, 7(4): 290–296
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the National 863 High-Tech Program of China (No. 2007AA12Z326).
About this article
Cite this article
Zhao, J., Zhang, H., Ma, F. et al. A new algorithm for clustering of seabed types. Geo-spat. Inf. Sci. 11, 279–282 (2008). https://doi.org/10.1007/s11806-008-0158-9
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11806-008-0158-9