Abstract
Multi-Beam Echo Sounders are often used for classification of seabed type, as there exists a strong link between sonar backscatter and sediment characteristics of the seabed. Most of the methods for seabed classification from MBES backscatter create a highly-dimensional data set of statistical features and then use a combination of Principal Component Analysis and k-means clustering to derive classes. This procedure can be time consuming for contemporary large MBES data sets with millions of records. This paper examines the complexity of one of most commonly used classification approaches and suggests an alternative where feature data set is optimised in terms of dimensionality using computational and visual data mining. Both the original and the optimised method are tested on an MBES backscatter data set and validated against ground truth. The study found that the optimised method improves accuracy of classification and reduced complexity of processing. This is an encouraging result, which shows that bringing together methods from acoustic classification, visual data mining, spatial analysis and remote sensing can support the unprecedented increases in data volumes collected by contemporary acoustic sensors.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Anderson J (2007) Acoustic seabed classification of marine physical and biological landscapes: Introduction. ICES Cooperative Research Report 286. http://info.ices.dk/pubs/crr/crr286/CRR286.pdf. Accessed 26 Feb 2011
Arescon Ltd. (2001) An approach to seabed classification from multi-beam bathymetric sonar data. http://arescon.com/pics/mbeam.pdf. Accessed 15 January, 2013
Augustin JM, Edy C, Savoye B, Le Drezen E (1994) Sonar mosaic computation from multibeam echo sounder. Oceans’94: Proceedings of the Oceans Engineering for Today’s Technology and Tomorrow’s Preservation. Brest, France, p 2:433–438
Bação F, Lobo V, Painho M (2005) Self-organizing maps as substitutes for k-means clustering. In: Sunderam VS, Albada GD, Sloot PMA, Dongarra J (eds) Computational Science–ICCS 2005. Springer, Berlin-Heidelberg, pp 3516:476–483
Bishop YM, Fienberg SE, Holland PW et al (2007) Discrete multivariate analysis: theory and practice. Springer Science + Business Media, New York
Bradley PS, Fayyad UM (1998) Refining initial points for k-means clustering. ICML’98: Proceedings of the Fifteenth International Conference on Machine Learning. Madison, Wisconsin, USA, pp 91–99
Brown CJ, Blondel P (2009) Developments in the application of multibeam sonar backscatter for seafloor habitat mapping. Appl Acoust 70:1242–1247. doi:10.1016/j.apacoust.2008.08.004
Brown C, Limpenny DS, Meadows W (2002) Guidelines for the conduct of benthic studies at aggregate dredging sites, Chapter 3. The Centre for Environment, Fisheries and Aquaculture Science (CEFAS). http://www.marbef.org/qa/documents/ConductofsurveysatMAEsites.pdf. Accessed 09 Apr 2011
Calinski RB, Harabasz J (1974) A dendrite method for cluster analysis. Commun Stat 3:1–27
Campbell JB (2008) Introduction to remote sensing, 4th edn. The Guilford Press, New York
Chivers RC, Emerson N, Burns DR (1990) New acoustic processing for underway surveying. Hydrol J 56:9–17
Collins WT, Preston JM (2002) Multibeam seabed classification. Int Ocean Syst 6(4):12–15
Cullen S (2003) Irish National Seabed Survey - an introductory overview. Hydrogr J 109:22–25
Cutter JGR, Rzhanov Y, Mayer LA (2003) Automated segmentation of seafloor bathymetry from multibeam echosounder data using local Fourier histogram texture features. J Exp Mar Biol Ecol 285–286:355–370. doi:10.1016/S0022-0981(02)00537-3
Demšar U, Harris P, Brunsdon C et al (2013) Principal component analysis on spatial data: an overview. Ann Assoc Am Geogr 103:106–128. doi:10.1080/00045608.2012.689236
Dunn JC (1974) Well seperated clusters and optimal fuzzy partitions. J Cybern 4:95–104
Everitt BS, Landau S, Leese M, Daniel S (2011) Cluster analysis, 5th edn. John Wiley & Sons, West Sussex
Fleiss JL (1981) Statistical methods for rates and proportions. John Wiley & Sons, New York
Goff JA, Kraft BJ, Mayers LA et al (2004) Seabed characterization on the New Jersey middle and outer shelf: correlatability and spatial variability of seafloor sediment properties. Mar Geol 209:147–172
Halkidi M, Bastistakis Y, Vazirgiannis M (2001) On clustering validation techniques. J Intell Inf Syst 17:107–145
Hellequin L (1998) Statistical characterization of multibeam echosounder data. In Proc Oceans’98 IEEE Ocean Conf, Nice, France, pp 228–233
Hellequin L, Boucher JM, Lurton X (2003) Processing of high-frequency multibeam echosounder data for seafloor characterization. In Proc Oceans’98 IEEE Ocean Conf, Nice, France, pp 78–89
Huges Clarke JE, Danforth BW, Valentine P (1997) High frequency acoustics in shallow water. In Proc NATO SACLANTCEN Conf, Lerici, Italy, pp 243–250
Jain AK, Dubes RC (1988) Algorithms for clustering data. Prentice Hall College Div, New Jersey
Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv 31:264–323
Kohonen T (2000) Self-Organizing Maps, 3rd edn. Springer, Berlin
Koua EL, Kraak M-J (2004) Alternative visualization of large geospatial datasets. Cartogr J 41:217–228. doi:10.1179/000870404X13283
Laboratory of Computer and Information Science (LCIS) (2010) SOM Toolbox documentation. http://www.cis.hut.fi/somtoolbox/documentation/. Accessed 1 Dec 2013
Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33:159–174. doi:10.2307/2529310
Lillesand TM, Kiefer RW, Chipman JW (2004) Remote sensing and image interpretation, 5th edn. John Wiley & Sons, New Jersey
Lurton X (2002) An introduction to underwater acoustics: principles and applications. Springer Verlag, Berlin-Heidelberg
Mather P, Koch M (2010) Computer processing of remotely-sensed images: an introduction, 4th edn. John Wiley and Sons, Oxford
Mayer LA (2006) Frontiers in seafloor mapping and visualization. Mar Geophys Res 27:7–17
McGonigle C, Brown C, Quinn R, Grabowski J (2009) Evaluation of image-based multibeam sonar backscatter classification for benthic habitat discrimination and mapping at Stanton Banks, UK. Estuar Coast Shelf Sci 81:423–437. doi:10.1016/j.ecss.2008.11.017
Orlowski A (1984) Application of multiple echoes energy measurements for evaluation of sea bottom type. Oceanologia 19:61–78
Pace NG, Gao H (1988) Swathe seabed classification. IEEE J Ocean Eng 13:83–90
Preston J (2009) Automated acoustic seabed classification of multibeam images of Stanton Banks. Appl Acoust 70:1277–1287
Preston J, Christney A, Bloomer S, Beaudet I (2001) Seabed classification of multibeam sonar images. In Proc Oceans’ 01MTS/IEEE Conf Exhib, Honolulu, USA, pp 2616–2623
Preston JM, Parrott DR, Collins WT, John S (2003) Sediment classification based on repetitive multibeam bathymetry surveys of an offshore disposal site. In Proc Oceans’03 MTS/IEEE Conf Exhib, San Diego, USA, pp 69–75
Preston JM, Christney AC, Collins WT (2004) Automated acoustic classification of sidescan images. In Proc Oceans ’04 MTS/IEEE Conf Exhib, Kobe, Japan
Quester Tangent Corporation (1997) QTC VIEW Operator’s manual and reference, Quester Tangent Corporation. Sidney, BC, Canada, Document Number SR-33-OM01-R01
Renard P, Pfeifer N (2005) Distinguishing features from outliers in automatic kriging-based filtering of MBES data: a comparative study. In: Renard P, Demougeot-Renard H, Froidevaux R (eds) Geostatistics for environmental applications. Springer, Berlin Heidelberg, pp 403–414
Satyanarayana Y, Naithani S, Anu R (2007) Seafloor sediment classification from single beam echo sounder data using LVQ network. Mar Geophys Res 28:95–99. doi:10.1007/s11001-007-9016-7
Simrad-Kongsberg (1999) EM1002 Multibeam echo sounder operator manual, Version C, 1999
Sutherland T, Galloway J (2007) Calibration techniques and sampling resolution requirements for groundtruthing multibeam acoustic backscatter (EM3000) and QTC VIEW™ classification technology. Estuar Coast Shelf Sci 75:447–458. doi:10.1016/j.ecss.2007.05.045
Vesanto J (1999) SOM-based data visualization methods. Intell Data Anal 3:111–126. doi:10.1016/S1088-467X(99)00013-X
Xinghua Z, Yongqi C (2004) Seafloor sediment classification based on multibeam sonar data. Geo Spat Inf Sci 7:290–296
Xinghua Z, Yongqi C (2005) Seafloor classification of multibeam sonar data using neural network approach. Mar Geod 28:201–206
Zimmermann M, Rooper CN (2008) Comparison of echogram measurements against data expectations and assumptions for distinguishing seafloor substrates. Fish Bull 106:293–304
Acknowledgments
The authors would like to thank Geological Survey or Ireland (GSI) for access to the MBES and ground truth data sets and in particular Xavier Monteys from GSI for his generous support and feedback. Research presented in this paper was partially funded by a Strategic Research Cluster grant (07/SRC/I1168) by Science Foundation Ireland under the National Development Plan, when both authors were working at the National Centre for Geocomputation at the National University of Ireland, Maynooth.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ahmed, K.I., Demšar, U. Improving seabed classification from Multi-Beam Echo Sounder (MBES) backscatter data with visual data mining. J Coast Conserv 17, 559–577 (2013). https://doi.org/10.1007/s11852-013-0254-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11852-013-0254-3