Suspended Matter Model on Alsat-1 Image by MLP Network and Mathematical Morphology: Prototypes by K-Means

Authors: S. Loumi, H. Merrad, F. Alilat, B. Sansal

Abstract:

In this article, we propose a methodology for the characterization of the suspended matter along Algiers-s bay. An approach by multi layers perceptron (MLP) with training by back propagation of the gradient optimized by the algorithm of Levenberg Marquardt (LM) is used. The accent was put on the choice of the components of the base of training where a comparative study made for four methods: Random and three alternatives of classification by K-Means. The samples are taken from suspended matter image, obtained by analytical model based on polynomial regression by taking account of in situ measurements. The mask which selects the zone of interest (water in our case) was carried out by using a multi spectral classification by ISODATA algorithm. To improve the result of classification, a cleaning of this mask was carried out using the tools of mathematical morphology. The results of this study presented in the forms of curves, tables and of images show the founded good of our methodology.

Keywords: Classification K-means, mathematical morphology, neural network MLP, remote sensing, suspended particulate matter

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1079504

References:

[1] D. K Hall., J. R. Key, Casey K. A., G. A. Riggs , D. J. Cavalieri., " Sea Ice Surface Temperature Product from MODIS," IEEE Trans. Geoscience Remote Sensing, , 2004, vol. 42, no. 5, May pp. 1076-1087.
[2] L. Parkinson, "Aqua: An Earth-Observing Satellite Mission to Examine Water and Other Climate Variables," IEEE Trans Geoscience Remote Sensing, 2003, vol. 41, no. 2, Feb pp. 173-183.
[3] J. M Froidefond , D. Doxaran, " Télédétection Optique Appliquée ├á l-étude de eaux c├┤tières," Télédétection, 2004, vol. 4, no. 2, pp. 157- 174.
[4] H. Merrad, "Caractérisation des Eaux C├┤tières ├á partir d-Images Multi spectrales de MODIS et ALSAT-1 : Application au littoral Algérien, " Thèse de Magister, 2005, Université des Sciences et de la Technologie Houari Boumediene ├á Alger,.
[5] M. Bekhti, A. Oussedik, J.R. Cooksley. " Alsat-1: Conception details and in orbit performance, " Actes des Journées Techniques ALSAT 1/ Utilisateurs, 2003, Juillet 14 et 15 , Alger.
[6] D.B. Patissier, G.H. Tilstone, V.M. Vincente & G.F. Moore, "Comparaison of bio-physical marine products from SeaWiFs, MODIS and a bio-optical model with in situ measurements from Northern European waters," .2004, Journal of Opitcs, pp. 875-889.
[7] D. Doxaran, J. M. Froidefond, S Lavender & P. Castaing, "Spectral signature of highly turbid waters Application with SPOT data to quantify suspended particulate matter," Remote Sensing of Environment, 2002,81, 149-161,
[8] M.Coster ET J. L.Cherman, "Précis d'analyse d'images," 1985, ├ëditions du CNRS.
[9] ] J. Serra. "Image Analysis and Mathematical Morphology," 1982 Academic Press, London.S.
[10] Haykin, "Neural Networks: A Comprehensive Foundation," 1999 Second edition, Prentice Hall.
[11] F. Alilat, S. Loumi, H. Merrad & B. Sansal, "Nouvelle approche du réseau ARTMAP Flou Application ├á la classification multispectrale des images SPOT XS de la baie d-Alger," Revue Fran├ºaise de Photogramétrie et de Télédétection SFPT, (2005-1),.no.177, pp 17-24.
[12] Z. Zhou, Chen & Z. Chen, "FANNC: A Fast Adaptive Neural Network classifier," 2000, Knowledge and Information Systems, Vol. 2, N┬░1, pp. 115-129.
[13] P. Baldi, "Gradient Descent Learning Algorithm Overview: A General Dynamical Systems Perspective," 1995, IEEE Transactions on Neural Networks, Vol. 6.
[14] M. Hagan T. & M .B. Menhaj, "Training Feed forward Networks with the Marquardt Algorithm,", 1994, IEEE Transactions on Neural Networks, Vol.5 No 6.
[15] B.M. Wilamowskin, S. Iplikci, O. Kaynak & Efe, "An Algorithm for fast Convergence in Training Neural Networks," 2001, IJCNN-01, Washington C. c July 15-19 , pp. 1778-1782.