A PSO-based End-Member Selection Method for Spectral Unmixing of Multispectral Satellite Images

Authors: Mahamed G.H. Omran, Andries P Engelbrecht, Ayed Salman

Abstract:

An end-member selection method for spectral unmixing that is based on Particle Swarm Optimization (PSO) is developed in this paper. The algorithm uses the K-means clustering algorithm and a method of dynamic selection of end-members subsets to find the appropriate set of end-members for a given set of multispectral images. The proposed algorithm has been successfully applied to test image sets from various platforms such as LANDSAT 5 MSS and NOAA's AVHRR. The experimental results of the proposed algorithm are encouraging. The influence of different values of the algorithm control parameters on performance is studied. Furthermore, the performance of different versions of PSO is also investigated.

Keywords: End-members selection, multispectral satellite imagery, particle swarm optimization, spectral unmixing.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1333168

References:

[1] J. Saghri, A. Tescher, M. Omran, Class-Prioritized Compression of Multispectral Imagery Data, Journal of Electronic Imaging, vol. 11 (2), 246-256, 2002.
[2] J. Kennedy, R. Eberhart, Swarm Intelligence, Morgan Kaufmann, 2001.
[3] J. J. Settle, N. A. Drake, Linear Mixing and Estimation of Ground Cover Proportions, International Journal in Remote Sensing, vol. 14 (6), 1159- 1177, 1993.
[4] J. Antoniades, D. Haas, P. Palmadesso, M. Baumback, L. J. Rickard, Use of Filter Vectors in Hyperspectral Data Analysis, In Proceedings of SPIE, vol. 2553, 128-139, 1995.
[5] A. Hlavka, M. A. Spanner, Unmixing AVHRR Imagery to Access Clearcuts and Forest Regrowth on Oregon, IEEE Transactions on Geoscience and Remote Sensing, vol. 33, 788-795, 1995.
[6] A. Bateson, B. Curtiss, A Method for Manual Endmember Selection and Spectral Unmixing, Remote Sensing of Enviornment, vol. 55, 229-243, 1996.
[7] F. Maselli, Multiclass Spectral Decomposition of Remotely Sensed Scenes by Selective Pixel Unmixing, IEEE Transactions on Geoscience and Remote Sensing, vol. 36 (5), 1809-1819, 1998.
[8] L. Parra, C. Spence, P. Sajda, A. Ziehe, K. M├╝ller, Unmixing Hyperspectral Data, In Advances in Neural Information Processing Systems 12, MIT Press, 942-948, 2000.
[9] J. Saghri, A. Tescher, F. Jaradi, M. Omran, A Viable End-Member Selection Scheme for Spectral Unmixing of Multispectral Satellite Imagery Data, Journal of Imaging Science and Technology, vol. 44 (3), 196-203, 2000.
[10] A. Plaza, P. Martinez, R. Perez, J. Plaza, A Quantitative and Comparative Analysis of Endmember Extraction Algorithms from Hyperspectral Data, IEEE Transactions on Geoscience and Remote Sensing, vol. 42(3), 650-663, 2004.
[11] J. Crespo, R. Duro, F. Lopez-Pena, Spectral Unmixing Through Gaussian Synapse ANNs in Hyperspecteal Images, Proceedings of the 8th International Conference on Knowledge-Based Intelligent Information and Engineering Systems, Wellington, New Zealand, 661-668, 2004.
[12] M. Grana, A. D'Anjou, Feature Extraction by Linear Spectral Unmixing, Proceedings of the 8th International Conference on Knowledge-Based Intelligent Information and Engineering Systems, Wellington, New Zealand, 692-698, 2004.
[13] J. Zhang, B. Rivard, A. Sanchez-Azofeifa, Derivative Spectral Unmixing of Hyperspectral Data Applied to Mixtures of Lichen and Rock, IEEE Transactions on Geoscience and Remote Sensing, vol. 42(9), 1934-1940, 2004.
[14] S. McDonald, K. Niemann, D. Goodenough, Development of Hyperspectral Biochemistry through the use of Statistical Modeling and Spectral Unmixing, Proceedings of the IEEE International Geoscince and Remote Sensing Symposium, vol. 2, 1007-1009, 2004.
[15] M. Cauguy, M. Roggemann, T. Schulz, Spectral Unmixing Methods to Estimate Materials on Satellite Surface, Proceedings of the 36th Southeastern Symposium on System Theory, 11-15, 2004.
[16] J. Settle, On the Residual Term in Linear Mixture Model and its Dependence on the Point Spread Function, IEEE Transactions on Geoscience and Remote Sensing, vol. 43(2), 398-401, 2005.
[17] J. Broadwater, R. Meth and R. Chellappa, A hybrid Algorithm for Subpixel Detection in Hyperspectral Imagery, Proceedings of the IEEE International Geoscince and Remote Sensing Symposium, vol. 3, 1601- 1604, 2004.
[18] C. Shah, P. Varshney, A Higher Order Statistical Appraoch to Spectral Unmixing of Remote Sensing Imagery, Proceedings of the IEEE International Geoscince and Remote Sensing Symposium, vol. 2, 1065- 1068, 2004.
[19] G. Ball and D. Hall, A Clustering Technique for Summarizing Multivariate Data, Behavioral Science, vol. 12, 153-155, 1967.
[20] J. Kennedy, R. Eberhart, Particle Swarm Optimization, Proceedings of IEEE International Conference on Neural Networks, Perth, Australia, vol. 4, 1942-1948, 1995.
[21] A. Engelbrecht, Computational Intelligence: An Introduction, John Wiley and Sons, 2002.
[22] Y. Shi, R. Eberhart, Parameter Selection in Particle Swarm Optimization, Evolutionary Programming VII: Proceedings of EP 98, 591-600, 1998.
[23] P. Suganthan, Particle Swarm Optimizer with Neighborhood Optimizer, Proceedings of the Congress on Evolutionary Computation, 1958-1962, 1999.
[24] Y. Shi, R. Eberhart, A Modified Particle Swarm Optimizer, Proceedings of the IEEE International Conference on Evolutionary Computation, Piscataway, NJ, 69-73, 1998.
[25] J. Kennedy, Small Worlds and Mega-Minds: Effects of Neighborhood Topology on Particle Swarm Performance, Proceedings of the Congress on Evolutionary Computation, 1931-1938, 1999.
[26] J. Kennedy, R. Mendes, Population Structure and Particle Performance, Proceedings of the IEEE Congress on Evolutionary Computation, Honolulu, Hawaii, 2002.
[27] F. Van den Bergh, An Analysis of Particle Swarm Optimizers, PhD Thesis, Department of Computer Science, University of Pretoria, 2002.
[28] F. van den Bergh, A.P. Engelbrecht, A New Locally Convergent Particle Swarm Optimizer, Proceedings of the IEEE Conference on Systems, Man, and Cybernetics, Hammamet, Tunisia, 2002.