The proposed algorithms for unsupervised classication of hyperspectral imaging data have been shown to be ecient, leading to promising results when applied to real-world benchmark hyperspectral data. However, there are issues and limitations that could be considered in possible future work.
The proposed outlier robust geodesic K-means was proven to be eective at improving the clustering accuracy of remote sensing test hyperspectral images. However, this algo-rithm involves the computation of geodesic distances over a shared nearest neighborhood connectivity graph that is prone to be computationally expensive. Dependency on pair-wise geodesic distance can diminish the eciency of the proposed outlier robust geodesic K-means for large-scale real-world hyperspectral data and time-demanding applications.
The results obtained by the two proposed Mmulti-manifold Spectral Clustering algo-rithms dictate that clustering based on the multi-manifold assumption compared to clus-tering based on the traditional manifold learning algorithms, built on a single manifold assumption, such as PCA, LLE and LTSA is more promising and well-tted to hyper-spectral image classication both in terms of accuracy and precision. These algorithms revealed to be successful in dealing with hyperspectral data containing data clusters with overlapping structures.
7.2 Discussion 101
However, these proposed multi-manifold-based algorithms seem to not be quite as ef-fective when there are high spectral similarities or signicant intersections among data clusters, e.g. as observed in the case of the Salinas dataset between the untrained grape and the untrained vineyard land-cover classes. This can be explained by the strong re-liance of these methods on a nearest neighborhood connectivity model to estimate the data anities that become inecient with overlapping data clusters with a high degree of intersections. Moreover, the current development of the proposed algorithms only incorporated the standard spectral clustering that relies on the computation of pairwise data anities. This can also bring about high space and time complexities when dealing with large sample-size remote sensing hyperspectral imaging data.
The proposed Sequential Spectral Clustering (SSC) algorithm is built over a bipartite graph representation aiming to alleviate the complexity of the clustering algorithm. This algorithm was successfully applied to ve popular hyperspectral benchmark datasets in-cluding Botswana, Salinas, Indian Pines, Pavia Center Scene and Pavia University Scene datasets. The obtained results have proven the eciency of the proposed SSC algorithm.
The present implementation of this algorithm was particularly developed in order to re-duce the computational complexity of the standard spectral clustering algorithm based on the Radial Basis Function (RBF) similarity kernel. However, it would be worthwhile to explore the eciency of the proposed SSC within a multi-manifold or a spatio-spectral framework for remote sensing hyperspectral image unsupervised classication.
102 7. Conclusions
Bibliography
[1] Salinas dataset. http://www.ehu.eus/ccwintco/index.php/Hyperspectral_
Remote_Sensing_Scenes. Accessed: 2018-12-08.
[2] Acito, N., Corsini, G., and Diani, M. An unsupervised algorithm for hyper-spectral image segmentation based on the gaussian mixture model. In IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Pro-ceedings (IEEE Cat. No.03CH37477) (July 2003), vol. 6, pp. 37453747 vol.6.
[3] Aggarwal, C. C., Hinneburg, A., and Keim, D. A. On the surprising behavior of distance metrics in high dimensional space. In Database Theory ICDT 2001 (Berlin, Heidelberg, 2001), J. Van den Bussche and V. Vianu, Eds., Springer Berlin Heidelberg, pp. 420434.
[4] Alhichri, H., Ammour, N., Alajlan, N., and Bazi, Y. Clustering of hy-perspectral images with an ensemble method based on fuzzy c-means and markov random elds. Arabian Journal for Science and Engineering 39, 5 (May 2014), 37473757.
[5] Alvarez-Taboada, F., Paredes, C., and Julián-Pelaz, J. Mapping of the invasive species hakea sericea using unmanned aerial vehicle (uav) and worldview-2 imagery and an object-oriented approach. Remote Sensing 9, 9 (2017).
[6] Arias-Castro, E., Chen, G., and Lerman, G. Spectral clustering based on local linear approximations. Electron. J. Statist. 5 (2011), 15371587.
[7] Arias-Castro, E., Lerman, G., and Zhang, T. Spectral clustering based on local pca. arXiv preprint arXiv:1301.2007 (2013).
[8] Asgharbeygi, N., and Maleki, A. Geodesic k-means clustering. In Pattern Recognition, 2008. ICPR 2008. 19th International Conference on (Tampa, FL, USA, Dec 2008), IEEE, pp. 14.
[9] Atzberger, C. Advances in remote sensing of agriculture: Context description, existing operational monitoring systems and major information needs. Remote Sensing 5, 2 (2013), 949981.
[10] Bachmann, C. M., Ainsworth, T. L., and Fusina, R. A. Exploiting manifold geometry in hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing 43, 3 (March 2005), 441454.
103
104 BIBLIOGRAPHY
[11] Ball, G. H., and Hall, D. J. A clustering technique for summarizing multi-variate data. Behavioral Science 12, 2 (March 1967), 153155.
[12] Bandyopadhyay, S., Maulik, U., and Mukhopadhyay, A. Multiobjective genetic clustering for pixel classication in remote sensing imagery. IEEE Trans-actions on Geoscience and Remote Sensing 45, 5 (May 2007), 15061511.
[13] Barbará, D., and Chen, P. Using the fractal dimension to cluster datasets.
In Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (New York, NY, USA, 2000), KDD '00, ACM, pp. 260 264.
[14] Belkin, M., and Niyogi, P. Laplacian eigenmaps and spectral techniques for embedding and clustering. In Advances in Neural Information Processing Systems 14, T. G. Dietterich, S. Becker, and Z. Ghahramani, Eds. MIT Press, 2002, pp. 585 591.
[15] Bellman, R. E. Adaptive control processes: a guided tour, vol. 2045. Princeton university press, 2015.
[16] Bengio, Y., Courville, A., and Vincent, P. Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 8 (Aug 2013), 17981828.
[17] Bengio, Y., and Monperrus, M. Non-local manifold tangent learning. In Advances in Neural Information Processing Systems 17, L. K. Saul, Y. Weiss, and L. Bottou, Eds. MIT Press, 2005, pp. 129136.
[18] Beyer, K., Goldstein, J., Ramakrishnan, R., and Shaft, U. When is near-est neighbor meaningful? In Database Theory ICDT'99 (Berlin, Heidelberg, 1999), C. Beeri and P. Buneman, Eds., Springer Berlin Heidelberg, pp. 217235.
[19] Bezdek, J. C. Pattern Recognition with Fuzzy Objective Function Algorithms.
Kluwer Academic Publishers, Norwell, MA, USA, 1981.
[20] Bhatta, B. Remote Sensing and GIS. Advances in geographic information science.
Oxford University Press, 2008.
[21] Bichot, C.-E. General Introduction to Graph Partitioning. Wiley-Blackwell, 2013, ch. 1, pp. 125.
[22] Bilgin, G., Erturk, S., and Yildirim, T. Unsupervised classication of hyperspectral-image data using fuzzy approaches that spatially exploit member-ship relations. IEEE Geoscience and Remote Sensing Letters 5, 4 (Oct 2008), 673677.
[23] Björck, A., and Golub, G. H. Numerical methods for computing angles be-tween linear subspaces. Mathematics of Computation 27, 123 (1973), 579594.
[24] Borengasser, M., Hungate, W. S., and Watkins, R. Hyperspectral remote sensing: principles and applications. CRC press, 2007.
BIBLIOGRAPHY 105
[25] Boser, B. E., Guyon, I. M., and Vapnik, V. N. A training algorithm for optimal margin classiers. In Proceedings of the fth annual workshop on Compu-tational learning theory (1992), ACM, pp. 144152.
[26] Brando, V. E., and Dekker, A. G. Satellite hyperspectral remote sensing for estimating estuarine and coastal water quality. IEEE Transactions on Geoscience and Remote Sensing 41, 6 (June 2003), 13781387.
[27] Breunig, M. M., Kriegel, H.-P., Ng, R. T., and Sander, J. Lof: Identifying density-based local outliers. In Proceedings of the 2000 ACM SIGMOD Interna-tional Conference on Management of Data (New York, NY, USA, 2000), SIGMOD '00, ACM, pp. 93104.
[28] Campbell, J. B., and Wynne, R. H. Introduction to remote sensing. Guilford Press, 2011.
[29] Cariou, C., and Chehdi, K. Unsupervised nearest neighbors clustering with application to hyperspectral images. IEEE Journal of Selected Topics in Signal Processing 9, 6 (Sept 2015), 11051116.
[30] Cariou, C., and Chehdi, K. A new k-nearest neighbor density-based clustering method and its application to hyperspectral images. In 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (July 2016), pp. 61616164.
[31] Chan, P. K., Schlag, M. D. F., and Zien, J. Y. Spectral k-way ratio-cut partitioning and clustering. IEEE Transactions on Computer-Aided Design of In-tegrated Circuits and Systems 13, 9 (Sep 1994), 10881096.
[32] Chen, B., Gao, B., Liu, T.-Y., Chen, Y.-F., and Ma, W.-Y. Fast spec-tral clustering of data using sequential matrix compression. In Machine Learn-ing: ECML 2006 (Berlin, Heidelberg, 2006), J. Fürnkranz, T. Scheer, and M. Spiliopoulou, Eds., Springer Berlin Heidelberg, pp. 590597.
[33] Chen, F., Wang, K., de Voorde, T. V., and Tang, T. F. Mapping urban land cover from high spatial resolution hyperspectral data: An approach based on simultaneously unmixing similar pixels with jointly sparse spectral mixture analy-sis. Remote Sensing of Environment 196 (2017), 324 342.
[34] Choe, E., van der Meer, F., van Ruitenbeek, F., van der Werff, H., de Smeth, B., and Kim, K.-W. Mapping of heavy metal pollution in stream sediments using combined geochemistry, eld spectroscopy, and hyperspectral re-mote sensing: A case study of the rodalquilar mining area, se spain. Rere-mote Sensing of Environment 112, 7 (2008), 3222 3233.
[35] Chung, F. R., and Graham, F. C. Spectral graph theory. No. 92. American Mathematical Soc., 1997.
[36] Clark, P. E., and Rilee, M. L. Remote sensing tools for exploration: observing and interpreting the electromagnetic spectrum. Springer Science & Business Media, 2010.
106 BIBLIOGRAPHY
[37] Clark, R., Boardman, J., Mustard, J., Kruse, F., Ong, C., Pieters, C., and Swayze, G. Mineral mapping and applications of imaging spectroscopy.
In 2006 IEEE International Symposium on Geoscience and Remote Sensing (July 2006), pp. 19861989.
[38] Cohen, J. A coecient of agreement for nominal scales. Educational and Psycho-logical Measurement 20, 1 (1960), 3746.
[39] Cox, M., and Cox, T. Multidimensional Scaling. Springer, 2018, pp. 315347.
[40] Cui, L., Li, G., Ren, H., He, L., Liao, H., Ouyang, N., and Zhang, Y.
Assessment of atmospheric correction methods for historical landsat tm images in the coastal zone: A case study in jiangsu, china. European Journal of Remote Sensing 47, 1 (2014), 701716.
[41] Deutsch, S., and Medioni, G. Intersecting manifolds: Detection, segmentation, and labeling. In Proceedings of the 24th International Conference on Articial Intelligence (2015), IJCAI'15, AAAI Press, pp. 34453452.
[42] Ding, C. H. Q., He, X., Zha, H., Gu, M., and Simon, H. D. A min-max cut algorithm for graph partitioning and data clustering. In Proceedings 2001 IEEE International Conference on Data Mining (2001), pp. 107114.
[43] Ding, S., Chen, L., and Li, J. Dimension reduction of local manifold learn-ing algorithm for hyperspectral image classication. Intelligent Image and Video Interpretation: Algorithms and Applications: Algorithms and Applications (2013), 217.
[44] Donath, W. E., and Hoffman, A. J. Lower bounds for the partitioning of graphs. IBM Journal of Research and Development 17, 5 (Sept 1973), 420425.
[45] Dong, P., and Chen, Q. LiDAR Remote Sensing and Applications. CRC Press, 2017.
[46] Donoho, D. L., and Grimes, C. Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data. Proceedings of the National Academy of Sciences 100, 10 (2003), 55915596.
[47] E.H., G., and Sam, T. Stochastic neighbor embedding. In Advances in Neural Information Processing Systems 15, S. Becker, S. Thrun, and K. Obermayer, Eds.
MIT Press, 2003, pp. 857864.
[48] Elhamifar, E., and Vidal, R. Sparse manifold clustering and embedding. In Advances in Neural Information Processing Systems 24, J. Shawe-Taylor, R. Zemel, P. Bartlett, F. Pereira, and K. Weinberger, Eds. Curran Associates, Inc., 2011, pp. 5563.
[49] ElMasry, G. M., and Nakauchi, S. Image analysis operations applied to hyperspectral images for non-invasive sensing of food quality â a comprehensive review. Biosystems Engineering 142 (2016), 53 82.
BIBLIOGRAPHY 107
[50] Ertöz, L., Steinbach, M., and Kumar, V. Finding Clusters of Dierent Sizes, Shapes, and Densities in Noisy, High Dimensional Data. In SDM (2003), D. Barbará and C. Kamath, Eds., SIAM.
[51] Evans, J., van Donkelaar, A., Martin, R. V., Burnett, R., Rainham, D. G., Birkett, N. J., and Krewski, D. Estimates of global mortality at-tributable to particulate air pollution using satellite imagery. Environmental Re-search 120 (2013), 33 42.
[52] Fan, M., Qiao, H., Zhang, B., and Zhang, X. Isometric multi-manifold learning for feature extraction. In 2012 IEEE 12th International Conference on Data Mining (Dec 2012), pp. 241250.
[53] Farrell, M. D., and Mersereau, R. M. Robust automatic clustering of hy-perspectral imagery using non-gaussian mixtures. In Image and Signal Processing for Remote Sensing X (2004), vol. 5573, International Society for Optics and Pho-tonics, pp. 161173.
[54] Fialko, Y., Sandwell, D., Simons, M., and Rosen, P. Three-dimensional deformation caused by the bam, iran, earthquake and the origin of shallow slip decit. Nature 435 (May 2005), 295 EP .
[55] Fodor, I. K. A survey of dimension reduction techniques. Center for Applied Scientic Computing, Lawrence Livermore National Laboratory 9 (2002), 118.
[56] Foody, G. M. The eect of mis-labeled training data on the accuracy of supervised image classication by svm. In 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (July 2015), pp. 49874990.
[57] Foody, G. M., Pal, M., Rocchini, D., Garzon-Lopez, C. X., and Bastin, L. The sensitivity of mapping methods to reference data quality: Training su-pervised image classications with imperfect reference data. ISPRS International Journal of Geo-Information 5, 11 (2016), 199.
[58] Francois, D., Wertz, V., and Verleysen, M. The concentration of fractional distances. Knowledge and Data Engineering, IEEE Transactions on 19, 7 (July 2007), 873886.
[59] Franklin, S. E. Remote sensing for sustainable forest management. CRC Press, 2001.
[60] Gao, B. C., Davis, C., and Goetz, A. A review of atmospheric correction techniques for hyperspectral remote sensing of land surfaces and ocean color. In 2006 IEEE International Symposium on Geoscience and Remote Sensing (July 2006), pp. 19791981.
[61] Gerard-Marchant, P. G. Manipulating Environmental Time Series in Python/Numpy: the Scikits.Timeseries Package and its Applications. AGU Fall Meeting Abstracts (Dec. 2008).
108 BIBLIOGRAPHY
[62] Gilbert, M., Xiao, X., Pfeiffer, D. U., Epprecht, M., Boles, S., Czar-necki, C., Chaitaweesub, P., Kalpravidh, W., Minh, P. Q., Otte, M. J., Martin, V., and Slingenbergh, J. Mapping h5n1 highly pathogenic avian inuenza risk in southeast asia. Proc Natl Acad Sci U S A 105, 12 (Mar 2008), 47694774.
[63] Gillis, N., Kuang, D., and Park, H. Hierarchical clustering of hyperspectral images using rank-two nonnegative matrix factorization. IEEE Transactions on Geoscience and Remote Sensing 53, 4 (April 2015), 20662078.
[64] Gionis, A., Hinneburg, A., Papadimitriou, S., and Tsaparas, P. Dimension induced clustering. In Proceedings of the Eleventh ACM SIGKDD International Conference on Knowledge Discovery in Data Mining (New York, NY, USA, 2005), KDD '05, ACM, pp. 5160.
[65] Giustarini, L., Hostache, R., Matgen, P., Schumann, G. J. ., Bates, P. D., and Mason, D. C. A change detection approach to ood mapping in urban areas using terrasar-x. IEEE Transactions on Geoscience and Remote Sensing 51, 4 (April 2013), 24172430.
[66] Goetz, A. F., Vane, G., Solomon, J. E., and Rock, B. N. Imaging spec-trometry for earth remote sensing. Science 228, 4704 (1985), 11471153.
[67] Goldberg, A. B., Zhu, X., Singh, A., Xu, Z., and Nowak, R. D. Multi-manifold semi-supervised learning. In AISTATS (2009), pp. 169176.
[68] Gong, D., Zhao, S., and Medioni, G. Robust multiple manifolds structure learning. CoRR abs/1206.4624 (2012).
[69] Goodenough, D. G., Chen, H., Gordon, P., Niemann, K. O., and Quinn, G. Forest applications with hyperspectral imaging. In 2012 IEEE International Geoscience and Remote Sensing Symposium (July 2012), pp. 73097312.
[70] Grekousis, G., Mountrakis, G., and Kavouras, M. An overview of 21 global and 43 regional land-cover mapping products. International Journal of Remote Sensing 36, 21 (2015), 53095335.
[71] Gudex-Cross, D., Pontius, J., and Adams, A. Enhanced forest cover mapping using spectral unmixing and object-based classication of multi-temporal landsat imagery. Remote Sensing of Environment 196 (2017), 193204.
[72] Guo, Q., Li, H., Chen, W., Shen, I., and Parkkinen, J. Manifold clustering via energy minimization. In Machine Learning and Applications, 2007. ICMLA 2007. Sixth International Conference on (Dec 2007), pp. 375380.
[73] Hagen, L., and Kahng, A. B. New spectral methods for ratio cut partition-ing and clusterpartition-ing. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 11, 9 (Sep 1992), 10741085.
[74] Hassanzadeh, A., Kaarna, A., and Kauranne, T. Unsupervised Multi-manifold Classication of Hyperspectral Remote Sensing Images with Contractive Autoencoder. Springer International Publishing, Cham, 2017, pp. 169180.
BIBLIOGRAPHY 109
[75] Hassanzadeh, A., Kauranne, T., and Kaarna, A. A multi-manifold clus-tering algorithm for hyperspectral remote sensing imagery. In 2016 IEEE In-ternational Geoscience and Remote Sensing Symposium (IGARSS) (July 2016), pp. 33263329.
[76] Hassanzadeh, A., Kauranne, T., and Kaarna, A. A multi-manifold clus-tering algorithm for hyperspectral remote sensing imagery. In 2016 IEEE In-ternational Geoscience and Remote Sensing Symposium (IGARSS) (July 2016), pp. 33263329.
[77] He, X., and Niyogi, P. Locality preserving projections. In Advances in Neural Information Processing Systems 16, S. Thrun, L. K. Saul, and P. B. Schölkopf, Eds. MIT Press, 2004, pp. 153160.
[78] Hettiarachchi, R., and Peters, J. Multi-manifold {LLE} learning in pattern recognition. Pattern Recognition 48, 9 (2015), 2947 2960.
[79] Houle, M. E., Kriegel, H.-P., Kröger, P., Schubert, E., and Zimek, A.
Can shared-neighbor distances defeat the curse of dimensionality? In Scientic and Statistical Database Management, M. Gertz and B. Ludäscher, Eds., vol. 6187 of Lecture Notes in Computer Science. Springer Berlin Heidelberg, 2010, pp. 482500.
[80] Huang, L., Yan, D., Taft, N., and Jordan, M. I. Spectral clustering with per-turbed data. In Advances in Neural Information Processing Systems 21, D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou, Eds. Curran Associates, Inc., 2009, pp. 705712.
[81] Huo, X., Ni, X. S., and Smith, A. K. A survey of manifold-based learning methods. Recent advances in data mining of enterprise data (2007), 691745.
[82] International Society for Optics and Photonics. Using of both hyperspec-tral aerial sensing and RPAS multispechyperspec-tral sensing for potential archaeological sites detection (2018), vol. 10780.
[83] Jarvis, R., and Patrick, E. A. Clustering using a similarity measure based on shared near neighbors. Computers, IEEE Transactions on C-22, 11 (Nov 1973), 10251034.
[84] Jia, P., Yin, J., Huang, X., and Hu, D. Incremental laplacian eigenmaps by preserving adjacent information between data points. Pattern Recognition Letters 30, 16 (2009), 1457 1463.
[85] Jin-wen, M. L. T. Anomaly detection algorithm for hyperspectral images based on local energy maximal division [j]. Journal of Remote Sensing 3 (2008), 007.
[86] Jung, M., Henkel, K., Herold, M., and Churkina, G. Exploiting syner-gies of global land cover products for carbon cycle modeling. Remote Sensing of Environment 101, 4 (2006), 534 553.
[87] Kang, X., Li, S., and Benediktsson, J. A. Hyperspectral image classica-tion: A benchmark. In 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (July 2017), pp. 36323639.
110 BIBLIOGRAPHY
[88] Karhunen, K. Zur Spektraltheorie stochastischer Prozesse. Annales Academiae Scientiarum Fennicae 37 (1946).
[89] Kaufman, L., and Rousseeuw, P. J. Finding Groups in Data: An Introduction to Cluster Analysis. John Wiley & Sons, Ltd., 2008, ch. 2, pp. 68125.
[90] Keogh, E., and Mueen, A. Curse of Dimensionality. Springer US, Boston, MA, 2017, pp. 314315.
[91] Khan, M. J., Khan, H. S., Yousaf, A., Khurshid, K., and Abbas, A.
Modern trends in hyperspectral image analysis: A review. IEEE Access 6 (2018), 1411814129.
[92] Klemas, V. Fisheries applications of remote sensing: An overview. Fisheries Research 148 (2013), 124 136.
[93] Knyazev, A. V. Toward the optimal preconditioned eigensolver: Locally opti-mal block preconditioned conjugate gradient method. SIAM Journal on Scientic Computing 23, 2 (2001), 517541.
[94] Kokaly, R. F., Clark, R. N., Swayze, G. A., Livo, K. E., Hoefen, T. M., Pearson, N. C., Wise, R. A., Benzel, W. M., Lowers, H. A., Driscoll, R. L., et al. Usgs spectral library version 7. Tech. rep., US Geological Survey, 2017.
[95] Kuching, S. The performance of maximum likelihood, spectral angle mapper, neural network and decision tree classiers in hyperspectral image analysis. Journal of Computer Science 3, 6 (2007), 419423.
[96] Lambin, E. F., Turner, B., Geist, H. J., Agbola, S. B., Angelsen, A., Bruce, J. W., Coomes, O. T., Dirzo, R., Fischer, G., Folke, C., George, P., Homewood, K., Imbernon, J., Leemans, R., Li, X., Moran, E. F., Mor-timore, M., Ramakrishnan, P., Richards, J. F., Skånes, H., Steffen, W., Stone, G. D., Svedin, U., Veldkamp, T. A., Vogel, C., and Xu, J.
The causes of land-use and land-cover change: moving beyond the myths. Global Environmental Change 11, 4 (2001), 261 269.
[97] Lee, J. A., and Verleysen, M. Nonlinear dimensionality reduction, 1 ed.
Springer, 2007.
[98] Lee, S., and Crawford, M. M. Hierarchical clustering approach for unsuper-vised image classication of hyperspectral data. In IGARSS 2004. 2004 IEEE Inter-national Geoscience and Remote Sensing Symposium (Sept 2004), vol. 2, pp. 941 944 vol.2.
[99] Lei Fan, D. W. M. Joint spatialâspectral hyperspectral image clustering using block-diagonal amplied anity matrix. Optical Engineering 57 (2018), 57 57 13.
[100] Lein, J. K. Environmental sensing, 1 ed. Springer, 2012.
BIBLIOGRAPHY 111
[101] Li, Y., Huang, J., and Liu, W. Scalable sequential spectral clustering. In Proceedings of the Thirtieth AAAI Conference on Articial Intelligence (2016), AAAI'16, AAAI Press, pp. 18091815.
[102] Li, Z., Chen, J., and Baltsavias, E. Advances in photogrammetry, remote sensing and spatial information sciences: 2008 ISPRS congress book, vol. 7. CRC Press, 2008.
[103] Liu, H., and Weng, Q. Enhancing temporal resolution of satellite imagery for public health studies: A case study of west nile virus outbreak in los angeles in 2007. Remote Sensing of Environment 117 (2012), 57 71. Remote Sensing of Urban Environments.
[104] Liu, W., Li, S., Lin, X., Wu, Y., and Ji, R. Spectralspatial co-clustering of hyperspectral image data based on bipartite graph. Multimedia Systems 22, 3 (Jun 2016), 355366.
[105] Lloyd, S. Least squares quantization in pcm. IEEE Transactions on Information Theory 28, 2 (March 1982), 129137.
[106] Loéve M., L. P. Fonctions aleatoire du second ordre. Processus stochastiques et mouvement Brownien (1948), 299.
[107] Lopez, R. D., and Frohn, R. C. Remote Sensing for Landscape Ecology: New Metric Indicators. CRC Press, 2017.
[108] Lu, D., and Weng, Q. A survey of image classication methods and techniques for improving classication performance. International Journal of Remote Sensing 28, 5 (2007), 823870.
[109] Lunga, D., Prasad, S., Crawford, M. M., and Ersoy, O. Manifold-learning-based feature extraction for classication of hyperspectral data: A review of ad-vances in manifold learning. IEEE Signal Processing Magazine 31, 1 (Jan 2014), 5566.
[110] Ma, Y., and Fu, Y. Manifold learning theory and applications. CRC press, 2011.
[111] Maaten, L. v. d., and Hinton, G. Visualizing data using t-sne. Journal of machine learning research 9, Nov (2008), 25792605.
[112] Maier, M., Hein, M., and von Luxburg, U. Optimal construction of k-nearest-neighbor graphs for identifying noisy clusters. Theoretical Computer Science 410, 19 (2009), 1749 1764. Algorithmic Learning Theory.
[113] Maila, M., and Shi, J. A random walks view of spectral segmentation. In AI and STATISTICS (AISTATS) 2001 (January 2001).
[114] Malik, Z. K., Hussain, A., and Wu, J. An online generalized eigenvalue version of laplacian eigenmaps for visual big data. Neurocomputing 173 (2016), 127 136.
[115] Manolakis, D. G., Lockwood, R. B., and Cooley, T. W. Hyperspectral Imaging Remote Sensing: Physics, Sensors, and Algorithms. Cambridge University Press, 2016.
112 BIBLIOGRAPHY
[116] Marcal, A. R. S., and Castro, L. Hierarchical clustering of multispectral images using combined spectral and spatial criteria. IEEE Geoscience and Remote Sensing Letters 2, 1 (Jan 2005), 5963.
[117] Mather, P., and Tso, B. Classication methods for remotely sensed data. CRC press, 2016.
[118] Meila, M., and Shi, J. Learning segmentation by random walks. In Advances in Neural Information Processing Systems 13, T. K. Leen, T. G. Dietterich, and V. Tresp, Eds. MIT Press, 2001, pp. 873879.
[119] Melesse, A. M., Weng, Q., Thenkabail, P. S., and Senay, G. B. Re-mote sensing sensors and applications in environmental resources mapping and modelling. Sensors (Basel) 7, 12 (Dec 2007), 32093241.
[120] Mercier, G., Derrode, S., and Lennon, M. Hyperspectral image segmenta-tion with markov chain model. In IGARSS 2003. 2003 IEEE Internasegmenta-tional Geo-science and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477) (July 2003), vol. 6, pp. 37663768 vol.6.
[121] Moëllic, P.-A., Haugeard, J.-E., and Pitel, G. Image clustering based on a shared nearest neighbors approach for tagged collections. In Proceedings of the 2008 International Conference on Content-based Image and Video Retrieval (New York, NY, USA, 2008), CIVR '08, ACM, pp. 269278.
[122] Muhammed, H. H. Unsupervised hyperspectral image segmentation using a new class of neuro-fuzzy systems based on weighted incremental neural networks. In Applied Imagery Pattern Recognition Workshop, 2002. Proceedings. (Oct 2002), pp. 171177.
[123] Mulla, D. J. Twenty ve years of remote sensing in precision agriculture: Key advances and remaining knowledge gaps. Biosystems Engineering 114, 4 (2013), 358 371. Special Issue: Sensing Technologies for Sustainable Agriculture.
[124] Nadler, B., et al. Finite sample approximation results for principal component analysis: A matrix perturbation approach. The Annals of Statistics 36, 6 (2008), 27912817.
[125] Nagler, T., and Czado, C. Evading the curse of dimensionality in nonpara-metric density estimation with simplied vine copulas. arXiv e-prints (Mar. 2015), arXiv:1503.03305.
[126] Nam, K., Je, H., and Choi, S. Fast stochastic neighbor embedding: a
[126] Nam, K., Je, H., and Choi, S. Fast stochastic neighbor embedding: a