Please enter verification code
Confirm
An Efficient Hybrid Classification System for High Resolution Remote Sensor Data
American Journal of Remote Sensing
Volume 1, Issue 2, April 2013, Pages: 21-32
Received: Mar. 15, 2013; Published: Apr. 2, 2013
Views 3220      Downloads 190
Authors
Roopesh Tamma, Dept of Geo Engineering, Andhra University, Visakhapatnam, India
T. Ch. Malleswara Rao, School of Electronics, Sreenidhi Institute of Technology, Hyderabad, India
G. Jaisankar, Dept of Geo Engineering, Andhra University, Visakhapatnam, India
Article Tools
PDF
Follow on us
Abstract
The classification of aerial and satellite remote sensing data has become a challenging problem due to the recent advances in remote sensor technology that led to higher spatial and spectral resolutions. This research paper presents novel sensor independent algorithms and techniques for dealing with the challenges of classification of high volume remote sensor data. A fast unsupervised band reduction method is proposed to lower the dimensionality of the input image. The band reduced image is then split into two mutually disjoint pure and mixed pixel subsets by a pixel segregator built using extended mathematical morphology techniques. A novel hierarchical spectral-spatial support vector machine based classifier that adaptively includes the usage of expensive spatial information based on the pixel categorization is proposed. The final thematic map is obtained after merging the classification results of the two subsets and fixed spatial neighborhood homogenization. The accuracy, efficiency and flexibility of the developed system are demonstrated by evaluating the classification results using several hyperspectral and multispectral data sets. The obtained results demonstrate that the proposed method performs significantly better than conventional classifiers while alleviating the computational complexity involved in generating spatial information.
Keywords
Morphological Profile Operators; Spectral And Spatial Classification; Vector Ordered Statistics; Support Vector Machine (SVM); Hyperspectral; Multispectral
To cite this article
Roopesh Tamma, T. Ch. Malleswara Rao, G. Jaisankar, An Efficient Hybrid Classification System for High Resolution Remote Sensor Data, American Journal of Remote Sensing. Vol. 1, No. 2, 2013, pp. 21-32. doi: 10.11648/j.ajrs.20130102.12
References
[1]
Kettig, R. L., and Landgrebe D. (1976). Classification of multispectral image data by extraction and classification of homogenous objects, IEEE Transactions on Geoscience Electronics, Vol. 14, No. 1, pp. 19-26.
[2]
Landgrebe D.A. (1980). The development of a spectral-spatial classifier for earth observational data. Pattern Recognition, Vol. 12, pp. 165-175.
[3]
Dobson, M. C., Pierce, L., Kellndorfer, J., and Ulbay, F. (1997). Use of SAR image texture in terrain classification. IEEE Trans. On Geosci. and Remote Sens., Vol. 3, No. 1, pp. 1180-1184.
[4]
de Jong, S. M., Hornstra, T.J., and Mass, H. (2001). An integrated spatial and spectral approach to the classification of Mediterranean land cover types: the SSC method. JAG, Vol. 3, No. 2, pp. 176-183.
[5]
Tarabalka, Y., Bendiktsson, J. A., and Chanussot, J. (2010). SVM and MRF-based method for accurate classification of hyperspectral images. IEEE Trans. Geosci. Remote Sens., Vol 7, No. 4, pp. 736-740.
[6]
Benediktsson, J. A., Plamson, J. A., and Sveinsson, J. (2005). Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Transactions on Geoscience and Remote Sensing, Vol. 43, No. 3, pp. 480–491.
[7]
Zhou, Y., Wu, B., Li, D., and Li, R. (2009). Edge detection on hyperspectral imagery via manifold techniques. IEEE Workshop on Hyperspectral Image and Signal Processing, WHISPERS’09, Grenoble, France.
[8]
Goel, P. K., Prasher, S. O., and Patel, R. M, Landry, J. A., Bonnell, R. B., and Viau, A. A. (2003). Classification of hyperspectral data by decision trees and artificial neural networks to identify weed stress and nitrogen status of corn, Comput. Electron. Agricult., Vol. 39, pp. 67–93.
[9]
Landgrebe., D. (2003). Signal Theory Methods in Multispectral Remote Sensing, John Wiley & Sons, Inc., 2003.
[10]
Camp-Valls, G., Bruzzone, L. (2005). Kernel-based methods for hyperspectral image classification, IEEE Transactions on Geoscience and Remote Sensing, vol. 43. No. 6, pp. 1351-1362.
[11]
Hoffbeck, J. P. and Landgrebe, D. A (1996), Covariance matrix estimation and classification with limited training data, IEEE Transactions Pattern Anal. Machine Intelligence, Vol. 8, pp. 763-767.
[12]
Tajudin, S., Landgrebe, D. A. (1999). Covariance estimation with limited training samples, IEEE Transactions on Geoscience Remote Sensing, Vol. 37, No. 4, pp. 2113-2118.
[13]
Vapnik, V. N (1998). Statistical learning theory. Wiley, New York.
[14]
Joachims, T. (1998). Making large scale SVM learning practical. In B. Scholkopf, C. Burges, & A. Smola (Eds.), Advances in Kernel methods-support vector learning. MIT Press, New York.
[15]
Cristianini, N., and Shawe-Taylor, J. (2000). An introduction to support vector machines and other Kernel-based learning methods. Cambridge University Press, Cambridge.
[16]
Kecman, V. (2001). Learning and soft computing — support vector machines, neural networks, fuzzy logic systems. MIT Press, Cambridge.
[17]
Verszkov, S., and Paclik, P. (2006). Edge detection in hyperspectral imaging – multivariate statistical approaches. Structural, Syntactic and Statistical Pattern Recognition, 4109, 551–559.
[18]
Huertas, A., Medioni, G. (1986). Detection of intensity changes with subpixel accuracy using Laplacian-Gaussian masks, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 5, pp. 651-664.
[19]
Serra, J. (1982). Image Analysis and Mathematical Morphology, vols. 1 and 2. Academic Press, San Diego.
[20]
Epifanio, I., Soille, P. (2003). Segmentation of natural landscapes using morphological texture features, Geoscience and Remote Sensing Symposium, IEEE-IGARSS Proceedings, Vol. 1, pp. 445-457.
[21]
Louverdis, G., Andreadis, I., Tsalides, P. (2002). New fuzzy model for morphological color image processing, Vision, Image and Signal Processing, IEEE Proceedings, vol. 149, no. 3, pp. 129-139.
[22]
Astolaa, J., Haavisto, P., & Neuvo, Y. (1990). Vector Median Filter. Proceedings of the IEEE, Vol. 78, No. 4, pp. 679-689.
[23]
Evans, A., and Liu, X. (2006). A morphological gradient approach to color edge detection. IEEE Transactions on Image Processing, Vol. 15, No. 6, pp. 1454–1463.
[24]
Melgani, P., Bruzzone, L. (2004). Classification of hyperspectral remote sensing images with support vector machines, IEEE Transactions on Geoscience and Remote Sensing, vol. 42, no. 8, pp. 1778-1790.
[25]
Bruzzone, L., and Prieto, D.F. (1999). A technique for the selection of kernel-function parameters in RBF neural networks for classification of remote-sensing images, IEEE Transactions on Geosicence and Remote Sensing, Vol. 37, No. 2, pp. 1179 – 1184.
[26]
Hsu, C., and Lin, C. (2002). A comparison of methods for multi-class support vector machines, IEEE Transactions on Neural Networks, Vol. 13, No. 2, pp. 415-425.
[27]
AVIRIS (1992). AVIRIS NW Indiana’s Indian Pines 1992 data set. ftp://ftp.ecn.purdue.edu/biehl/Multispec/92AV3C.lan(data set) and ftp://ftp.ecn.purdue.edu/biehl/Multispec/ ThyFiles.zip (ground truth). Accessed 24 Jan, 2011.
[28]
Pavia University (2000). University of Pavia data set. www.ehu.es/uploads/e/ee/PaviaU.mat (data set) and www.ehu.es/uploads/5/50/PaviaU_gt.mat (ground truth). Accessed 24 Jan, 2011.
[29]
Chang, C., and Lin, C. (2001). LIBSVM: a library for support vector machines. Software available at http://www.csie. ntu.edu.tw/~cjlin/libsvm. Accessed 24 Jan 2011.
[30]
Biehl, L., and Landgrebe, D. A. (2002). MultiSpec – a tool for multispectral and hyperspectral image data analysis, Computers and Geosciences, Vol. 28, No. 10, pp. 1153-1159.
ADDRESS
Science Publishing Group
1 Rockefeller Plaza,
10th and 11th Floors,
New York, NY 10020
U.S.A.
Tel: (001)347-983-5186