Skip to main content
SpringerLink
Log in

A model on achieving higher performance in the classification of hyperspectral satellite data: a case study on Hyperion data

  • Original Paper
  • Published:
Applied Geomatics Aims and scope Submit manuscript

Abstract

Hyperspectral remote sensing data is characterized by the large number of contiguous spectral bands with narrow bandwidth. Enormous information available in hyperspectral data is quite challenging for classification as compared to multispectral remote sensing data. Most of the widely used conventional ‘hard’ classifiers are producing inconsistent classification results while employed in classification of hyperspectral data. In this paper, we present an effective hyperspectral classification model for achieving higher accuracy. The proposed model is characterized by three major components: dimensionality reduction using principal component analysis (PCA), multiresolution segmentation, and fuzzy membership-based nearest neighbor (NN)-classification. Here, the bands of the dimensionality-reduced images are represented by the first principal component (PC) of each of the spectral region covered by the hyperspectral sensor. Then, multiresolution segmentation is carried out on these PC composite images based on color and shape homogeneity criterion. The conventional NN-classifier is effectively used by appropriate utilization of fuzzy membership function defined on a set of optimal features derived from the segmented image objects. We demonstrate a case study on Hyperion sensor data of Earth Observing-1 (EO-1) satellite. A comparative assessment is carried out with other competing techniques such as spectral angle mapper (SAM), artificial neural network (ANN), and support vector machine (SVM) on a set of images with different land cover surfaces. The proposed classification model outperforms the existing classification approaches investigated here.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  • Addink EA, De Jong SM, Davis SA, Dubyanskiy V, Burdelow LA, Leirs H (2010) The use of high-resolution re-mote sensing for plague surveillance in Kazakhstan. Remote Sens Environ 114:674–681

    Article  Google Scholar 

  • Atkinson P, Tatnall A (1997) Neural networks in remote sensing. Int J Remote Sens 18(4):699–709

    Article  Google Scholar 

  • Baatz M, Schape A (2000) Multiresolution segmentation: an optimizationapproach for high quality multi-scale image segmentation. In 12th Angewandte Geographische Informationseverarbeitung (Karlsruhe: Herbert Wichmann Verlag), pp. 12–23.

  • Baatz M, Benz UC, Dehghani S, Heynen M, Höltje A, Hoffmann P, Lingenfelder I, Mimler M, Sohlbach M, Weber M, Wilhauck G (2003) eCognition object oriented image analysis user guide. Definiens, Munchen

    Google Scholar 

  • Baofeng G, Gunn SR, Damper RI, Nelson JDB (2006) Band selection for hyperspectral Image classification using mutual information. Geosci Remote Sens Lett IEEE 3(4):522–526

    Article  Google Scholar 

  • Belluco E, Camuffo M, Ferrari S, Modenese L, Silvestri S, Marani A, Marani M (2006) Mapping salt-marsh vegetation by multispectral and hyperspectral remote sensing. Remote Sens Environ 105(1):54–67

    Article  Google Scholar 

  • Benz UC, Hofmann P, Willhauck G, Lingenfelder I, Heynen M (2004) Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS. J Photogramm Remote Sens 58(3):239–258

    Article  Google Scholar 

  • Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum, New York

    Book  Google Scholar 

  • Bilgin G, Erturk S, Yildirim T (2008) Unsupervised classification of hyperspectral-image data using fuzzy approaches that spatially exploit membership relations. Geosci Remote Sens Lett IEEE 5(4):673–677

    Article  Google Scholar 

  • Bilgin G, Erturk S, Yildirim T (2011) Segmentation of hyperspectral images via subtractive clustering and cluster validation using one-class support vector machines. Geosci Remote Sens Lett IEEE Trans 49(8):2936–2944

    Article  Google Scholar 

  • Chang YL, Fang JP, Hsu WL, Chang L, Chang WY (2010) Simulated annealing band selection approach for hyperspectral imagery. J Appl Remote Sens 4:041767

    Article  Google Scholar 

  • Chen G, Qian SE (2007) Dimensionality reduction of hyperspectral imagery using improved locally linear embedding. J Appl Remote Sens 1(1):013509

    Article  Google Scholar 

  • Chen G, Qian SE (2008) Simultaneous dimensionality reduction and denoising of hyperspectral imagery using bivariate wavelet shrinking and principal component analysis. Can J Remote Sens 34(5):447–454

    Article  Google Scholar 

  • Chi M, Kun Q, Benediktsson JA, Feng R (2009) Ensemble classification algorithm for hyperspectral remote sensing data. Geosci Remote Sens Lett IEEE 6(4):762–766

    Article  Google Scholar 

  • Chutia D, Bhattacharyya DK, Sudhakar S (2012) Effective feature extraction approach for fused images of Cartosat-I and Landsat ETM + satellite sensors. Appl Geomatics Springer 4(3):217–224

    Article  Google Scholar 

  • Congalton R (1991) A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens Environ 37(1):35–46

    Article  Google Scholar 

  • d’Oleire-Oltmanns S, Eisank C, Dragut L, Blaschke T (2013) An object-based workflow to extract landforms at multiple scales from two distinct data types. Geosci Remote Sens Lett IEEE 10(4):947–951

    Article  Google Scholar 

  • Demir B, Persello C, Bruzzone L (2011) Batch-mode active-learning methods for the interactive classification of remote sensing images. Geosci Remote Sens Lett IEEE Trans 49(3):1014–1031

    Article  Google Scholar 

  • Du P, Xia J, Zhang W, Tan K, Liu Y, Liu S (2011) Multiple classifier system for remote sensing image classification: a review. Sensors Basel Switzerland 12(4):4764–4792

    Google Scholar 

  • Filippi AM, Jensen JR (2006) Fuzzy learning vector quantization for hyperspectral coastal vegetation classification. Remote Sens Environ 100(4):512–530

    Article  Google Scholar 

  • Filippi A, Dobreva I, Klien AG, Jensen JR (2010) Self-organizing map-based applications in remote sensing. In Self-Organizing Maps, 231–248.

  • Green AA, Berman M, Switzer and P, Craig MD (1988) A transformation for ordering multispectral data in terms of image quality with implications for noise removal. Geoscience and Remote Sensing, IEEE Transactions on, 26(1), 65–74

  • Guorong X, Peiqi C, Minhui W (1996). Bhattacharyya distance feature selection. In Pattern Recognition, 1996, Proceedings of the 13th International Conference on (Vol. 2, pp. 195–199). IEEE.

  • Harken J, Sugumaran R (2005) Classification of Iowa wetlands using an airborne hyperspectral image: a comparison of the spectral angle mapper classifier and an object-oriented approach. Can J Remote Sens 31(2):167–174

    Article  Google Scholar 

  • Harris JR, Ponomarev P, Shang J, Rogge D (2006) Noise reduction and best band selection techniques for improving classification results using hyperspectral data: application to lithological mapping in Canada’s Arctic. Can J Remote Sens 32(5):341–354

    Article  Google Scholar 

  • Howard A (1987) Elementary linear algebra 5e, 2nd edn. Wiley & Sons Canada, Limited, John

    Google Scholar 

  • Hsieh PF (2009) Impact and realization of increased class separability on the small sample size problem in hyperspectral classification. Can J Remote Sens 35(3):248–261

    Article  Google Scholar 

  • Hsu PH (2007) Feature extraction of hyperspectral images using wavelet and matching pursuit. ISPRS J Photogramm Remote Sens 62(2):78–92

    Article  Google Scholar 

  • Jensen JR (1996) Introductory digital image processing: a remote sensing perspective 2ndEd. Prentice-Hall, Upper Saddle River, NJ

    Google Scholar 

  • Johansen K, Phinn S, Witte C, Philip S, Newton L (2009) Mapping banana plantations from object-oriented classi-fication of SPOT-5 imagery. Photogramm Eng Remote Sens 75(9):1069–1081

    Article  Google Scholar 

  • Ju J, Kolaczyk ED, Gopal S (2003) Gaussian mixture discriminant analysis and sub-pixel land cover characterization in remote sensing. Remote Sens Environ 84:550–560

    Article  Google Scholar 

  • Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43(1):59–69

    Article  Google Scholar 

  • Laidler GJ, Treitz PM, Atkinson DM (2008) Remote sensing of arctic vegetation: relations between the NDVI, spatial resolution and vegetation cover on Boothia Peninsula, Nunavut. Arctic 61(1):1–13

    Google Scholar 

  • Li S, Zhang B, Chen D, Gao L, Peng M (2011) Adaptive support vector machine and Markov random field model for classifying hyperspectral imagery. J Appl Remote Sens 5(1):053538

    Article  Google Scholar 

  • Li W, Prasad S, Fowler JE, Bruce LM (2012) Locality-preserving discriminant analysis in kernel-induced feature spaces for hyperspectral image classification. Geosci Remote Sens Lett IEEE 8(5):894–898

    Article  Google Scholar 

  • Linden SVD, Janz A, Waske B, Eiden M, Hostert P (2007) Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines. J Appl Remote Sens 1(1):013543

    Article  Google Scholar 

  • Lu D, Weng Q (2007) A survey of image classification methods and techniques for improving classification performance. Int J Remote Sens 28(5):823–870

    Article  Google Scholar 

  • MaderS, VohlandM, Jarmer T, Casper M (2006) Crop classification with hyperspectral data of the HyMap sensor using different feature extraction techniques. In 2nd Workshop of the EARSel SIG on Remote Sensing of Land Use & Land Cover, edited by M Braun (Bonn, Germany) (pp. 96–101).

  • Marpu PR, Niemeyer I, Nussbaum S, Gloaguen R (2008) A procedure for automatic object-based classification. In: Blaschke T, Lang S, Hay GJ (eds) Object-based Image analysis: spatial concepts for knowledge-driven remote sensing applications. Springer, Berlin, pp 169–184

    Chapter  Google Scholar 

  • Martinez-Uso A, Pla F, Sotoca JM, Garcia-Sevilla P (2007) Clustering-based hyperspectral band selection using information measures. Geosci Remote Sens IEEE Trans 45(12):4158–4171

    Article  Google Scholar 

  • Mayer R, Antoniades J, Baumback M, Chester D, Edwards J, Goldstein A, Haas D, Henderson S (2007) Extending classification approaches to hyperspectral object detection. J Appl Remote Sens 1(1):013526–013526

    Article  Google Scholar 

  • Murat Dundar M, Landgrebe D (2002) A model-based mixture-supervised classification approach in hyperspectral data analysis. Geosci Remote Sens IEEE Trans 40(12):2692–2699

    Article  Google Scholar 

  • Myint SW (2001) A robust texture analysis and classification approach for urban land-use and land-cover feature discrimination. Geocarto Int 16:27–38

    Article  Google Scholar 

  • Neville RA, Levesque J, Staene K, Nadeau C, Hauff P, Borstad GA (2003) Spectral unmixing of hyperspectral imagery for mineral exploration: comparison of results from SFSI and AVIRIS. Can J Remote Sens 29:99–110

    Article  Google Scholar 

  • Nussbaum S, Niemeyer I, Canty MJ (2006) SEATH - A new tool for automated feature extraction in the context of ob-ject-based image analysis. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Salzburg, Austria, Vol. XXXVI-4, Part C42.

  • Oldeland J, Dorigo W, Lieckfeld L, Lucieer A, Jürgens N (2010) Combining vegetation indices, constrained ordination and fuzzy classification for mapping semi-natural vegetation units from hyperspectral imagery. Remote Sens Environ 114(6):1155–1166

    Article  Google Scholar 

  • Pal M (2012) Multinomial logistic regression-based feature selection for hyperspectral data. Int J Appl Earth Obs Geoinformation 14(1):214–220

    Article  Google Scholar 

  • Pal M, Mather PM (2006) Some issues in the classification of DAIS hyperspectral data. Int J Remote Sens 27(14):2895–2916

    Article  Google Scholar 

  • Qiu F (2008) Neuro-fuzzy based analysis of hyperspectral imagery. Photogramm Eng Remote Sens 74(10):1235–1247

    Article  Google Scholar 

  • Richards JA, Jia X (2008) Using suitable neighbors to augment the training set in hyperspectral maximum likelihood classification. Geosci Remote Sens Lett IEEE 5(4):774–777

  • Sarkar A, Vulimiri A, Paul S, Iqbal Md J, Banerjee A, Chatterjee R, Ray SS (2012) Unsupervised and supervised classification of hyperspectral imaging data using projection pursuit and Markov random field segmentation. Int J Remote Sens 33(18):5799–5818

    Article  Google Scholar 

  • Schmidt F, Doute S, Schmitt B (2007) WAVANGLET: an efficient supervised classifier for hyperspectral images. GeosciIEEE Trans Remote Sens 45(5):1374–1385

    Article  Google Scholar 

  • Sheeren D, Bastin N, Ouin A, Ladet S, Balent G, Lcombe JP (2009) Discriminating small wooded elements in rural landscape from aerial photography: a hybrid pixel/object-based analysis approach. J Remote Sens 30(19):4979–4990

    Article  Google Scholar 

  • Stavrakoudis DG, Galidaki GN, Gitas IZ, Theocharis JB (2012) A genetic fuzzy-rule-based classifier for land cover classification from hyperspectral imagery. Geosci Remote Sens IEEE Trans 50(1):130–148

    Article  Google Scholar 

  • Su H, Yang H, Du Q, Sheng Y (2011) Semisupervised band clustering for dimensionality reduction of hyperspectral imagery. Geosci Remote Sens Lett IEEE 8(6):1135–1139

    Article  Google Scholar 

  • Tsao ECK, Bezdek JC, Pal NR (1994) Fuzzy Kohonen clustering networks. Pattern Recogn 27(5):757–764

    Article  Google Scholar 

  • Villa A, Benediktsson JA, Chanussot J, Jutten C (2011) Hyperspectral image classification with independent component discriminant analysis. Geosci Remote Sens IEEE Trans 49(12):4865–4876

    Article  Google Scholar 

  • Waske B, Benediktsson JA, Árnason K, Sveinsson JR (2009) Mapping of hyperspectral AVIRIS data using machine-learning algorithms. Can J Remote Sens 35(S1):S106–S116

    Article  Google Scholar 

  • Wei W, Du Q, Younan NH (2012) Fast supervised hyperspectral band selection using graphics processing unit. J Appl Remote Sens 6(1):061504

    Article  Google Scholar 

  • Yang C, Everitt JH, Johnson HB (2009) Applying image transformation and classification techniques to airborne hyperspectral imagery for mapping Ashe juniper infestations. Int J Remote Sens 30(11):2741–2758

    Article  Google Scholar 

  • Yang H, Ma B, Du Q, Yang C (2010) Improving urban land use and land cover classification from high-spatial-resolution hyperspectral imagery using contextual information. J Appl Remote Sens 4(1):041890

    Article  Google Scholar 

  • Yu S, Backer SD, Paul S (2002) Genetic feature selection combined with composite fuzzy nearest neighbor classifiers for hyperspectral satellite imagery. Pattern Recogn Lett 23:183–190

    Article  Google Scholar 

  • Zhang C, Qiu F (2012) Hyperspectral image classification using an unsupervised neuro-fuzzy system. J Appl Remote Sens 6(1):063515–1

    Article  Google Scholar 

  • Zhong P, Zhang P, Wang R (2008) Dynamic learning of SMLR for feature selection and classification of hyperspectral data. Geosci Remote Sens Lett IEEE 5(2):280–284

    Article  Google Scholar 

Download references

Acknowledgment

The authors would like to thank the North Eastern Space Applications Centre, Department of Space, Government of India, Umiam, Meghalaya, India for providing the necessary guidance and support during the study. The authors also acknowledge the concerned authorities of Definiens Imaging for using their software.

Author information

Authors and Affiliations

  1. North Eastern Space Applications Centre, Department of Space, Government of India, Umiam, Meghalaya, 793103, India

    Dibyajyoti Chutia, Ranjan Kalita, Jonali Goswami, Puyam S. Singh & S. Sudhakar

  2. Department of Computer Science and Engineering, Tezpur University, Napaam, Assam, 784028, India

    Dhruba Kumar Bhattacharyya

Authors
  1. Dibyajyoti Chutia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dhruba Kumar Bhattacharyya
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ranjan Kalita
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jonali Goswami
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Puyam S. Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. S. Sudhakar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dibyajyoti Chutia.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chutia, D., Bhattacharyya, D.K., Kalita, R. et al. A model on achieving higher performance in the classification of hyperspectral satellite data: a case study on Hyperion data. Appl Geomat 6, 181–195 (2014). https://doi.org/10.1007/s12518-014-0134-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12518-014-0134-z

Keywords

Search

Navigation