Skip to main content
Log in

An adaptive framework for spectral-spatial classification based on a combination of pixel-based and object-based scenarios

  • Research Article
  • Published:
Earth Science Informatics Aims and scope Submit manuscript

Abstract

Remotely sensed image analysis using spectral-spatial information plays a key role in modern remote sensing applications. This article presents a new semi-automatic framework for spectral-spatial classification of hyperspectral images. The proposed framework benefits from a combination of pixel-based and object-based classification scenarios in which the main parameters are adaptively tuned. In order to reduce the complexity of the method, an unsupervised band selection technique is used as well. Meanwhile, the wavelet thresholding is applied in order to smooth the selected bands. The classification results after applying the proposed method to well-known standard hyperspectral datasets are better than those of the most of the other state-of-the-art approaches. As an example, the overall classification accuracy achieved by applying the proposed semi-automatic spectral-spatial classification framework to the Salinas dataset is more than 99% for 10% training samples per class. Moreover, the vital parameters are adaptively set in our approach.

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

Access this article

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
Fig. 9

Similar content being viewed by others

References

  • Bernabe S, Marpu PR, Plaza A, Dalla Mura M, Benediktsson JA (2014) Spectral–spatial classification of multispectral images using kernel feature space representation. IEEE Geosci Remote Sens Lett 11(1):288–292

    Article  Google Scholar 

  • Blaschke T (2010) Object based image analysis for remote sensing. ISPRS J Photogramm Remote Sens 65:2–16

    Article  Google Scholar 

  • Blaschke T, Hay GJ, Kelly M et al (2014) Geographic object based image analysis–towards a new paradigm. ISPRS J Photogramm Remote Sens 87:180–191

    Article  Google Scholar 

  • Burrus CS, Gopinath RA, Guo H (1998) Introduction to wavelets and wavelet transforms. Prentice Hall, New Jersey

    Google Scholar 

  • Camps-Valls G, Gomez-Chova L, Munoz-Mari J, Vila-Frances J, Calpe-Maravilla J (2006) Composite kernels for hyperspectral image classification. IEEE Geosci Remote Sens Lett 3(1):93–97

    Article  Google Scholar 

  • Cariou C, Chehdi K, Le Moan S (2011) BandClust: an unsupervised band reduction method for hyperspectral remote sensing. IEEE Geosicnece and Remote Sensing Letters 8(3):565–569

    Article  Google Scholar 

  • Chang SG, Yu B, Vetterli M (2000) Adaptive wavelet thresholding for image Denoising and compression. IEEE Trans Image Processing 9:1532–1545

    Article  Google Scholar 

  • Chang CC et al (2001) LIBSVM: a library for support vector machines, Software available at http://www.csie.ntu.edu.tw/cjlin/libsvm

  • Fauvel M, Tarabalka Y, Benediktsson JA, Chanussot J, Tilton JC (2013) Advances in spectral-spatial classification of hyperspectral images. Proc IEEE 101(3):652–675

    Article  Google Scholar 

  • Gaetano R, Masi G, Poggi G (2015) Marker-controlled watershed-based segmentation of Multiresolution remote sensing images. IEEE Transactions on Geosicnece and Remote Sensing 53(6):2987–3004

    Article  Google Scholar 

  • Ghamisi P, Benediktsson JA, Cavallaro G, Plaza A (2014a) Automatic framework for spectral–spatial classification based on supervised feature extraction and morphological attribute profiles. Selected Topics in Applied Earth Observations and Remote Sensing 7(6):2147–2160

    Article  Google Scholar 

  • Ghamisi P, Couceiro MS, Fauvel M, Benediktsson JA (2014b) Integration of segmentation techniques for classification of hyperspectral images. IEEE Geosicnece and Remote Sensing Letters 11(1):342–346

    Article  Google Scholar 

  • Ghamisi P, Dalla Mura M, Benediktsson JA (2015) A survey on spectral-spatial classification techniques based on attribute profiles. IEEE Transactions on Geosicnece and Remote Sensing 53(5):2335–2353

    Article  Google Scholar 

  • Ghassemian H, Landgrebe DA (1988) Object-oriented feature extraction method for image data compaction. IEEE Cont Syst Mag 8(3):42–48

    Article  Google Scholar 

  • Golipour M, Ghassemian H, Mirzapour F (2016) Integrating hierarchical segmentation maps with MRF prior for classification of hyperspectral images in a Bayesian framework. IEEE Transactions on Geosicnece and Remote Sensing 54(2):805–816. doi:10.1109/TGRS.2015.2466657

    Article  Google Scholar 

  • Gupta S, Kaur L (2002) Wavelet based image compression using daubechies filters. 8th National conference on communications, I.I.T. Bombay 88–92

  • Hassanpour H, Yousefian H, Zehtabian A (2011) Pixon-based image segmentation. In: Pei-Gee Ho (ed) Image segmentation. InTech pub., Rijeka, p 496–516

  • Holbling D, Friedl B, Eisank C (2015) An object-based approach for semi-automated landslide change detection and attribution of changes to landslide classes in northern Taiwan. Earth Sciences Informatics 8(2):327–335. doi:10.1007/s12145-015-0217-3

    Article  Google Scholar 

  • Kang X, Li S, Benediktsson JA (2014) Spectral-spatial hyperspectral image classification with edge-preserving filtering. IEEE Transactions on Geosicnece and Remote Sensing 52(5):2666–2677

    Article  Google Scholar 

  • Khodadadzadeh M, Li J, Plaza A, Ghassemian H, Bioucas-Dias JM, Li X (2014) Spectral–spatial classification of hyperspectral data using local and global probabilities for mixed pixel characterization. IEEE Transactions on Geosicnece and Remote Sensing 52(10):6298–6314

    Article  Google Scholar 

  • Li J, Zhang H, Zhang L (2014) Supervised segmentation of very high resolution images by the use of extended morphological attribute profiles and a sparse transform. IEEE Geo. Sci. & Remote Sensing Letters 11(8):1409–1413

    Article  Google Scholar 

  • Liu D, Xia F (2010) Assessing object-based classification: advantages and limitations. Remote Sensing Letters 1(4):187–194

    Article  Google Scholar 

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

    Article  Google Scholar 

  • Machala M, Zejdova L (2014) Forest mapping through object-based image analysis of multispectral and Lidar Arerial data. European Journal of Remote Sensing 47:117–131

    Article  Google Scholar 

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

    Article  Google Scholar 

  • Mirzapour F, Ghassemian H (2015) Improving hyperspectral image classification by combining spectral, texture, and shape features. Int Jour Remote Sens 36(4):1070–1096

    Google Scholar 

  • Mylonas SK, Stavrakoudis DG, Theocharis JB, Mastorocostas PA (2015) Classification of remotely sensed images using the GeneSIS fuzzy segmentation algorithm. IEEE Transactions on Geosicnece and Remote Sensing 53(10):5352–5376

    Article  Google Scholar 

  • Plaza A, Benediktsson JA, Boardman JW et al (2009) Recent advances in techniques for hyperspectral image processing. Remote Sens of Environment 113:110–122

    Article  Google Scholar 

  • Ramzi P, Samadzadegan F, Reinartz P (2013) Classification of hyperspectral data using an AdaBoostSVM technique applied on band clusters. IEEE Jour of Selected Topics in Applied Earth Observations and Remote Sens 7(6):2066–2079

    Article  Google Scholar 

  • Rubner Y, Tomasi C, Guibas LJ (2000) The earth Mover’s distance as a metric for image retrieval. Int Jour of Comp Vision 40(2):99–121

    Article  Google Scholar 

  • Samal DR, Gedam SS (2015) Monitoring land use changes associated with urbanization: an object based image analysis approach. European Journal of Remote Sensing 48:85–99

    Article  Google Scholar 

  • Shi W, Mao Z (2016) Building extraction from panchromatic high-resolution remotely sensed imagery based on potential histogram and neighborhood Total variation. Earth Sciences Informatics. doi:10.1007/s12145-016-0262-6

    Google Scholar 

  • Sun W, Li W, Li J, Lai YM (2015) Band selection using sparse nonnegative matrix factorization with the thresholded. Earth’s mover distance for hyperspectral imagery classification 8(4):907–918. doi:10.1007/s12145-014-0201-3

    Google Scholar 

  • Ward JH (1963) Hierarchical grouping to optimize an objective function. Amer Stat Assoc 58(301):236–244

    Article  Google Scholar 

  • Zahidi I, Yusuf B, Hamedianfar A, Shafri HZM, Mohamed TA (2015) Object-based classification of QuickBird image and low point density LIDAR for tropical trees and shrubs mapping. European Journal of Remote Sensing 48:423–446

    Article  Google Scholar 

  • Zehtabian A, Ghassemian H (2015) An adaptive Pixon extraction technique for multispectral/hyperspectral image classification. IEEE Geo. Sci. & Remote Sensing Letters 12(4):831–835

    Article  Google Scholar 

  • Zehtabian A, Nazari A, Ghassemian H, Gribaudo M (2015) Adaptive restoration of multispectral datasets. The European Journal of Remote Sensing 48:183–200

    Article  Google Scholar 

  • Zhang P, Lv Z, Shi W (2013) Object-based spatial feature for classification of very high resolution remote sensing images. IEEE Geo Sci & Remote Sensing Letters 10(6):1572–1576

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Amin Zehtabian.

Additional information

Responsible editor: H. A. Babaie

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zehtabian, A., Ghassemian, H. An adaptive framework for spectral-spatial classification based on a combination of pixel-based and object-based scenarios. Earth Sci Inform 10, 357–368 (2017). https://doi.org/10.1007/s12145-017-0298-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12145-017-0298-2

Keywords

Navigation