A mutual information-Dempster-Shafer based decision ensemble system for land cover classification of hyperspectral data

Parham PAHLAVANI , Behnaz BIGDELI

Front. Earth Sci. ›› 2017, Vol. 11 ›› Issue (4) : 774 -783.

PDF (4124KB)
Front. Earth Sci. ›› 2017, Vol. 11 ›› Issue (4) : 774 -783. DOI: 10.1007/s11707-016-0611-2
RESEARCH ARTICLE
RESEARCH ARTICLE

A mutual information-Dempster-Shafer based decision ensemble system for land cover classification of hyperspectral data

Author information +
History +
PDF (4124KB)

Abstract

Hyperspectral images contain extremely rich spectral information that offer great potential to discriminate between various land cover classes. However, these images are usually composed of tens or hundreds of spectrally close bands, which result in high redundancy and great amount of computation time in hyperspectral classification. Furthermore, in the presence of mixed coverage pixels, crisp classifiers produced errors, omission and commission. This paper presents a mutual information-Dempster-Shafer system through an ensemble classification approach for classification of hyperspectral data. First, mutual information is applied to split data into a few independent partitions to overcome high dimensionality. Then, a fuzzy maximum likelihood classifies each band subset. Finally, Dempster-Shafer is applied to fuse the results of the fuzzy classifiers. In order to assess the proposed method, a crisp ensemble system based on a support vector machine as the crisp classifier and weighted majority voting as the crisp fusion method are applied on hyperspectral data. Furthermore, a dimension reduction system is utilized to assess the effectiveness of mutual information band splitting of the proposed method. The proposed methodology provides interesting conclusions on the effectiveness and potentiality of mutual information-Dempster-Shafer based classification of hyperspectral data.

Keywords

mutual information / Dempster-Shafer / hyperspectral / classification / support vector machine

Cite this article

Download citation ▾
Parham PAHLAVANI, Behnaz BIGDELI. A mutual information-Dempster-Shafer based decision ensemble system for land cover classification of hyperspectral data. Front. Earth Sci., 2017, 11(4): 774-783 DOI:10.1007/s11707-016-0611-2

登录浏览全文

4963

注册一个新账户 忘记密码

References

[1]

Akbari DHomayuoni  SSaffari A, Mehrshad N (2016). Mapping urban land cover based on spatial-spectral classification of hyperspectral remote- sensing data. Int J Remote Sens37(2): 440–454

[2]

Benediktsson J A Chanussot J Fauvel M  (2007). Multiple classifier systems in remote sensing: from basics to recent developments. In: Haindl M, Kittler J, Roli F, eds. Multiple Classifier Systems. Heidelberg: Springer, 501–512

[3]

Bigdeli BSamadzadegan  FReinartz P  (2013). A multiple SVM system for classification of hyperspectral remote sensing data. Journal of the Indian Society of Remote Sensing41(4): 763–776

[4]

Borasca BBruzzone  LCarlin L Zusi M (2006). A fuzzy-input fuzzy-output SVM technique for classification of hyperspectral remote sensing images. Signal Processing Symposium, 2006. NORSIG 2006. Proceedings of the 7th Nordic, 2–5

[5]

Breve FPonti  MMascarenhas N  (2007). Multilayer Perceptron Classifier Combination for Identification of Materials on Noisy Soil Science Multispectral Images. Computer Graphics and Image Processing, 2007. SIBGRAPI 2007. XX Brazilian Symposium on. 239–244

[6]

Camps-Valls GBruzzone  L (2005). Kernel-based methods for hyperspectral image classification. IEEE Trans Geosci Rem Sens43(6): 1351–1362

[7]

Ceamanos XWaske  BBenediktsson J Chanussot J Fauvel M Sveinsson J  (2010). A classifier ensemble based on fusion of support vector machines for classifying hyperspectral data. International Journal of Image and Data Fusion1(4): 293–307

[8]

Chen C F (1999). Fuzzy training data for fuzzy supervised classification of remotely sensed images. Asian Conference Remote Sensing (ACRS 1999)

[9]

Chen HVarshney  P KArora  M K (2003). Performance of mutual information similarity measure for registration of multitemporal remote sensing images. IEEE Trans Geosci Rem Sens41(11): 2445–2454

[10]

Del Frate FPacifici  FSchiavon G Solimini C  (2007). Use of neural networks for automatic classification from high-resolution images. IEEE Trans Geosci Rem Sens45(4): 800–809

[11]

Di WPan  QHe L Cheng Y  (2008). Anomaly detection in hyperspectral imagery by fuzzy integral fusion of band-subsets. Photogramm Eng Remote Sensing74(2): 201–213

[12]

Goel P KPrasher  S OPatel  R MLandry  J ABonnell  R BViau  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 Agric39(2): 67–93

[13]

Ham JYangchi  ChenCrawford M M Ghosh J (2005). Investigation of the random forest framework for classification of hyperspectral data. IEEE Trans Geosci Rem Sens43(3): 492–501

[14]

Imani MGhasemian  H (2015). Feature reduction of hyperspectral images: discriminant analysis and the first principal component. Journal of AI and Data Mining3(1): 1–9 

[15]

Jia X (2002). Simplified maximum likelihood classification for HS data in cluster space. In: IEEE Int. Geoscience and Remote Sensing Symp. (IGARSS ‘02), Toronto, Ontario, Canada5: 2578–2580

[16]

Kasiri bidhendi S Shirazi A Fotoohi N Ebadzadeh M  (2007). Material Classification of hyperspectral images using unsupervised fuzzy clustering methods. Third International IEEE Conference on Signal-Image Technologies and Internet-Based System, SITIS '07. 619 –623

[17]

Kuncheva L (2004). Combining Pattern Classifiers methods and algorithms. Hoboken, New jersey. Canada: John Wiley&sons, INC.

[18]

Li JHuang  XGamba P Bioucas-Dias J M B Zhang L Benediktsson J A Plaza A  (2015). Multiple feature learning for hyperspectral image classification. IEEE Trans Geosci Rem Sens53(3): 1592–1606

[19]

Li SWu  HWan D Zhu J (2011). An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine. Knowl Base Syst24(1): 40–48

[20]

Martínez-Usó A Pla FSotoca  J MGarcia-Sevilla  P (2006). Clustering based multispectral band selection using mutual information, Proceedings of the 18th International Conference on Pattern Recognition (ICPR)2: 760–763

[21]

Müller K L Mika SRätsch  GTsuda K Schölkopf B  (2001). An introduction to kernel-based learning algorithms. IEEE Trans Neural Netw12(2): 181–201

[22]

 Pepe MBoschetti  LBrivio P A Rampini A  (2010). Comparing the performance of fuzzy and crisp classifiers on remotely sensed images: a case of snow classification. Int J Remote Sens31(23): 6189–6203

[23]

Shafer G (1976). A Mathematical Theory of Evidence. Princeton University Press

[24]

Shen JWang  CWang R Huang F Fan CXu  L (2015). A band selection method for hyperspectral image classification based on improved particle swarm optimization, International Journal of Signal Processing. Image Processing and Pattern Recognition8(4): 325–338

[25]

Su HYang  HDu Q Sheng Y  (2011). Semi-supervised band clustering for dimensionality reduction of hyperspectral imagery. IEEE Geosci Remote Sens Lett8(6): 1135–1139

[26]

Vaiphasa C (2003). Innovative genetic algorithm for hyperspectral image classification. In: Proc. Int. Conf. Map Asia.

[27]

Vapnik V N (1998). Statistical Learning Theory.New York: Wiley & Sons, Inc.

[28]

Yu SDe Backer  SScheunders P  (2002). Genetic feature selection combined with composite fuzzy nearest neighbor classifiers for hyperspectral satellite imagery. Pattern Recognit Lett23(1‒3): 183–190 

[29]

Zhang CQiu  F (2012). Hyperspectral image classification using an unsupervised neuro-fuzzy system. J Appl Remote Sens6(1): 1–15

RIGHTS & PERMISSIONS

Higher Education Press and Springer-Verlag Berlin Heidelberg

AI Summary AI Mindmap
PDF (4124KB)

933

Accesses

0

Citation

Detail

Sections
Recommended

AI思维导图

/