Abstract
Principal component analysis (PCA) and independent component analysis (ICA) are linear feature extraction methods in terms of the second-order statistics and higher-order statistics and have good compatibility and complementarity. For the feature extraction of the hyperspectral remote sensing image, an approach of the combined PCA and ICA was followed in the real remote sensing classification applications. In this study, the weighted PCA-ICA method was introduced to extract the feature information from HJ-1A hyperspectral imager (HSI) image. And then the real airborne visible infrared imaging spectrometer (AVIRIS) image case was performed by the distance similarity measure. Experimental results on HJ-1A HSI and AVIRIS images indicate that the proposed method can get high average accuracy of 89.55% and kappa coefficient of 0.8101 than the typical methods under certain condition with a suitable number of eigenvectors and weighted values.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Chang CI, Chiang SS, Smith JA, Ginsberg IW (2002) Linear spectral random mixture analysis for hyperspectral imagery. IEEE Trans Geosci Remote Sens 40(2):375–392
Chen Y, Nasrabadi NM, Tran TD (2013) Hyperspectral image classification via kernel sparse representation. IEEE Trans Geosci Remote Sens 51(1):217–231
Duda T, Canty M (2002) Unsupervised classification of satellite imagery: choosing a good algorithm. Int J Remote Sens 23(11):2193–2212
Fan LH, Lu JW, Deng JS (2014) Classification of hyperspectral remote sensing images based on bands grouping and classification ensembles. Acta Opt Sin 34(9):91–101
Green AA, Berman M, Switzer PA (1988) Transformation for ordering multispectral data in terms of image quality with implication for noise removal. IEEE Trans Geosci Remote Sens 26(1):65–74
Heblinski J, Schmieder K, Heege T, Agyemang TK, Sayadyan H, Vardanyan L (2011) High-resolution satellite remote sensing of littoral vegetation of Lake Sevan (Armenia) as a basis for monitoring and assessment. Hydrobiologia 61(1):97–111
Hyvarinen A (1999) Survey on independent component analysis. Neural Comput Survey 22(2):94–128
Hyvarinen A, Oja E (2000) Independent component analysis: algorithm and application. Neural Netw 13(4–5):411–430
Iordache MD, Dias JMB, Plaza A (2011) Sparse unmixing of hyperspectral data. IEEE Trans Geosci Remote Sens 49(6):2014–2039
Lee TW, Girolami M, Sejnowski TJ (1999) Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources. Neural Comput 11(2):417–441
Liang L, Yang MH, Li YF (2010) Hyperspectral remote sensing image classification based on ICA and SVM algorithm. Spectrosc Spectr Anal 30(10):2724–2728
Lin N, Yang W (2013) Hyperspectral remote sensing image feature extraction based on kernel minimum noise fraction transformation. Remote Sens Technol Appl 28(2):245–251
Lin N, Yang WN, Wang B (2016) Using kernel method to study on hyperspectral pixel linearly un-mixing. Geomat Inf Sci Wuhan Univ 41(11):1–8
Liu Z, Yi DY (2003) The application of projection pursuit in hyperspectral image analysis. Math Theory Appl 23(1):76–81
Liu L, Li CF, Lei YM, Yin JY, Zhao JJ (2017) Volcanic ash cloud detection from MODIS image based on CPIWS method. Acta Geophys 65(1):151–163
Mountrakis G, Irn J, Ogole C (2011) Support vector machines in remote sensing: a review. ISPRS J Photogramm Remote Sens 66(3):247–259
Nielsen AA (2011) Kernel maximum autocorrelation factor and minimum noise fraction transformation. IEEE Trans Image Process 20(3):612–624
Pan ZK, Wang F, Xia LH, Zou X (2012) Research in urban vegetation stress monitoring by hyperspectral remote sensing. Remote Sens Technol Appl 27(1):68–76
Sahin M, Yildiz BY, Senkal O, Pestemalci V (2012) Modeling and remote sensing of land surface temperature in Turkey. J Indian Soc Remote Sens 40(3):399–409
Sanchez-Azofeifa A, Rivard B, Wright J, Feng JL, Li PJ, Chong MM, Bohiman SA (2011) Estimation of the distribution of Tabebuia guayacan (Bignoniaceae) using high-resolution remote sensing imagery. Sensors 11(4):3831–3851
Segl K, Roessner S, Heiden U (2003) Fusion of spectral and shape features for identification of urban surface cover types using reflective and thermal hyperspectral data. ISPRS J Photogramm Remote Sens 58(1–2):99–112
Song XF, Jiao LC (2012) Classification of hyperspectral remote sensing image based on sparse representation and spectral information. J Electron Inf Technol 34(2):268–272
Teodoro AC, Araújo R (2016) A comparison of performance of OBIA techniques available in open source software (spring and OTB/Monteverdi) considering very high spatial resolution data. J Appl Remote Sens 10(1):016011
Wang XM, Zeng SG, Xia DS (2006) Remote sensing image classification based on a loose modified FastICA algorithm. J Comput Res Dev 43(4):708–715
Wang ZQ, Liu XQ, Zhang GL, Wang ZJ (2007) Face recognition based on PCA and ICA. J Huazhong Nor Univ 41(3):373–376
Ward CA, Starks SA (2000) An approach to predict Africanized honey bee migration using remote sensing. Comput Electr Eng 26(1):33–45
Wen XP, Yang XF, Hu GD (2011) Relationship between land cover ration and urban heat island from remote sensing and automatic weather stations data. J Indian Soc Remote Sens 39(2):193–201
Xu YM, Qin ZH, Wan HX (2010) Spatial and temporal dynamics of urban heat island and their relationship with land cover changes in urbanization process: a case study in Suzhou, China. J Indian Soc Remote Sens 38(4):654–663
Yang ZS, Guo L, Luo X, Hu XT (2006) A PCA based band selection algorithm of hyperspectral image. Microelectron Comput 23(12):72–74
Yang ZX, Zou ZR, Tao C, Tian YP, He XF (2015) Hyperspectral image classification based on the combination of spatial-spectral feature and sparse representation. Acta Geod Cartographica Sin 44(7):775–781
Yi WB, Tang H, Chen YH (2011) An object-oriented semantic clustering algorithm for high-resolution remote sensing images using the aspect model. IEEE Geosci Remote Sens Lett 8(3):522–526
Zhang LP, Huang X (2009) Advanced processing techniques for remotely sensed imagery. J Remote Sens 13(4):559–569
Acknowledgements
We thank the vital comments made by the reviewers, the editorial team, and the technique support by “Ziqiang 4000” HPC team in Shanghai University. This work was co-supported by the Projects of National Science Foundation of China (41404024), Shanghai Science and Technology Development Foundation (16dz1206000 and 16142203000), and Young Teachers Training and Supporting Plan in Shanghai Universities (ZZSD14025). The HSI remote sensing image was obtained from the China Centre for Resource Satellite Data and Application. The authors gratefully acknowledge these supports.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liu, L., Li, Cf., Lei, Ym. et al. Feature extraction for hyperspectral remote sensing image using weighted PCA-ICA. Arab J Geosci 10, 307 (2017). https://doi.org/10.1007/s12517-017-3090-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12517-017-3090-1