Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data
Borzov S.M., Guryanov M.A., Potaturkin O.I.

 

Institute of Automation and Electrometry of the Siberian Branch of the Russian Academy of Sciences, 630090, Novosibirsk Russia, Academician Koptyug ave. 1

 PDF

Abstract:
The article is devoted to the effectiveness research of methods of controlled spectral and spectral-spatial classification of hyperspectral data. In particular, minimum distance, support vector machine, mahalanobis distance and maximum likelihood methods are considered on the example of vegetative cover types differentiation. Significant attention is paid to studying the dependence of the accuracy of data classification with listed methods on the spectral features number and their selection method. The perspectivity of complex processing of spectral and spatial features, considering the correlation of close pixels, is demonstrated. The experimental results obtained with various methods of forming training sets are presented.

Keywords:
remote sensing, hyperspectral images, cover types classification, spectral and spatial features, image processing

Citation:
Borzov SM, Guryanov MA, Potaturkin OI. Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data. Computer Optics 2019; 43(3): 464-473. DOI: 10.18287/2412-6179-2019-43-3-464-473.

References:

  1. Soifer VA, ed. Information technologies remote sensing of the Earth [In Russian]. Samara: “Novaya Tehnika” Publisher; 2015. ISBN: 978-5-88940-138-4.
  2. Ostrikov VN, Plahotnikov OV, Kirienko AV. Processing of hyperspectral data obtained from aeronautical and space carriers [In Russian]. Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa 2013; 10(2): 243-251.
  3. Kuznetsov AV, Myasnikov VV. A comparison of algorithms for supervised classification using hyperspectral data [In Russian]. Computer Optics 2014; 38(3): 494-502.
  4. Fursov VA, Bibikov SA, Bajda OA. Thematic classification of hyperspectral images using conjugacy indicator. [In Russian]. Computer Optics 2014; 38(1): 154-158.
  5. Bibikov SA, Kazanskiy NL, Fursov VA. Vegetation type recognition in hyperspectral images using a conjugacy indicator [In Russian]. Computer Optics 2018; 42(5): 846-854. DOI: 10.18287/2412-6179-2018-42-5-846-854.
  6. Plaza A, Du Q, Bioucas-Dias J, Jia X, Kruse F. Foreword to the special issue on spectral unmixing of remotely sensed data. IEEE Trans Geosci and Remote Sensing 2011; 49(11): 4103-4110.
  7. Denisova AY, Juravel YN, Myasnikov VV. Estimation of parameters of a linear spectral mixture for hyperspectral images with atmospheric distortions [In Russian]. Computer Optics 2016; 40(3): 380-387. DOI: 10.18287/2412-6179-2016-40-3-380-387.
  8. Kozoderov VV, Kondranin TV, Dmitriev EV. Natural and anthropogenic objects pattern recognition and their condition assessment using multispectral and hyperspectral airspace remote sensing data [In Russian]. Issledovanie Zemli iz kosmosa 2014; 1: 35-42.
  9. Asmus VV, Buchnev AA, Pyatkin VP. Controlled classification of Earth remote sensing data. Optoelectronics, instrumentation and data processing 2008; 44(4): 60-67.
  10. Plaza A, Benediktsson JA, Boardman JW, Brazile J, Bruzzone L, Camps-Valls G, Chanussot J, Fauvel M, Gamba P, Gualtieri A, Marconcini M, Tilton JC, Trianni G. Recent advances in techniques for hyperspectral image processing/ Remote Sensing of Environment 2009; 113: 110-122.
  11. Borzov SM, Potaturkin OI. Efficiency of the spectral-spatial classification of hyperspectral imaging data. Optoelectronics, instrumentation and data processing 2017; 53(1): 26-34.
  12. Borzov SM, Potaturkin OI. Spectral-spatial methods for hyperspectral image classification: Review. Optoelectronics, instrumentation and data processing 2018; 54(6): 582-599.
  13. Huang X, Zhang L. An SVM ensemble approach combining spectral, structural, and semantic features for the classification of high-resolution remotely sensed imagery. IEEE Trans Geosci Remote Sens 2013; 51(1):257-272.
  14. Wang ZY, Nasrabadi NM, Huang TS. Spatial-spectral classification of hyperspectral images using discriminative dictionary designed by learning vector quantization. IEEE Trans Geosci Remote Sens 2014; 52(8): 4808-4822.
  15. Chen C, Li W, Tramel EW, Cui M, Prasad S, Fowler JE. Spectral-spatial preprocessing using multihypothesis prediction for noise-robust hyperspectral image classification. IEEE J Sel Top Appl Earth Observ Remote Sens 2014; 7(4): 1047-1059.
  16. Li W, Ran Q, Du Q, Yang C. Improved classification of conservation tillage practices using hyperspectral imagery with spatial-spectral features. Proceedings in the 3rd International Conference on Argo-Informatics 2014; 14618199. DOI: 10.1109/Agro-Geoinformatics.2014.6910589.
  17. Li W, Hu W, Ran Q, Zhang F, Du Q, Younan N. Improving hyperspectral image classification using smoothing filter via sparse gradient minimization. Proceedings of the 8th IAPR Workshop on Pattern Recognition in Remote Sensing 2014; 14649026. DOI: 10.1109/PRRS.2014. 6914279.
  18. Palsson F, Ulfarsson MO, Sveinsson JR. Hyperspectral image denoising using a sparse low rank model and dual-tree complex wavelet transform. IEEE Geoscience and Remote Sensing Symposium (IGARSS) 2014: 14716286. DOI: 10.1109/IGARSS.2014.6947279.
  19. Borhani M, Ghassemian H. Hyperspectral image classification based on spectral-spatial features using probabilistic SVM and locally weighted Markov random fields. Proceedings of the Iranian Conference on Intelligent Systems (ICIS) 2014: 14253336. DOI: 10.1109/IranianCIS.2014.6802573.
  20. Borhani M, Ghassemian H. Hyperspectral image classification based on non-uniform spatial-spectral kernels. Proceedings of the Iranian Conference on Intelligent Systems (ICIS) 2014: 14253321. DOI: 10.1109/IranianCIS.2014.6802579.
  21. Zhen Ye, Mingyi He, Fowler JE, Qian Du. Hyperspectral image classification based on spectra derivative features and locality preserving analysis. Proceedings of the Signal and Information Processing (ChinaSIP), IEEE China Summit & International Conference 2014: 138-142. DOI: 10.1109/ChinaSIP.2014.6889218.
  22. Nezhevenko ES, Feoktistov AS, Dashevskii OYu. Neural network classification of hyperspectral images on the basis of the Hilbert-Huang transform. Optoelectronics, instrumentation and data processing 2017; 53(2): 165-170.
  23. Myasnikov EV. Hyperspectral image segmentation using dimensionality reduction and classical segmentation approaches. Computer Optics 2017; 41(4): 564-572.
  24. Zimichev EA, Kazanskiy NL, Serafimovich PG. Spectral-spatial classification with k-means++ particional clustering [In Russian]. Computer Optics 2014; 38(2): 281-286.
  25. Bondur VG. Modern approaches to processing large hyperspectral and multispectral aerospace data flow. Izvestiya. Atmospheric and oceanic physics 2014; 50(9): 840-852.
  26. Pestunov IA, Rylov SA. Algorithms of spectral and texture segmentation of satellite images of high spatial resolution [In Russian]. Vestnik KemGU 2012; 52(4/2): 104-109.
  27. Borzov SM, Potaturkin OI. Classification of vegetation types according to hyperspectral data of remote sensing of the Earth [In Russian]. Vestnik NGU: Informacionnye tehnologii 2014; 12(4): 13-22.
  28. Kruse FA, Lefkoff AB, Boardman JB, Heidebrecht KB, Shapiro AT, Barloon PJ, Goetz AFH. The spectral image processing system (SIPS) – interactive visualization and analysis of imaging spectrometer data. Remote Sensing of Environment 1993; 44: 145-163.
  29. Joachims T. Making large scale SVM learning practical. In Book: Schölkopf B, Burges ChJC, Smola AJ, eds. Cambridge: MIT Press; 1998: 169-184. DOI: 10.17877/DE290R-5098.
  30. Richards JA. Remote sensing digital image analysis. Berlin, Heidelberg: Springer; 2013.
  31. Green AA, Berman M, Switzer P, Craig MD. A transformation for ordering multispectral data in terms of image quality with implications for noise removal. IEEE Transactions on Geoscience and Remote Sensing 1988; 26(1): 65-74.
  32. Lillesand TM, Kiefer RW, Chipman JW. Remote sensing and image interpretation. New York: John Wiley & Song Inc; 2004.
  33. Hughes GF. On the mean accuracy of statistical pattern recognizers. IEEE Transactions on Information Theory 1968; 14(1): 55-63. DOI:10.1109/TIT.1968.1054102.
© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846)332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20