(44-6) 11 * << * >> * Russian * English * Content * All Issues

Increasing the classification efficiency of hyperspectral images due to multi-scale spatial processing
S.M. Borzov 1, O.I. Potaturkin 1

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

 PDF, 1165 kB

DOI: 10.18287/2412-6179-CO-779

Pages: 937-943.

Full text of article: Russian language.

Abstract:
Classification of the land cover types from multi- and hyperspectral (HS) imagery is traditionally carried out on the basis of analysis of scatter plots of pixel values in a multidimensional feature space, which are used as brightness in individual channels. To increase the reliability of HS image classification, approaches are used based on simultaneously accounting for the characteristics of each pixel and the nearest-neighbor pixels, i.e., on the joint analysis of spectral and spatial features. The pixel neighborhood analysis is performed at various stages of the classification process.
     In this work, using a test hyperspectral image, the efficiency of spectral-spatial data classification methods that take into account spatial information at various stages of processing is studied. Special attention is paid to selecting the size of the spatial processing core. It is shown that the best results are obtained by combining pre-processing of raw data before performing the procedures of pixel-by-pixel spectral classification and post-processing of the resulting maps. Prospects of multi-scale smoothing of initial images, with the increase of the number of spectral-spatial features being multiple of the number of the scales, are shown.

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

Citation:
Borzov SM, Potaturkin OI. Increasing the classification efficiency of hyperspectral images due to multi-scale spatial processing. Computer Optics 2020; 44(6): 937-943. DOI: 10.18287/2412-6179-CO-779.

Acknowledgements:
This work was financially supported by the RF Ministry of Science and Higher Education within the State assignment No. АААА-А17-117052410034-6 in IA&E SB RAS.

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. Bondur VG. Modern approaches to processing large streams of hyperspectral and multispectral aerospace information [In Russian]. Issledovanie Zemli iz kosmosa 2014; 1: 4-16.
  3. 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.
  4. Kuznetsov AV, Myasnikov VV. A comparison of algorithms for supervised classification using hyperspectral data. Computer Optics 2014; 38(3): 494-502.
  5. Buchnev AA, P’atkin VP. Classification with training of hyperspectral data of remote sensing of the earth [In Russian]. Interexpo Geo-Siberia 2017; 4(2): 8-12.
  6. Bibikov SA, Kazanskiy NL, Fursov VA. Vegetation type recognition in hyperspectral images using a conjugacy indicator. Computer Optics 2018; 42(5): 846-854. DOI: 10.18287/2412-6179-2018-42-5-846-854.
  7. Lebedev LI, Yasakov YuV, Utesheva TSh, Gromov VP, Borusjak AV, Turlapov VE. Complex analysis and monitoring of the environment based on Earth sensing data. Computer Optics 2019; 43(2): 282-295. DOI: 10.18287/2412-6179-2019-43-2-282-295.
  8. Vorobiova NS, Sergeyev VV, Chernov AV. Information technology of early crop identification by using satellite images. Computer Optics 2016; 40(6): 929-938. DOI: 10.18287/2412-6179-2016-40-6-929-938.
  9. Zhukov DV. Method of thematic processing of hyperspectral data in the problem of assessing the ecological state of port waters [In Russian]. Issledovanie Zemli iz kosmosa 2014; 1: 66-71. DOI: 10.7868/S0205961414010084
  10. Borzov SM, Potaturkin OI. Spectral-spatial methods for hyperspectral image classification. review. Optoelectronics, Instrumentation and Data Processing 2018; 54(6): 582-599. DOI: 10.3103/S8756699018060079.
  11. Huo L-Z, Tang P. Spectral and spatial classification of hyperspectral data using SVMs and Gabor textures. IEEE International Geoscience and Remote Sensing Symposium 2011: 1708-1711. DOI: 10.1109/IGARSS.2011.6049564.
  12. Zhang L, Zhang L, Tao D, Huang X. On combining multiple features for hyperspectral remote sensing image classification. IEEE Trans Geosci Remote Sens 2012; 50: 879-893.
  13. Ghamisi P, Dalla Mura M, Benediktsson JA. A survey on spectral–spatial classification techniques based on attribute profiles. IEEE Trans Geosci Remote Sens 2015; 53: 2335-2353.
  14. Fauvel M, Chanussot J, Benediktsson JA, Sveinsson JR. Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles. IEEE Trans Geosci Remote Sens 2008; 46: 3804-3814.
  15. Tuia D, Volpi M, Dalla Mura M, Rakotomamonjy A, Flamary R. Automatic feature learning for spatio-spectral image classification with sparse SVM. IEEE Trans Geosci Remote Sens 2014; 52: 6062-6074.
  16. Gormus ET, Canagarajah N, Achim A. Dimensionality reduction of hyperspectral images with wavelet based empirical mode decomposition. 18th IEEE Int Conf Image Process 2011; 1709-1712.
  17. Nezhevenko ES. Neural network classification of difficult-to-distinguish types of vegetation on the basis of hyperspectral features. Optoelectronics, Instrumentation and Data Processing 2019; 55(3): 263-270. DOI: 10.3103/S8756699019030087.
  18. Kettig RL, Landgrebe DA. Classification of Multispectral Image Data by Extraction and Classification of Homogeneous Objects. IEEE T Geosci Elect 1976; GE-14(1): 19-26.
  19. Benz UC, Hofmann P, Willhauck G, Lingenfelder I, Heynen M. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS J Photogramm Remote Sens 2004; 58(3-4): 239-258.
  20. Varlamova AA, Denisova AY, Sergeev VV. Earth remote sensing data processing for obtaining vegetation types maps. Computer Optics 2018; 42(5): 864-876. DOI: 10.18287/2412-6179-2018-42-5-864-876.
  21. Denisova AY, Egorova AA, Sergeyev VV, Kavelenova LM. Requirements for multispectral remote sensing data used for the detection of arable land colonization by tree and shrubbery vegetation. Computer Optics 2019; 43(5): 846-856. DOI: 10.18287/2412-6179-2019-43-5-846-856.
  22. Lillesand MT, Kiefer RW, Chipman JW. Remote Sensing and Image Interpretation. New York: John Wiley and Sons; 2004.
  23. Borzov SM, Melnikov PV, Pestunov IA, Potaturkin OI, Fedotov AM. Integrated processing of hyperspectral images on the basis on spectral and spatial information [In Russian]. Vychislitel'nye Tekhnologii 2016; 21(1): 25-39.
  24. Pestunov IA, Rylov SA. Algorithms for spectral-texture segmentation of high-resolution satellite images [In Russian]. Vestnik KemGU 2012; 4/2: 104-109.
  25. Myasnikov EV. Hyperspectral image segmentation using dimensionality reduction and classical segmentation approaches. Computer Optics 2017; 41(4): 564-572. DOI: 10.18287/2412-6179-2017-41-4-564-572.
  26. Zimichev EA, Kazanskiy NL, Serafimovich PG. Spectral-spatial classification with k-means++ particional clustering. Computer Optics 2014; 38(1): 281-286.
  27. Borzov SM, Potaturkin AO, Potaturkin OI, Fedotov AM. Analysis of the efficiency of classification of hyperspectral satellite images of natural and man-made areas. Optoelectronics, Instrumentation and Data Processing 2016; 52(1): 1-10. DOI: 10.3103/S8756699016010015.
  28. Borzov SM, Potaturkin OI. Efficiency of the spectral-spatial classification of hyperspectral imaging data. Optoelectronics, Instrumentation and Data Processing 2017; 53(1): 26-34. DOI: 10.3103/S8756699017010058.
  29. 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.
  30. Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods. Cambridge: Cambridge University Press, 2000.
  31. Richards JA. Remote sensing digital image analysis. Berlin, Heidelberg: Springer-Verlag; 1999.
  32. 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 Trans Geosci Remote Sens 1988; 26(1): 65-74.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: ko@smr.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20