استفاده از آنالیزهای مورفولوژی به‌منظور بهبود دقت طبقه‌بندی تصاویر ابر‌طیفی با حد تفکیک بالا

نوع مقاله : علمی - پژوهشی

نویسنده

دانشگاه خواجه نصیرالدین طوسی

چکیده

 آنالیز موفولوژی، با تمرکز بر آنالیز روابط مکانی بین پیکسل‌های همسایه، پردازش تصویر کامل‌تری را در مقایسه با آنالیزهایی که بر پایة اثر طیفی یک پیکسل تنها هستند، به‌دست می‌دهد. روش پیشنهادی در این مقاله با استفادة هم‌زمان از اطلاعات طیفی و اطلاعات مکانی حاصل از آنالیز مورفولوژی نتایج نهایی طبقه‌بندی را در تصاویر ابر‌طیفی بهبود می‌بخشد. در این پژوهش ابتدا با استفاده از نمونه‌های آموزشی محدود، ویژگی‌های منتخب اولیه استخراج شدند و پس از اعمال آنالیزهای مورفولوژی روی هر یک از آنها، پروفایل‌های مورفولوژی تشکیل شدند و از ترکیب این پروفایل‌ها، پروفایل مورفولوژی گسترده تولید شد. سپس پروفایل مورفولوژی گسترده‌شده با ویژگی‌های منتخب اولیه ترکیب شد و مجدداً استخراج ویژگی نهایی صورت گرفت. ویژگی‌های منتخب نهایی با استفاده از طبقه‌بندی‌کنندة ماشین‌ بردار پشتیبان طبقه‌بندی شدند. سپس پس‌پردازش تصویر نهایی با استفاده از فیلتر رأی‌گیری اکثریت انجام شد. این روش، روی دادة شهری و نیمه‌شهری از سنجندة ROSIS تست شد. دقت طبقه‌بندی نهایی از 86/98 و 70/82 درصد در روش‌های معمولی به 36/99 و 75/95 درصد در روش پیشنهادی به‌ترتیب در تصویر منطقة شهری و نیمه‌شهری افزایش یافته است.  کلید‌واژه‌ها: آنالیز مورفولوژی، ماشین‌بردار پشتیبان، استخراج ویژگی، طبقه‌بندی، رأی‌گیری اکثریت.   

کلیدواژه‌ها


عنوان مقاله [English]

Using of Morphology Analysis for Precision Improvement of High Resolution Hyper Spectral Images Classification

چکیده [English]

Morphology analysis which concentrates on spatial relations analysis between neighborhood pixels provides a better image processing compared to analyses which are only based on spectral signature of a single pixel. The proposed method in this paper integrates spectral and spatial information produced from morphology analysis to improve the final result of hyper spectral image classification. For this reason at first, primary components are extracted using limited training samples. Extended morphological profiles are then produced by applying morphological analysis on each extracted features. Afterwards, Final components are extracted by applying a supervised feature selections on a datasets composed of both the spectral and the extended morphological features. The extracted features are introduced into the Support Vector Machine (SVM) algorithm. The final results are then archived by implementing a majority filter as a post-processing step. The proposed method is implemented on aerial hyper spectral images of Rosis sensor taken from urban and semi-urban areas from. The obtained results proved the efficiency of the proposed method where classification accuracies are improved from 98.86 and 82.70 in conventional method to 99.36 and 95.75 in urban and semi-urban areas respectively. Keywords: Morphological Analysis, Support Vector Machines (SVMS), Feature Extraction (FE), Classification, Majority Vote

  1. Akcay H. G¨okhan and Selim Aksoy, 2007, Morphological Segmentation of Urban Structures, IEEE, Department of Computer Engineering, Bilkent University.
  2. Benediktsson J.A., J.A. Palmason, and J. Sveinsson, Mar., 2005, Classification of Hyperspectral Data from Urban Areas Based on Extended Morphological Profiles, IEEE Trans. Geosci. Remote Sens., Vol. 43, No. 3, PP. 480–491.
  3. Benediktsson J.A., M. Pesaresi, and K. Arnason, Sep. 2003, Classification and Feature Extraction for Remote Sensing Images from Urban Areas Based on Morphological Transformations, IEEE Trans. Geosci. Remote Sens., Vol. 41, No. 9, PP. 1940–1949 .
  4. Chang C.I., 2003, Hyperspectral Imaging: Techniques for Spectral Detection and Classification, New York: Kluwer/Plenum.
  5. Chanussot J., J.A. Benediktsson and M. Fauvel, Jan., 2006, Classification of Remote Sensing Images from Urban Areas Using a Fuzzy Possibilistic Model, IEEE Geosci. Remote Sens. Lett., Vol. 3, No. 1, PP. 40–44.
  6. Epifanio I. and P. Soille, Apr., 2007, Morphological Texture Features for Unsupervised and Supervised Segmentations of Natural Landscapes, IEEE Trans. Geosci Remote Sens., Vol. 45, No. 4, PP. 1074–1083.
  7. Fauvel M., J. Chanussot and J.A. Benediktsson, 2006, Evaluation of Kernels for Multiclass Classification of Hyperspectral Remote Sensing Data, in Proc. ICASSP, Vol. 2,
  8. PP. 813–816.
  9. Fauvel Mathieu, 2007, Spectral and Spatial Methods for the Classification of Urban Remote Sensing Data, Doctoral Thesis.
  10. Fauvel Mathieu, Jon Atli Benediktsson, Jocelyn Chanussot, and Johannes R. Sveinsson, 2008, Spectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles, Transactians on Geoscience and Remote Sensing, Vol. 46, No. 11.
  11. Ghamari asl Mohsen, 2006, Using Nonparametric Weighted Feature Extraction for Dimension Reduction of Hyprspectral Image, Master of science thesis, K.N. Toosi University of Technology.
  12. Goetz A.F.H., G. Vane, J.E. Solomon and B.N. Rock, 1985, Imaging Spectrometry for Earth Remote Sensing, Science, Vol. 228, No. 4704, PP. 1147-1153.
  13. Gonzalez R.C. and R.E. Woods, 2008, Digital Image Processing, Prentice Hall.
  14. Gualtieri J.A. and R.F. Cromp, 1998, Support Vector Machines for Hyperspectral Remote Sensing Classification, Proc. SPIE, Vol. 3584, PP. 221–232.
  15. Gualtieri J.A. and S. Chettri, 2000, Support Vector Machines for Classification of Hyperspectral Data, in Proc. IGARSS, Vol. 2, PP. 813–815.
  16. Halldorsson G.H., J.A. Benediktsson and J.R. Sveinsson, 2003, Support Vector Machines in Multisource Classification, in Proc. IGARSS, Vol. 3, PP. 2054–2056.
  17. He Lin, 2010, Multiscale-Multivariate Autoregressive Detection for Hyperspectral Imagery, Artificial Intelligence and Computational Intelligence (AICI), PP. 120_123.
  18. Jia X., J.A. Richards and D. E. Ricken, 1999, Remote Sensing Digital Image Analysis: An Introduction, Berlin, Germany: Springer-Verlag.
  19. Jimenez L. and D.A. Landgrebe, 1998, Supervised Classification in High-dimensional Space: Geometrical, Statistical, and Asymptotical Properties of Multivariate Data, IEEE Trans. Syst., Man, Cybern. C., Vol. 28, PP. 39–54.
  20. Kelman Timothy, 2009, Classification of Chinese Tea Samples for Food Quality Control using Hyperspectral Imaging, Centre for excellence in Signal and Image Processing, Dept of Electronic and Electrical Engineering, University of Strathclyde.
  21. Keshavarz Ahmad, Ghasemiyan Hasan, 2005, A Fast Algorithm Based on Support Vector Machin for Classification of Hyperspectral Image Using Spatial Correlation, Iranian Journal of Electrical and Computer Engineering (IJECE), No. 1.
  22. Landgrebe D. A., 2003, Signal Theory Methods in Multispectral RemoteSensing, Hoboken, NJ: Wiley.
  23. Mojaradi Barat, 2009, Feature Extraction for Classification of Hyperspectral Image, Doctoral thesis, K.N. Toosi Univrsity of Technology.
  24. Palmason J.A., J.A. Benediktsson, J.R. Sveinsson and J. Chanussot, 2005, Classification of Hyperspectral Data from Urban Areas Using Morphological Preprocessing and Independent Component Analysis, in Proc. IGARSS, Vol. 1, PP. 176–179.
  25. Pesaresi M., 2001, A New Approach for the Morphological Segmentation of High-Resolution Satellite Imagery, IEEE Trans. Geosci. Remote Sens., Vol. 39, No. 2,
  26. PP. 309–320.
  27. Plaza A., P. Martinez, J. Plaza, R.M. Perez, 2005, Dimensionality Reduction and Classification of Hyperspectral Image Data Using Sequences of Extended Morphological Transformations, IEEE Trans. Geosci. Remote Sens., Vol. 43, No. 3, PP. 466-479.
  28. Rahimzadegan Majid, 2007, Presentation of Method for Using Feature Extraction and Integeration of Classifiers for Classification of Hyperspectral Data, master of science thesis, K.N. Toosi Univrsity of Technology.
  29. Richards John A., 2006, Remote Sensing Digital Image Analysis, The Australian National University Research School of Information Sciences, Springer-Verlag Berlin Heidelberg.
  30. Scott D.W., 1992, The Curse of Dimensionality and Dimension Reduction, in Multivariate Density Estimation, Theory, Practice, and Visualization, New York: Wiley, ch. 7,
  31. PP. 195–217.
  32. Shah hoseyni Reza, Homayooni Saeed, Serajian Mohamad Reza, 2009, Classification of Hyperspectral Image Using of Support Vector Machin, Tehran university, Geomatic conference.
  33. Soille Pierre, 2003, Morphological Image Analysis: Principles and Applications, Springer-Verlag New York, Inc. Secaucus, NJ.
  34. Tarabalka Yuliya, 2009, Spectral–Spatial Classification of Hyperspectral Imagery Based on Partitional Clustering Techniques, IEEE Geoscience and Remotesensing, Vol. 47, No. 8.
  35. Tian Qingjiu, 2010, Extraction of Hydrocarbon Content Information by Using Hyperspectral Image, Geoinformatics, 2010 18th International Conference on.
  36. Tuominen Jyrki, 2011, Detection of Environmental Change Using Hyperspectral Remote Sensing, Tampere University of Technology, Pori Unit.
  37. Zortea M., A. Plaza, 2009, Spatial Preprocessing for Endmember Extraction, IEEE, Transactions on Geoscince and Remote Sensing.