طبقه‌بندی تصاویر چندطیفی با قدرت تفکیک مکانی متوسط، با استفاده از شاخص‌های مکانی و حرارتی

نوع مقاله : علمی - پژوهشی

نویسندگان

1 استادیار گروه سنجش از دور و سیستم اطلاعات جغرافیایی، دانشگاه تربیت مدرس، تهران

2 دانشجوی کارشناسی ارشد سنجش از دور و سیستم اطلاعات جغرافیایی، دانشگاه آزاد اسلامی، واحد علوم و تحقیقات تهران

چکیده

در طبقه‌بندی تصاویر با قدرت تفکیک مکانی متوسط، مانند لندست، تمایز اراضی کشاورزی بدون پوشش گیاهی از زمین‌های بایر و همچنین، شناسایی زمین‌های بایر از مناطق ساخته‌شده معمولاً دشوار و همراه با خطاست. به همین علت در این مطالعه، ترکیب‌های متفاوتی از ویژگی‌های ورودی، به‌روش‌های طبقه‌بندی، به‌منظور بررسی امکان ارتقای دقت طبقه‌بندی مقایسه شد. داده‌های ورودی شامل باندهای طیفی تصویر لندست-7، ویژگی‌های بافتی شامل ماتریس وقوع هم‌زمان گام‌های خاکستری و شاخص‌های حرارتی و مکانی پیشنهادی در این تحقیق است. در بررسی حاضر، به‌منظور طبقه‌بندی سناریوهای متفاوت، از سه روش طبقه‌بندی شامل بیشترین میزان شباهت، شبکة عصبی و ماشین بردار پشتیبان با هسته‌های متفاوت استفاده شد. نتایج نشان داد که ادغام تمامی داده‌های ورودی و استفاده از روش ماشین بردار پشتیبان با هستة پایة شعاعی، با صحت کلی 81/۹۸% و ضریب کاپا 25/98%، ممکن است نتایجی بهتر از دیگر روش‌ها و سناریوها داشته باشد. همچنین، در تحلیل اهمیت متغیرهای ورودی، با استفاده از روش انتخاب ویژگی برپایة جنگل تصادفی، مشخص شد که شاخص‌های پیشنهادی در این مطالعه نقش مهمی در طبقه‌بندی با صحت بالا و کارآمد داشته‌اند.

کلیدواژه‌ها


عنوان مقاله [English]

Medium Spatial Resolution Image Classification Based on Spatial and Thermal Indices

نویسندگان [English]

  • A Shamsoddini 1
  • Sh Esmaeili 2
1 Assistant Prof., Dep. of Remote Sensing and GIS Tarbiat Modares University, Tehran
2 M.Sc. Student, Dep. of Remote Sensing and GIS, Islamic Azad University, Science and Research branch, Tehran
چکیده [English]

Differentiating agricultural areas which are not covered by vegetation from bare lands as well as identifying bare lands from urban areas in medium spatial resolution images, e.g. Landsat imagery, are usually difficult and erroneous tasks which lead to the inaccurate classification results. Therefore, this study aims to present a new approach to increase the accuracy of the classification. For this purpose, different scenarios were applied based on different input attributes. The input attributes comprised of spectral bands, textural attributes, i.e. grey level co-occurrence matrix (GLCM), and two types of indices including spatial and thermal attributes proposed in this study. Three classification methods, maximum likelihood (ML), artificial neural networks (ANN), and support vector machine (SVM) embedded with different kernels, were applied to examine different scenarios. The results showed that SVM algorithm embedded with Radial basis function (RBF) results in better accuracy, with overall accuracy of 98.81% and Kappa coefficient of 98.25%, when all types of input attributes were combined together. Finally, the variable importance analysis by random forest feature selection indicated that the proposed indices played an important role to execute more efficient classification by SVM.

کلیدواژه‌ها [English]

  • Landsat 7
  • Random forest
  • Textural information
  • Spatial index
  • Brightness temperature
  • Support vector machine
  1. Afifi, A., 2014, Laguerre Kernels – Based SVM for Image Classification, International Journal of Advanced Computer Science and Applications, 5(1), PP. 15-23.
  2. As-syakur, A.R., Adnyana, I.W.S., Arthana, I.W., Nuarsa, I.W., 2012, Enhanced Built-Up and Bareness Index (EBBI) for mapping Build-Up and Bare Land in an Urban Area, Remote Sensing, 10(4), PP. 2957-2970.
  3. Bastitella, D.L.U. & Moran, E., 2007, Land-Cover Classification in the Brazilian Amazon with the integration of Landsat ETM+ and Radarsat data, International Journal of Remote Sensing, 28(24), PP. 5447-5479.
  4. Belgiu, M. & Dragut, L., 2016, Random Forest in Remote Sensing: A Review of Application and Future Directions, ISPRS Journal of Photogrammetry and Remote Sensing, 114, PP., 24-31.
  5. Bishop, C.M., 2007, Pattern Recognition and Machine Learning, Springer. USA, Chapter 3.
  6. Chen, C.H. & Young, G.K., 1982, A Study of Texture Classification Sensing Spectral Features, Human Factors Engineering & Man Machine System, 19(22), PP. 1-14.
  7. Chu, H.T., Ge, L., Ng, A.H.N. & Rizos, C., 2012, Application of Genetic Algorithm and Support Vector machine in Classifiation of Mulrisource Remote Sensing Data, International Journal Remote Sensing Applications, 2(2), PP.1-11.
  8. Cristianini, N. & Taylor, J.S., 2000, An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, Cambridge University, USA, Chapter 6.
  9. Devadas, R., Denham, R.J. & Pringle, M., 2012, Support Vector Machine Classification of Object-Based Data for Crop Mapping, Using Multi-Temporal Landsat Imagery, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XXXIX-B7, 2012 XXII ISPRS Congress, 25 August – 01 September 2012, Melbourne, Australia.
  10. Eiumnoh, A. and Shrestha, R.P., 2000, Application of DEM Data to Landsat Image Classification: Evaluation In a Tropical Wet-Dry Landscape of Thailand, Photogram. Eng. Remote Sensing, 66, PP. 297-1304.
  11. Fauvel, M., Chanussot, J. & Benediktsson, J.A., 2012, A Spatial-Spectral Kernel-Based Approach for the Classification of Remote-Sensing Images, Pattern Reconition, 45(1), PP. 381-392.
  12. Otukei, J.R. & Blaschke, B., 2010, Land Cover Change Assessment Using Decision Trees, Support Vector Machines and Maximum Likelihood Classification Algorithms, International Journal of Applied Earth Observation and Geoinformation, 12S, PP. S27-S31.
  13. Gao, J., Xu, L. & Huang, F., 2016, A Spectral-Textural Kernel-Based Classification Method of Remotely Sensed Images, Neural Computing and Applications, 27(2), PP. 431-446.
  14. Hughes, G.F., 1968, On the Mean Accuracy of Statistical Pattern Recognizers, IEEE Trans. on Information Theory, 14(1), PP. 55-63.
  15. Haralick, R., Shanmugam, K. & Dinstein, I., 1973, Textural Features for Image Classification, IEEE Transactions on Systems, Man, and Cybernetics, 3(6), PP. 610-621.
  16. Hulchinson, C.K., 1982, Techniques for Combining Landsat and Ancillary Data for Digital Classification Improvement, Photogram, Eng. Remote Sensing, 48, PP. 123-130.
  17. Herold, M., Gardner, M.E. & Roberts, D.A., 2003, Spectral Resolution Requirements for Mapping Urban Areas, IEEE Trans. Geosci. Remote Sensing, 41(9), PP. 1907-1919.
  18. Jin, M. & Liang, Sh., 2006, An Improved Land Surface Emissivity Parameter for Land Surface Models Using Global Remote Sensing Observations, American Meteorological Society, 19(12), PP. 2867-2881.
  19. Kavazoglu, T. & Colkesen, I., 2009, A Kernel Functions Analysis for Support Vector Machines for Land Cover Classification, International Journal of Applied Earth Observation and Geoinformation, 11(5), PP. 352-359.
  20. Kurosu, T., Yokoyama, S., Fujita, M. & Chiba, K., 2001, Land Use Classification with Textural Analysis and the Aggreation Techique Using Multi-Temporal JERS1-1 L-band SAR images, International Journal of Remote Sensing, 22(4), PP. 595-613.
  21. Li, S. & Chen, X., 2014, A New Bare-Soil Index for Rapid Mapping Developing Areas Using Landsat,The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 14-16 May. Suzhou, China.
  22. Lu, D. & Weng, Q., 2006, Use of Impervious Surface in Urban Land-Use Classification, Remote Sensing of Environment, 102(1), PP. 146-160.
  23. Lo, C.P. & Chol, J., 2004, A Hybrid Approach to Urban Land Use/Cover Mapping Sing Landsat 7 Enhanced Thematic Mapper Plus (ETM+) Images, Int.J. Remote Sensing, 125(4), PP. 2687-2700.
  24. Lu, D. & Weng, Q., 2005, Urban Classification Using Full Spectral Information of Landsat ETM+ Imagery in Marion County, Indiana, Photogrammetric Engineering and Remote Sensing, 71(11), PP. 1275-1284.
  25. Li, C., Wang, J., Wang, L., Hu, L. & Cong, P., 2014, Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Lassification with Landsat Thematic Mapper Imagery, Remote Sensing, 6(2), PP. 964-983.
  26. Melgani, G. & Bruzzone, L., 2004, Classification of Hyperspectral Remote Sensing Images with Support Vector Machines, IEEE Transactions on Geoscience and Remote Sensing, 42(8), PP. 1778-1790.
  27. Nguyen, T., Huang, J.Z. & Nguyen, T., 2015, Unbiased Feature Selection in Learning Random Forests for High-Dimensional Data, The Scientific World Journal, 2015, PP. 1-18.
  28. Oommen, T., Misra, D., Twarakavi, N., Prakash, A., Sahoo, B. & Bandopadhyay, S., 2008, An Objective Analysis of Support Vector Machine Based Classification for Remote Sensing, Mathematical Geosciences, 40, PP. 409-424.
  29. Raval, S. & Shamsoddini, A., 2014, A Monitoring Framework for Land Use Around Kaoli Mining Areas Through Landsat TM Images, Erath Sci Information, 7(3), PP. 153-163.
  30. Richards. J.A., 2013, Remote Sensing Digital Image Analysis, Springer, Springer.Verlag Berlin Heidelberg, Chapter 8.
  31. Ruiz, L.A., Sarria, A.F. & Recio, J.A., 2004, Texture Feature Extraction for Classification of Remote Sensing Data Using Wavelet Decomposition: A Comparative Study, 20th ISPRS Congress. 12 to 23 July. Istanbul, Turkey.
  32. Snyder, W.C., Wan, Z., Zhang, Y. & Feng, Z., 1998, Classification-Based Emissivity for Land Surface Temperature Measurement from Space, International Journal Remote Sensing, 19(14), PP. 2753-2774.
  33. Shaban, M. & Dikshit, O., 2001, Improvement of Classification in Urban Areas by the Use of Textural Features: The Case Study of Lucknow City, Uttar Pradesh, International Journal Remote Sensing, 22(4), PP. 565-593.
  34. Stehman, S.V., 1997, Estimating Standard Errors of Accuracy Assessment Statistics under Cluster Sampling, Remote Sensing of Environment , 60(3), PP. 258-269.
  35. Sim, J. & Wright, C.C., 2005, The Kappa Statistic in Reliability Studies: Use, Interpretation, and Sample Size Requirements, Phys Ther, 85(3), PP. 257-268
  36. Tadesse, W., Coleman, T.L. & Tsegaye, T.D., 2003, Improvement of Land Use and Land Cover Classification of an Urban Area Using Image Segmentation from Landsat ETM Data, Proceedings of the 30th International Symposium on Remote Sensing of the Environment, November 10-14. Honolulu, Hawaii.
  37. Waqar, M.M., Miraza, J.F., Mumtaz, R. & Hussain, E., 2012, Development of New Indices for Extraction of Built-Up Area & Bare Soil From Landsat Data, Scientific Reports, 1(1), PP. 2- 4.
  38. Https://www.usgs.gov/faqs/what-are-band-designations-landsat-satellites-0?qt-news_science_products=7#qt-news_science_products.
  39. Shi, X., & Xue, B., 2016, Parallelizing Maximum Likelihood Classification on Computer Cluster and Graphics Processing Unit for Supervised Image Classification, International Journal of Digital Earth, PP.1-12.
  40. Yuan, H.F.C., Wlele, V. & Khorram, S., 2009, An Automated Artificial Neural Network System for Land Use/Land Cover Classification from Landsat TM Imagery, Remote Sensing, 1(1), PP. 243-265.
  41. Zhang, J., Li, P. & Wang, J., 2014, Urban Built-Up Area Extraction from Landsat TM/ETM+ Images Using Spectral Information and Multivariate Texture, Remote Sensing, 6, PP. 7339-7359.
  42. Zhu, C., 1996, Remote Sensing Image Texture Analysis and Classification with Wavelet Transform, International Archives of Photogrammetry and Remote Sensing, 19(16), 12-18 July, Vienna, Austria.