قابلیت الگوریتم‌های نظارت شده در تهیه نقشه پوشش اراضی در مقیاس محلی (مطالعه موردی: استان گیلان
محورهای موضوعی : آمایش سرزمین
سیداحمدرضا نورالدینی
1
(دکتری دانشکده منابع طبیعی دانشگاه گیلان* (مسئول مکاتبات).)
امیراسلام بنیاد
2
(استاد دانشکده منابع طبیعی دانشگاه گیلان.)
کلید واژه: سنجند OLI, لندست8, طبقه‌بندی, SV6,
چکیده مقاله :
زمینه و اهداف: امکان بررسی پوشش زمین در مقیاس گسترده با استفاده از داده های سنجش از دور وجود دارد. طبقه بندی پوشش زمین در استان گیلان با استفاده از سنجنده OLI و 4 کرنل ماشین بردار پشتیبان (SVM)، شبکه عصبی مصنوعی (ANN) و حداکثر احتمال (ML) انجام شد. روش بررسی: طبقه بندی ها بر اساس نمونه های تعلیمی 10 پوشش مختلف در کل استان صورت گرفت. برای بالابردن دقت نقشه ها، تصویر OLI با استفاده از محصولات MODIS با اعمال کد انتقال تابشی وکتوری در طیف خورشید (SV6) مورد تصحیح اتمسفری قرار گرفته است. تصویر بر مبنای معیار همگنی به 219000 پلی گون، سگمنت بندی گردید. به روش کاملاَ تصادفی 2% از پلی گون های همگن برای آموزش و آزمون استفاده گردید. با بازدید میدانی، پلی گون ها به کلاس ها برچسب داده شدند. یافته ها: به کارگیری تصاویر تصحیح شده با کد SV6 در طبقه بندی سبب ارتقاء صحت کلی الگوریتم های ANN، SVMو ML به ترتیب به میزان 11/0%، 8/0% و 9/1% گردیده است. ارزیابی نتایج بیان گر برتری کرنل شعاعی SVM به ترتیب با صحت کلی و ضریب کاپای آماری 6/75% و 72/0 است. در این الگوریتم صحت کلاس های کشاورزی، مراتع مشجر و آبی به ترتیب 16/93%، 55/72% و 57/96% است. نتایج بیان گر ارتقاء صحت کلی الگوریتم SVM در مقایسه با الگوریتم ML به میزان 67/1% است. بحث و نتیجه گیری: این تحقیق نشان دهنده برتری روش ناپارامتریکSVM در مقایسه با پارامتریک در تهیه نقشه پوشش اراضی استان گیلان است. اعمال تصحیحات دقیق اثرات اتمسفر بر روی تصاویر در مناطق با مقیاس محلی و بزرگ با توجه به تغییرات شرایط اتمسفر و خصوصیات زمین قابل پیشنهاد است.
Background and Objective: There was a possibility to study earth coverage on a large scale using remote sensing data. The support vector machines (SVM), artificial neural network ‏)ANN( and maximum likelihood )ML‏( algorithms were used to Land cover classification on OLI sensors data and 4 kernels in Guilan province. Methods: Classifications were based on training samples of 10 different covers in the entire Guilan province. To improve the classification accuracy on OLI image data, the MODIS atmospheric products used in 6SV atmospheric correction model. The OLI atmospheric corrected image segmented to 219000 polygons based on homogeneity. In this study 2% of polygons were used to test and training samples by the random statistical method. Polygons labeled to classes by field survey. Findings: Applying ANN, SVM and ML algorithms on the OLI images after atmospheric corrected by 6SV model, the overall accuracy of classification improved 0.11%, 0.8%, and 1.9% respectively. The results indicated that the land cover map by RBF-SVM had overall accuracy and kappa coefficient with 75.6% and 0.72 respectively. In this algorithm accuracy of agriculture, range‏ shrub land and water body classes were ‏93.16%, 72.55% and‏ 96.57% respectively. The results of this study indicated that SVM algorithm improved overall accuracy 1.67% compared to the ML algorithm. Discussion and Conclusion: This research indicated that in land cover classification and mapping of Guilan province, the nonparametric SVM algorithm had more accurate than the ML parametric algorithm. According to the results of this research, it is suggested that atmospheric correction models should be used especially on the large and local images.
1. Feng, M., Sexton, J.O., Huang, C., Masek, J.G., Vermote, E.F., Gao, F., Narasimhan, R., Channan, S., Wolfe, R.E., Townshend, J.R., 2013. Global surface reflectance products from Landsat: Assessment using coincident MODIS observations. Remote Sensing of Environment, 134(1) :276-293.
2. King, M.D., Tsay, S.C., Platnick, S.E., 1997. Cloud retrieval algorithms for MODIS: Optical thickness, effective particle radius, and thermodynamic phase, see information in: https://eospso.nasa.gov/sites/default/files/atbd/atbd_mod05.pdf. 83p.
5. Ju, J., Roy, D.P., Vermote, E., Masek, J., Kovalskyy, V., 2012. Continental-scale validation of MODIS-based and LEDAPS Landsat ETM+ atmospheric correction methods. Remote Sensing of Environment, 122)3(:175–184.
6. Hutt, C., Koppa, W., Miao, Y., Bareth, G., 2016. Best Accuracy Land Use/Land Cover (LULC) Classification to Derive Crop Types Using Multi temporal, Multi sensor and Multi-Polarization SAR Satellite Images. Remote Sens ,8(8) :2-15.
7. Arveti ,N., Etikala, B., Dash, P., 2016. Land Use/Land Cover Analysis Based on Various Comprehensive Geospatial Data Sets: A Case Study from Tirupati Area, South India. Advances in Remote Sensing, 5, 73-82.
8. Lu, D., Batistella, M., Li, G., Moran, E., Hetrick, S., Freitas, C.C., Durta, L.V., Santana SJS. 2012. Land use/cover classification in the Brazilian Amazon using satellite images. NIH. Public. Access, 47)9(: 1-36.
9. Lu, D., Weng, Q.H., 2007. A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 28)5 :(823–870.
10. Jensen, J.R ,.2005. Introductory digital image processing: a remote sensing perspective. 3ed. Upper Saddle River: Prentice Ha.
11. Zhu, G. ,Blumberg, DG., 2002. Classification using ASTER data and SVM algorithms; the case study of Beer Sheva, Israel. Remote Sensing of Environment, 80(2): 233–240.
12. Hu, G., Blumberg, D.G., 2002. Classification using ASTER data and SVM algorithms; the case study of Beer Sheva, Israel. Remote Sensing of Environment, 80(2): 233–24.
13. Foody, GM., Mathur, A., 2004. A relative evaluation of multiclass image classification by support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(6): 1335–1343.
14. Yang, X., 2011. Parameterizing support vector machines for land cover classification. Photogrammetric Engineering & Remote Sensing, 77)1(: 27-37.
15. Yan, L., Roy, D.P., 2014. Automated crop field extraction from multi-temporal Web Enabled Landsat Data. Remote Sensing of Environment, 144(1): 42-64
16. Li, H., Gu, H., Han, Y., Yang, J., 2010. Object-oriented classification of high-resolution remote sensing imagery based on an improved color structure code and a support vector machine. International Journal of Remote Sensing, 31(6): 1453–1470.
17. Kaufman, Y.J, Tanre, D., 1992. Atmospherically resistant vegetation index (ARVI) for EOS-MODIS. IEEE Trans. Geosci. Remote Sens. 30(2): 261–270.
18. Menzel, W., Seemann, S., Li J. 2002. MODIS atmospheric profile retrieval algorithm theoretical basis document (MOD-07), Eos ATBD web site [Online]. see information in: http://modis-atmos.gsfc.nasa.gov/_docs/MOD07MYD07ATBDC005.pdf . 39p.
19. Benz, U.C., Hoffmann, p., Willhauck, G., Lingenfelder, I., Heynen, M., 2004. Multi-resolution object-oriented fuzzy analysis of remote sensing data for GIS-ready Information. ISPRS Journal of Photogrammetry and Remote Sensing, 58(1) :239-258.
20. Song, X.P., Huang, C., Feng, M., Sexton, J.O., Channan, S., Townshend, J.R., 2014. Integrating global land cover products for improved forest cover characterization: an application in North America. International Journal of earth, 9(7): 709-724.
21. Carreiras, J.M.B., Jose. M.C., Pereira. J., Pereira. S., 2006. Estimation of tree canopy cover in evergreen oak woodlands using remote sensing. Forest Ecology and Management, 223(1): 5–53
22. Mather, P.M., 2011. Computer Processing of Remotely-Sensed Images, 4ed. John Wiley & Sons, Ltd: Chichester, UK.
23. Van Niel, T., McVicar, T., Datt, B., 2005. On the relationship between training sample size and data dimensionality: Monte Carlo analysis of broadband multi-temporal classification. Remote Sensing of Environment. 98(1): 468–480.
24. Mountrakis, G., Im, J., Ogole, C., 2011. Support vector machines in remote sensing: A review ISPRS Journal of Photogrammetry and Remote Sensing, 66(1): 247–259.
25. Richards, J.A., 2013. Remote sensing digital image analysis, 4ed, springer.
26. Topaloglur, R.H, Sertele, E., Musaoglune, N., 2016. Assessment of classification of sentinel-2 and landsat-8 data for land cover/use mapping. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLI-B8: 1055-1059.
27. Baatz, M., Schape, A. «Object-oriented and multi-scale image analysis in semantic network»-2nd Int. Ssymposium on Operationalization of Detailed remote sensing, August 1999-Enscheda-Netherlands.
28. Huang, H., Gong, P., Clinton, N., Hui, F., 2008. Reduction of atmospheric and topographic effect on Landsat TM data for forest classification. International Journal of Remote Sensing, 29(19): 5623–5642.
29. Lardeux, C., Frison, P.L., Tison, C., Souyris, J.C., Stoll, B., Fruneau, B., Rudant, J.P., 2009. Support vector machine formulate frequency SAR polar metric data classification. IEEE Transactions on Geoscience and Remote Sensing, 47(12): 4143–4152.
_||_
1. Feng, M., Sexton, J.O., Huang, C., Masek, J.G., Vermote, E.F., Gao, F., Narasimhan, R., Channan, S., Wolfe, R.E., Townshend, J.R., 2013. Global surface reflectance products from Landsat: Assessment using coincident MODIS observations. Remote Sensing of Environment, 134(1) :276-293.
2. King, M.D., Tsay, S.C., Platnick, S.E., 1997. Cloud retrieval algorithms for MODIS: Optical thickness, effective particle radius, and thermodynamic phase, see information in: https://eospso.nasa.gov/sites/default/files/atbd/atbd_mod05.pdf. 83p.
5. Ju, J., Roy, D.P., Vermote, E., Masek, J., Kovalskyy, V., 2012. Continental-scale validation of MODIS-based and LEDAPS Landsat ETM+ atmospheric correction methods. Remote Sensing of Environment, 122)3(:175–184.
6. Hutt, C., Koppa, W., Miao, Y., Bareth, G., 2016. Best Accuracy Land Use/Land Cover (LULC) Classification to Derive Crop Types Using Multi temporal, Multi sensor and Multi-Polarization SAR Satellite Images. Remote Sens ,8(8) :2-15.
7. Arveti ,N., Etikala, B., Dash, P., 2016. Land Use/Land Cover Analysis Based on Various Comprehensive Geospatial Data Sets: A Case Study from Tirupati Area, South India. Advances in Remote Sensing, 5, 73-82.
8. Lu, D., Batistella, M., Li, G., Moran, E., Hetrick, S., Freitas, C.C., Durta, L.V., Santana SJS. 2012. Land use/cover classification in the Brazilian Amazon using satellite images. NIH. Public. Access, 47)9(: 1-36.
9. Lu, D., Weng, Q.H., 2007. A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 28)5 :(823–870.
10. Jensen, J.R ,.2005. Introductory digital image processing: a remote sensing perspective. 3ed. Upper Saddle River: Prentice Ha.
11. Zhu, G. ,Blumberg, DG., 2002. Classification using ASTER data and SVM algorithms; the case study of Beer Sheva, Israel. Remote Sensing of Environment, 80(2): 233–240.
12. Hu, G., Blumberg, D.G., 2002. Classification using ASTER data and SVM algorithms; the case study of Beer Sheva, Israel. Remote Sensing of Environment, 80(2): 233–24.
13. Foody, GM., Mathur, A., 2004. A relative evaluation of multiclass image classification by support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(6): 1335–1343.
14. Yang, X., 2011. Parameterizing support vector machines for land cover classification. Photogrammetric Engineering & Remote Sensing, 77)1(: 27-37.
15. Yan, L., Roy, D.P., 2014. Automated crop field extraction from multi-temporal Web Enabled Landsat Data. Remote Sensing of Environment, 144(1): 42-64
16. Li, H., Gu, H., Han, Y., Yang, J., 2010. Object-oriented classification of high-resolution remote sensing imagery based on an improved color structure code and a support vector machine. International Journal of Remote Sensing, 31(6): 1453–1470.
17. Kaufman, Y.J, Tanre, D., 1992. Atmospherically resistant vegetation index (ARVI) for EOS-MODIS. IEEE Trans. Geosci. Remote Sens. 30(2): 261–270.
18. Menzel, W., Seemann, S., Li J. 2002. MODIS atmospheric profile retrieval algorithm theoretical basis document (MOD-07), Eos ATBD web site [Online]. see information in: http://modis-atmos.gsfc.nasa.gov/_docs/MOD07MYD07ATBDC005.pdf . 39p.
19. Benz, U.C., Hoffmann, p., Willhauck, G., Lingenfelder, I., Heynen, M., 2004. Multi-resolution object-oriented fuzzy analysis of remote sensing data for GIS-ready Information. ISPRS Journal of Photogrammetry and Remote Sensing, 58(1) :239-258.
20. Song, X.P., Huang, C., Feng, M., Sexton, J.O., Channan, S., Townshend, J.R., 2014. Integrating global land cover products for improved forest cover characterization: an application in North America. International Journal of earth, 9(7): 709-724.
21. Carreiras, J.M.B., Jose. M.C., Pereira. J., Pereira. S., 2006. Estimation of tree canopy cover in evergreen oak woodlands using remote sensing. Forest Ecology and Management, 223(1): 5–53
22. Mather, P.M., 2011. Computer Processing of Remotely-Sensed Images, 4ed. John Wiley & Sons, Ltd: Chichester, UK.
23. Van Niel, T., McVicar, T., Datt, B., 2005. On the relationship between training sample size and data dimensionality: Monte Carlo analysis of broadband multi-temporal classification. Remote Sensing of Environment. 98(1): 468–480.
24. Mountrakis, G., Im, J., Ogole, C., 2011. Support vector machines in remote sensing: A review ISPRS Journal of Photogrammetry and Remote Sensing, 66(1): 247–259.
25. Richards, J.A., 2013. Remote sensing digital image analysis, 4ed, springer.
26. Topaloglur, R.H, Sertele, E., Musaoglune, N., 2016. Assessment of classification of sentinel-2 and landsat-8 data for land cover/use mapping. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLI-B8: 1055-1059.
27. Baatz, M., Schape, A. «Object-oriented and multi-scale image analysis in semantic network»-2nd Int. Ssymposium on Operationalization of Detailed remote sensing, August 1999-Enscheda-Netherlands.
28. Huang, H., Gong, P., Clinton, N., Hui, F., 2008. Reduction of atmospheric and topographic effect on Landsat TM data for forest classification. International Journal of Remote Sensing, 29(19): 5623–5642.
29. Lardeux, C., Frison, P.L., Tison, C., Souyris, J.C., Stoll, B., Fruneau, B., Rudant, J.P., 2009. Support vector machine formulate frequency SAR polar metric data classification. IEEE Transactions on Geoscience and Remote Sensing, 47(12): 4143–4152.