انتخاب بهترین روش طبقه‌بندی در تهیه نقشه کاربری اراضی با استفاده از داده‌های سنجنده OLI ماهواره لندست 8(مطالعه موردی حوضه آبخیز بهشت گمشده، استان فارس)
محورهای موضوعی : جنگلداری
محمد کاظمی
1
(دانشجوی دکترای آبخیزداری، دانشگاه هرمزگان)
احمد نوحه گر
2
(استاد دانشکده محیط زیست دانشگاه تهران)
میرداد میردادی
3
(کارشناسی ارشد سنجش از دور و سیستم های اطلاعات جغرافیایی پردیس دانشگاه هرمزگان)
کلید واژه: کاربری اراضی, ماشین بردار پشتیبان, طبقه‌بندی, سنجنده OLI, دقت,
چکیده مقاله :
لازمه اتخاذ اطلاعات دقیق ار فناوری سنجش از دور، طبقه‌بندی اصولی و دقیق تصاویر ماهواره‌ای می‌باشد. نقشة کاربری اراضی یکی از فاکتور های اساسی در مطالعات منابع طبیعی و مدیریت محیط زیست می‌باشد. اغلب تهیة نقشة کاربری اراضی یک منطقه یکی از پرهزینه‌ترین بخش‌های پروژه‌های زیست محیطی و منابع طبیعی است. در سال های اخیر محققان از روش‌های مختلفی نقشه کاربری اراضی را با استفاده از این داده‌ها تهیة کرده‌اند. روش‌های مختلفی جهت طبقه‌بندی تصاویر ماهواره‌ای وجود دارد. هر یک از روش‌ها دارای معایب و مزایایی می باشند. در تحقیق حاضر هدف انتخاب بهترین روش طبقه‌بندی تصویر OLI ماهواره لندست 8 در تهیه نقشه کاربری اراضی بود. بر این اساس از 8 الگوریتم مختلف طبقه‌بندی نظارت‌شده جهت استخراج نقشه کاربری اراضی منطقه بهشت گمشده استفاده شد. نتایج نشان داد که روش‌های حداکثر احتمال و ماشین بردار پشتیبان با صحت کلی 93/98 و 73/98 و ضریب کاپا به ترتیب 41/98 و 09/98 درصد نسبت به روش‌های دیگر دارای دقت بالاتری هستند. اولویت‌بندی دقت روش‌های 8گانه به ترتیب حداکثر احتمال ، ماشین بردار پشتیبان ، فاصله ماهالانوبی ، واگرایی اطلاعات طیفی ، نقشه‌بردار زاویه طیفی ، حداقل فاصله ، کدهای باینری و سطوح موازی بود. روش حداکثر احتمال بیشترین اطمینان طبقه-بندی با میزان 83/98 درصد را در سطح اعتماد 1 درصد به‌خود اختصاص داد. نتایج تحقیق حاضر نشان-دهنده دقت روش‌های مختلف طبقه‌بندی تصاویر ماهواره‌ای جهت کاهش وقت و هزینه می‌باشد.
All necessary information from the remote sensing technology basics and accurate classification of satellite images. Land use mapping is one of the key factors in studies of environment and natural resources management. Mapping land use is often one of the most expensive parts of natural resources and environmental projects. Satellite data is one of the fastest and most cost-effective methods for mapping land use that is available for researchers. In recent years, researchers from the different methods of classification algorithms land use maps have been produced using this data. This study investigated the ability of 8 common algorithms for land use mapping by Beheshte Gomshodeh in Fars province Using data from the Landsat OLI sensor is 2015. The results showed that the ML and SVM classification by 98.98 and 98.73% overall accuracy factor and 98.41 and 98.09% kappa coefficient is better than other methods, respectively. The accuracy of the order of priority 8 that is, Maximum likelihood, Support Vector Mashine, Mahalanobis distance, Spectral information divergence, Spectral angle mapper, Minimum distance from the mean, binary code and parallel piped. Method of maximum likelihood classification with98.83 was the highest confidence in level of 1 percent confidence interval. All the research results of this study can be using the correct classification. Land use maps can be extracted with higher accuracy.
1. Rahdari ,Vahid; Maleki Najfabdai ,Saeideh; Khajeddin, Seyed Jamaleddin; Rahnama,M (2009) Comparison of Satellite Image Sorting (Supervised and Unmanaged) Methods for Land Use Mapping and Land Covering in Arid and Semi-arid Regions (Case Study: Muteh Wildlife Refuge). National conference of geomatic.tehran iran(in persian).
2. Riahi bakhtiari ,H (2000). Determining the most suitable method for mapping natural resources coverage on a scale of 1/25000 using satellite data in the Arjan plain area. A thesis submitted for master of forestry, natural resources faculty, University of Tehran. (in Persian)
3. Zahedifard,N.(2002)Preparation of land use map using satellite data in Baft watershed. A thesis submitted for master of geology. Faculty of Agriculture. Isfahan University of technology. (in Persian)
4. M , M. Fattahi; A.A.Noroozi ; A.A.Abkar; A.Khalkhali (1997). Comparison of methods for classification and creating landuse map in arid region by using satellite images. Pajouhesh & Sazandegi No: 76 pp: 122-135. (in Persian)
5. Sarooei, S (1999). Investigating the possibility of forest classification in terms of density in Zagros forests using satellite data. Master thesis, University of Tehran. (in Persian)
6. R. Soffianian , E. Mohamadi Towfigh , L. Khodakarami, F. Amiri (2011) .Land use mapping using artificial neural network (Case study: Kaboudarahang, Razan and Khonjin- Talkhab catchment in Hamedan province). Journal of Applied RS & GIS Techniques in Natural Resource Science; Vol.2.Issue1. Spring 2011. (in Persian)
7. Mirzaeizadeh,V; Niknezhad,M; Mahdavi,A ,(2014). Comparison of Maximal Probability and Mahalanobi Distance Classification Methods in Forest Planning (Case Study: Bioreh Region, Ilam Province). Fourth International Conference on Ecological Challenges and Tree Histology, Caspian Ecosystem Research Institute, May, 2014, Sari, Iran.(in Persian)
8. Al-Ahmadi, F. S. and A. S. Hames. 2009. Comparison of four classification methods to extract land use and land cover from raw satellite images for some remote arid areas, Kingdom of Saudi Arabia. JKAU, Earth Science, 20 (1): 167-191.
9. Brian, W. S., C. Qi and B. Michael. 2011.A comparison of classification techniques to support land cover and land use analysis in tropical coastal zones. Applied Geography, 31: 525-532.
10. Elizabeth, A. W., L. William, C. G. Stefanov and H. Diane. 2006. Land use and land cover mapping from diverse data sources for an arid urban environments. Computers, Environment and Urban Systems 30 (3): 320–346.
11. Gualtieri, J. A and R. F. Cromp. 1998. Support vector machines for hyperspectral remote sensing classification. In:Proceedings of the 27th AIPR Workshop: Advances in Computer Assisted Recognition, Washington, DC, 27 October. SPIE, Washington, DC, pp. 221–232.
12. Hopkins, P. F., A. L. Maclean and T. M. Lillesand. 1988. Assessment of thematic mapper imagery for forestry application under lake states conditions, Photogrameteric Engineering and Remote Sensing, 54 (1): 61-68.
13. Huang, C., L. S. Davis and J. R. G. Townshend. 2002. An assessment of support vector machines for land cover classification. International Journal of Remote Sensing, 23 (4): 725–749.
14. Jensen, J. 2005. Introductory digital image processing: A remote sensing perspective (3rd ed.). Upper Saddle River, NJ: Prentice Hall. 526 pp.
15. Kruse, F. A., A. B. Lefkoff, J. B. Boardman, K. B. Heidebrecht, A. T. Shapiro, P. J. Barloon and A. F. H. Goetz.1993. The spectral image processing system (SIPS) - interactive visualization and analysis of imaging spectrometer data.Remote Sensing of the Environment, 44:145 - 163.
16. Lu, D. and Q. Weng. 2007. A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 28 (5): 823-870.
17. Mazer, A. S., M. Martin, M. Lee and J. E. Solomon. 1988. Image processing software for imaging spectrometry analysis, Remote Sensing of the Environment, 24 (1): 201-210.
18. Mountrakis, G., Im., J. and Ogole, C., 2011. Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 13, 247–259.
19. Ommen, T., 2008. An objective analysis of Support Vector Machine based classificat ion for remote sensing. Mathematical Geosciences, 40, 409–424.
20. Pal, M. and P. M. Mather. 2005. Support vector machines for classification in remote sensing. International Journal of Remote Sensing 26 (5): 1007-1011.
21. Perumal, K. and R. Bhaskaran. 2010. Supervised classification performance of multispectral images. Journal of Computing, 2 (2): 124-129.
22. Qiu, F. and J. R. Jensen. 2004. Opening the black box of neural networks for remote sensing image classification. International Journal of Remote Sensing, 25(9): 1749-1768.
23. Rajesh, B. T. and M. Yuji. 2009. Urban mapping, accuracy, & image classification: A comparison of multiple approaches in Tsukuba City, Japan.Applied Geography 29, 135-144.
24. Richards J. A., Jia X., 2006, Remote Sensing Digital Image Analysis an Introduction, 4th Edition, Chapter 1, Springer, Germany, Berlin, Heide lberg.
25. Richards, J. A. 1999. Remote Sensing Digital Image Analysis, Springer-Verlag, Berlin,. 240 pp.
26. Su, L., Huang, Y., Chopping, M.J., Rango, A. and Martonchik, J.V., 2009. An empirical study on the utility of BRDF model parameters and topographic parameters for mapping vegetation in a semi -arid region with MISR imagery. International Journal of Remote Sensing, 30, 3463–3483.
1. Rahdari ,Vahid; Maleki Najfabdai ,Saeideh; Khajeddin, Seyed Jamaleddin; Rahnama,M (2009) Comparison of Satellite Image Sorting (Supervised and Unmanaged) Methods for Land Use Mapping and Land Covering in Arid and Semi-arid Regions (Case Study: Muteh Wildlife Refuge). National conference of geomatic.tehran iran(in persian).
2. Riahi bakhtiari ,H (2000). Determining the most suitable method for mapping natural resources coverage on a scale of 1/25000 using satellite data in the Arjan plain area. A thesis submitted for master of forestry, natural resources faculty, University of Tehran. (in Persian)
3. Zahedifard,N.(2002)Preparation of land use map using satellite data in Baft watershed. A thesis submitted for master of geology. Faculty of Agriculture. Isfahan University of technology. (in Persian)
4. M , M. Fattahi; A.A.Noroozi ; A.A.Abkar; A.Khalkhali (1997). Comparison of methods for classification and creating landuse map in arid region by using satellite images. Pajouhesh & Sazandegi No: 76 pp: 122-135. (in Persian)
5. Sarooei, S (1999). Investigating the possibility of forest classification in terms of density in Zagros forests using satellite data. Master thesis, University of Tehran. (in Persian)
6. R. Soffianian , E. Mohamadi Towfigh , L. Khodakarami, F. Amiri (2011) .Land use mapping using artificial neural network (Case study: Kaboudarahang, Razan and Khonjin- Talkhab catchment in Hamedan province). Journal of Applied RS & GIS Techniques in Natural Resource Science; Vol.2.Issue1. Spring 2011. (in Persian)
7. Mirzaeizadeh,V; Niknezhad,M; Mahdavi,A ,(2014). Comparison of Maximal Probability and Mahalanobi Distance Classification Methods in Forest Planning (Case Study: Bioreh Region, Ilam Province). Fourth International Conference on Ecological Challenges and Tree Histology, Caspian Ecosystem Research Institute, May, 2014, Sari, Iran.(in Persian)
8. Al-Ahmadi, F. S. and A. S. Hames. 2009. Comparison of four classification methods to extract land use and land cover from raw satellite images for some remote arid areas, Kingdom of Saudi Arabia. JKAU, Earth Science, 20 (1): 167-191.
9. Brian, W. S., C. Qi and B. Michael. 2011.A comparison of classification techniques to support land cover and land use analysis in tropical coastal zones. Applied Geography, 31: 525-532.
10. Elizabeth, A. W., L. William, C. G. Stefanov and H. Diane. 2006. Land use and land cover mapping from diverse data sources for an arid urban environments. Computers, Environment and Urban Systems 30 (3): 320–346.
11. Gualtieri, J. A and R. F. Cromp. 1998. Support vector machines for hyperspectral remote sensing classification. In:Proceedings of the 27th AIPR Workshop: Advances in Computer Assisted Recognition, Washington, DC, 27 October. SPIE, Washington, DC, pp. 221–232.
12. Hopkins, P. F., A. L. Maclean and T. M. Lillesand. 1988. Assessment of thematic mapper imagery for forestry application under lake states conditions, Photogrameteric Engineering and Remote Sensing, 54 (1): 61-68.
13. Huang, C., L. S. Davis and J. R. G. Townshend. 2002. An assessment of support vector machines for land cover classification. International Journal of Remote Sensing, 23 (4): 725–749.
14. Jensen, J. 2005. Introductory digital image processing: A remote sensing perspective (3rd ed.). Upper Saddle River, NJ: Prentice Hall. 526 pp.
15. Kruse, F. A., A. B. Lefkoff, J. B. Boardman, K. B. Heidebrecht, A. T. Shapiro, P. J. Barloon and A. F. H. Goetz.1993. The spectral image processing system (SIPS) - interactive visualization and analysis of imaging spectrometer data.Remote Sensing of the Environment, 44:145 - 163.
16. Lu, D. and Q. Weng. 2007. A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 28 (5): 823-870.
17. Mazer, A. S., M. Martin, M. Lee and J. E. Solomon. 1988. Image processing software for imaging spectrometry analysis, Remote Sensing of the Environment, 24 (1): 201-210.
18. Mountrakis, G., Im., J. and Ogole, C., 2011. Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 13, 247–259.
19. Ommen, T., 2008. An objective analysis of Support Vector Machine based classificat ion for remote sensing. Mathematical Geosciences, 40, 409–424.
20. Pal, M. and P. M. Mather. 2005. Support vector machines for classification in remote sensing. International Journal of Remote Sensing 26 (5): 1007-1011.
21. Perumal, K. and R. Bhaskaran. 2010. Supervised classification performance of multispectral images. Journal of Computing, 2 (2): 124-129.
22. Qiu, F. and J. R. Jensen. 2004. Opening the black box of neural networks for remote sensing image classification. International Journal of Remote Sensing, 25(9): 1749-1768.
23. Rajesh, B. T. and M. Yuji. 2009. Urban mapping, accuracy, & image classification: A comparison of multiple approaches in Tsukuba City, Japan.Applied Geography 29, 135-144.
24. Richards J. A., Jia X., 2006, Remote Sensing Digital Image Analysis an Introduction, 4th Edition, Chapter 1, Springer, Germany, Berlin, Heide lberg.
25. Richards, J. A. 1999. Remote Sensing Digital Image Analysis, Springer-Verlag, Berlin,. 240 pp.
26. Su, L., Huang, Y., Chopping, M.J., Rango, A. and Martonchik, J.V., 2009. An empirical study on the utility of BRDF model parameters and topographic parameters for mapping vegetation in a semi -arid region with MISR imagery. International Journal of Remote Sensing, 30, 3463–3483.