Sentinel 2 MSI Uydu Görüntülerini Kullanarak Spektral İndeks Çıkarımına Dayalı Peyzaj Düzeyinde Nesne Tabanlı Görüntü Sınıflandırma Süreci

Yıl 2025, Cilt: 21 Sayı: 2, 66 - 81, 30.12.2025

Esin Karamanlı , Ömer Faruk Uzun

https://doi.org/10.58816/duzceod.1675848

Öz

Arazi Örtüsü-Arazi Kullanımı (AÖ-AK) sınıflandırması, peyzaj ölçeğinde çevresel ve ekolojik kararların etkin şekilde yönetilmesi için veriler sunar. Bu süreçte, Sentinel-2 Multispektral Görüntüleyici (MSI) uydu görüntüleri, yüksek spektral çözünürlükleriyle bilgi çıkarımını kolaylaştırarak sınıflandırma yöntemlerine katkı sağlar. İndeks tabanlı yöntemler çoğunlukla tek sınıf ayrımına odaklanırken, peyzajlarda çoklu sınıfların ayrıştırılması gerekmektedir. Bu çalışmada, Sentinel-2 MSI görüntülerinden türetilen çeşitli spektral indekslerin nesne tabanlı görüntü sınıflandırma tekniği ile geniş alanlarda nasıl kullanılabileceği ortaya konulmuştur. Örneklem alanı olarak Mersin ili Silifke ilçesi seçilmiştir. Normalize Edilmiş Fark Vejetasyon İndeksi (NDVI), Normalize Edilmiş Fark Su İndeksi (NDWI), Yapı Alanı Çıkarım İndeksi (BAEI), Yapı Alan İndeksi (BAI), Bant Oranı (BR28, BR38), Normalize Edilmiş Yapı Alan İndeksi (NBAI), Yeni Yapı İndeksi (NBI), Kent İndeksi (UI), Normalize Edilmiş Fark Toprak İşleme İndeksi (NDTI), Kırmızı Kenar Bazlı Normalize Edilmiş Fark Vejetasyon İndeksi (NDVIre) ve Dönüştürülmüş Normalize Fark Su İndeksi (MNDWI) kullanılmıştır. BR28, BR38, NBAI, NBI ve UI ile anlamlı sonuçlar elde edilemezken, diğer indekslerle 0.8815 kappa katsayısı ve %94.11 genel doğruluk oranı sağlanmıştır.

Anahtar Kelimeler

Nesne-tabanlı görüntü analizi , Spektral indisler , Sınıflandırma , En yakın komşu algoritması , Makine öğrenmesi

Object-Based Image Classification Process at Landscape Level Based on Spectral Index Extraction Using Sentinel 2 MSI Satellite Imagery

Öz

Land Cover-Land Use (LC/LU) classification provides data for effective management of environmental and ecological decisions at the landscape scale. In this process, Sentinel-2 Multi Spectral Imager (MSI) satellite images contribute to classification methods by facilitating information extraction with their high spectral resolution. While index-based methods mostly focus on the separation of single classes, landscapes require the separation of multiple classes. This study shows how different spectral indexes derived from Sentinel-2 MSI imagery can be used in large areas with the object-based image classification technique. The Silifke district of Mersin province was selected as a sample area. Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), Built-up Area Extraction Index (BAEI), Built-up Area Index (BAI), Band Ratio (BR28, BR38), Normalized Built-up Area Index (NBAI), New Building Index (NBI), Urban Index (UI), Normalized Difference Soil Tillage Index (NDTI), Red Edge Based Normalized Difference Vegetation Index (NDVIre) and Normalized Difference Water Index (MNDWI) were used. While no significant results were obtained with BR28, BR38, NBAI, NBI and UI, 0.8815 kappa coefficient of 0.8815 and overall accuracy rate of %94.11 were obtained with other indexes.

Anahtar Kelimeler

Object-based image analysis , Spectral indexes , Classification , Nearest neighbour algorithm , Machine learning

Kaynakça

• Ali, U., Esau, T. J., Farooque, A. A., Zaman, Q. U., Abbas, F., & Bilodeau, M. F. (2022). Limiting the collection of ground truth data for land use and land cover maps with machine learning algorithms. ISPRS International Journal of Geo-Information, 11(6), 333. https://doi.org/10.3390/ijgi11060333
• Bayburt, S. (2009). Uydu görüntülerinin piksel ve nesne tabanlı sınıflandırma sonuçlarının karşılaştırılması (Doğu Trakya bölgesi örneği) (Thesis no. 251917) [Master’s thesis, İstanbul Technical University]. Council of Higher Education Thesis Center.
• Bhaskaran, S., Paramananda, S., & Ramnarayan, M. (2010). Per-pixel and object-oriented classification methods for mapping urban features using Ikonos satellite data. Applied Geography, 30, 650–665. https://doi.org/10.1016/j.apgeog.2010.01.009
• Bhatt, A., Ghosh, S. K., & Kumar, A. (2018). Spectral indices based object oriented classification for change detection using satellite data. International Journal of System Assurance Engineering and Management, 9, 33–42. https://doi.org/10.1007/s13198-016-0458-7
• Blaschke, T. (2010). Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 65(1), 2–16. https://doi.org/10.1016/j.isprsjprs.2009.06.004
• Congalton, R. G. (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 37(1), 35–46. https://doi.org/10.1016/0034-4257(91)90048-B
• Copernicus Browser (CB). (2024, March 1). Data sources: SENTINEL-2. https://browser.dataspace.copernicus.eu/
• Da Silva, V. S., Salami, G., Da Silva, M. I. O., Silva, E. A., Junior, J. J. M., & Alba, E. (2020). Methodological evaluation of vegetation indexes in land use and land cover (LULC) classification. Geology, Ecology, and Landscapes, 4(2), 159–169. https://doi.org/qg99
• Du, Y., Zhang, Y., Ling, F., Wang, Q., Li, W., & Li, X. (2016). Water bodies’ mapping from Sentinel-2 imagery with modified normalized difference water index at 10-m spatial resolution produced by sharpening the SWIR band. Remote Sensing, 8(4), 354. https://doi.org/10.3390/rs8040354
• Duro, D. C., Franklin, S. E., & Dubé, M. G. (2012). A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery. Remote Sensing of Environment, 118, 259–272. https://doi.org/10.1016/j.rse.2011.11.020
• Esetlili, M. T., Balcık, F. B., Şanlı, F. B., Üstüner, M., Kalkan, K., Göksel, Ç., Gazioğlu, C., & Kurucu, Y. (2018). Comparison of object and pixel-based classifications for mapping crops using RapidEye imagery: A case study of Menemen Plain, Turkey. International Journal of Environment and Geoinformatics (IJEGEO), 5(2), 231–243. https://doi.org/10.30897/ijegeo.442002
• Flanders, D., Hall-Beyer, M., & Pereverzoff, J. (2003). Preliminary evaluation of eCognition object-based software for cut block delineation and feature extraction. Canadian Journal of Remote Sensing, 29(4), 441–452. https://doi.org/10.5589/m03-006
• Gaitan, C. F., Hsieh, W. W., Cannon, A. J., & Gachon, P. (2014). Evaluation of linear and non-linear downscaling methods in terms of daily variability and climate indices: surface temperature in Southern Ontario and Quebec, Canada. Atmosphere-Ocean, 52(3), 211–221. https://doi.org/10.1080/07055900.2013.857639
• Ghorbanpour, A. K., Hessels, T., Moghim, S., & Afshar, A. (2021). Comparison and assessment of spatial downscaling methods for enhancing the accuracy of satellite-based precipitation over Lake Urmia Basin. Journal of Hydrology, 596, 126055. https://doi.org/10.1016/j.jhydrol.2021.126055
• Grimm, R., Behrens, T., Märker, M., & Elsenbeer, H. (2008). Soil organic carbon concentrations and stocks on Barro Colorado Island - Digital soil mapping using Random Forests analysis. Geoderma, 146(1–2), 102–113. https://doi.org/10.1016/j.geoderma.2008.05.008
• Harrak, Y., Rachid, A., & Aguejdad, R. (2025). Evaluation of spectral indices and global thresholding methods for the automatic extraction of built-up areas: An application to a semi-arid climate using Landsat 8 imagery. Urban Science, 9(3), 78. https://doi.org/10.3390/urbansci9030078
• Hong, S.-H., Hendrickx, J. M. H., & Borchers, B. (2011). Down-scaling of SEBAL derived evapotranspiration maps from MODIS (250 m) to Landsat (30 m) scales. International Journal of Remote Sensing, 32(21), 645–6477. https://doi.org/10.1080/01431161.2010.512929
• Jawak, S. D., Devliyal, P., & Luis, A. J. (2015). A comprehensive review on pixel oriented and object oriented methods for information extraction from remotely sensed satellite images with a special emphasis on cryospheric applications. Advances in Remote Sensing, 4(3), 177–195. http://doi.org/10.4236/ars.2015.43015
• Jieli, C., Manchun, L., Yongxue, L., Chenglei, S., & Wei, H. (2010). Extract residential areas automatically by new built-up index. In 2010 18th International Conference on Geoinformatics (Vol. 3, pp. 171–175). IEEE. http://doi.org/10.1109/GEOINFORMATICS.2010.5567823
• Kalkan, K., & Maktav, D. (2010). Comparison of object-based and pixel-based classification methods [Symposium paper]. In T. Kavzaoğlu & D. Maktav (Eds.), III. Remote Sensing and Geographic Information Systems Symposium (pp. 153–160). Gebze-Kocaeli.
• Karakus, P., Karabork, H., & Kaya, S. (2017). A comparison of the classification accuracies in determining the land cover of Kadirli Region of Turkey by using the pixel based and object based classification algorithms. International Journal of Engineering and Geosciences (IJEG), 2(2), 52–60. http://doi.org/10.26833/ijeg.298951
• Kaufman, Y. J. (1987). Atmospheric effect on spectral signature – measurements. Advances in Space Research, 7(11), 203–206. https://doi.org/10.1016/0273-1177(87)90313-9
• Kawamura, M., Jayamanna, S., & Tsujiko, Y. (1996). Relation between social and environmental conditions in Colombo Sri Lanka and the urban index estimated by satellite remote sensing data. International Archives of Photogrammetry and Remote Sensing, 31, 321–326.
• Kebede, T. A., Hailu, B. T., & Suryabhagavan, K. V. (2022). Evaluation of spectral built-up indices for impervious surface extraction using Sentinel-2A MSI imageries: A case of Addis Ababa city, Ethiopia. Environmental Challenges, 8, 100568. https://doi.org/10.1016/j.envc.2022.100568
• Lamichhane, S., Kumar, L., & Wilson, B. (2019). Digital soil mapping algorithms and covariates for soil organic carbon mapping and their implications: A review. Geoderma, 352, 395–413. https://doi.org/10.1016/j.geoderma.2019.05.031
• Lemenkova, P., & Debeir, O. (2023). Computing vegetation indices from the satellite images using GRASS GIS scripts for monitoring mangrove forests in the coastal landscapes of Niger Delta, Nigeria. Journal of Marine Science and Engineering, 11(4), 871. https://doi.org/10.3390/jmse11040871
• Li, C., Shao, Z., Zhang, L., Huang, X., & Zhang, M. (2021). A comparative analysis of index-based methods for impervious surface mapping using multiseasonal Sentinel-2 satellite data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 3682–3694. https://doi.org/10.1109/jstars.2021.3067325
• Magpantay, A. T., Adao, R. T., Bombasi, J. L., Lagman, A. C., Malasaga, E. V., & Ye, C.-S. (2019). Analysis on the effect of spectral index images on improvement of classification accuracy of Landsat-8 OLI image. Korean Journal of Remote Sensing, 35(4), 561–571. https://doi.org/10.7780/kjrs.2019.35.4.6
• McFeeters, S. K. (1996). The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17(7), 1425–1432. https://doi.org/10.1080/01431169608948714
• Myint, S. W., Gober, P., Brazel, A., Grossman-Clarke, S., & Weng, Q. (2011). Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery. Remote Sensing of Environment, 115(5), 1145–1161. https://doi.org/10.1016/j.rse.2010.12.017
• Nandam, V., & Patel, P. L. (2021). A novel hybrid approach using SVM and spectral indices for enhanced land use land cover mapping of coastal urban plains. Geocarto International, 37(16), 4714–4736. https://doi.org/10.1080/10106049.2021.1899300
• NASA (2025, February 26). Earth data Sentinel-2 MSI. https://tinyurl.com/4dacb7ar
• Newman, M. E., McLaren, K. P., & Wilson, B. S. (2011). Comparing the effects of classification techniques on landscape-level assessments: pixel-based versus object-based classification. International Journal of Remote Sensing, 32(14), 4055–4073. https://doi.org/10.1080/01431161.2010.484432
• Nichols, T. R., Wisner, P. M., Cripe, G., & Gulabchand, L. (2010). Putting the kappa statistic to use. The Quality Assurance Journal, 3(3–4), 41–77. https://doi.org/10.1002/qaj.481
• Nussbaum, S., & Menz, G. (2008). eCognition image analysis software. In T. Blaschke, S. Lang, & G. J. Hay (Eds.), Object-based image analysis and treaty verification (pp. 129–143). Springer. https://doi.org/10.1007/978-1-4020-6961-1_3
• Nwagoum, C. S. K., Yemefack, M., Tedou, F. B. S., & Oben, F. T. (2023). Sentinel-2 and Landsat-8 potentials for high-resolution mapping of the shifting agricultural landscape mosaic systems of southern Cameroon. International Journal of Applied Earth Observation and Geoinformation, 124, 103545. https://doi.org/10.1016/j.jag.2023.103545
• Orman Genel Müdürlüğü (OGM). (2021). E-Harita Uygulaması- Meşçere. https://cbs.ogm.gov.tr/vatandas/. Accessed February 16, 2021.
• Osgouei, P. E., Kaya, S., Sertel, E., & Alganci, U. (2019). Separating Built-Up Areas from Bare Land in Mediterranean Cities Using Sentinel-2A Imagery. Remote Sensing, 11, 345. https://doi.org/10.3390/rs11030345
• Ouchra, H., Belangour, A., & Erraissi, A. (2022). A comparative study on pixel-based classification and object-oriented classification of satellite image. International Journal of Engineering Trends and Technology, 70(8), 206–215. https://doi.org/10.14445/22315381/ijett-v70i8p221
• Özgür, D. (2023, March 3). Coğrafi bilgi sistemleri verileri, Türkiye sayısallaştırılmış yükselti modeli (dijital yükseklik modeli (DEM)). https://www.ozgurcografya.com/
• Öztürk, D. (2022). Sentinel-2A MSI ve Landsat-9 OLI-2 görüntüleri kullanılarak farklı geçirimsiz yüzey indekslerinin karşılaştırmalı değerlendirmesi: Samsun örneği. Ege Coğrafya Dergisi, 31(2), 401–423. https://doi.org/10.51800/ecd.1175827
• Pandey, D., & Tiwari, K. C. (2020). Extraction of urban built-up surfaces and its subclasses using existing built-up indices with separability analysis of spectrally mixed classes in AVIRIS-NG imagery. Advances in Space Research, 66(8), 1829–1845. https://doi.org/10.1016/j.asr.2020.06.038
• Rahar, P. S., & Pal, M. (2020). Comparison of various indices to differentiate built-up and bare soil with Sentinel 2 Data. In J. K. Ghosh & I. da Silva (Eds.), Applications of Geomatics in Civil Engineering (pp. 501–509). Springer, Singapore. https://doi.org/10.1007/978-981-13-7067-0_39
• Rastner, P., Bolch, T., Notarnicola, C., & Paul, F. (2014). A comparison of pixel- and object-based glacier classification with optical satellite images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(3), 853–862. https://doi.org/10.1109/jstars.2013.2274668
• Reddy, B. B. K., Maragatham, S., Santhi, R., Balachandar, D., Vijayalakshmi, D., Vasu, D., & Gopalakrishnan, M. (2024). Predictive soil mapping using random forest models: Applications in pH and soil organic matter assessment. Plant Science Today, 11(4), 1–12. https://doi.org/10.14719/pst.3865
• Rouibah, K. (2023). The use of bands ratio derived from Sentinel 2 imagery to detect built up area in the dry period (North East Algeria). Applied Geomatics, 15, 473–482. https://doi.org/10.1007/s12518-023-00513-y
• Rouse, J. W., Haas, R. H., Schell, J. A., & Deering, D. W. (1973). Monitoring vegetation systems in the great plains with ERTS [Symposium paper]. In S. C. Freden & E. P. Mercanti (Eds.), Proceedings of the Third Earth Resources Technology Satellite-1 Symposium (pp. 309–317). Washington, DC.
• Sentiwiki. (2025, March 26). Sentinel-2 Products MSI Products Overview. https://sentiwiki.copernicus.eu/web/s2-products
• Story, M., & Congalton, R. G. (1986). Accuracy assessment: a user’s perspective. Photogrammetric Engineering and Remote Sensing, 52(3), 397–399.
• Suharyadi, R., Umarhadi, D. A., Awanda, D., & Widyatmanti, W. (2022). Exploring built-up indices and machine learning regressions for multi-temporal building density monitoring based on Landsat series. Sensors, 22, 4716. https://doi.org/10.3390/s22134716
• Tehrany, M. S., Pradhan, B., & Jebuv, M. N. (2014). A comparative assessment between object and pixel-based classification approaches for land use/land cover mapping using SPOT 5 imagery. Geocarto International, 29(4), 351–369. https://doi.org/10.1080/10106049.2013.768300
• Tonbul, H., & Kavzoğlu, T. (2018). Nesne Tabanlı Görüntü Analizinde Görüntü Bölütleme Yaklaşımları ve Bölütleme Kalitesinin Analizi. Harita Dergisi, 160, 12–23. https://doi.org/10.15659/uzalcbs2018.6403
• Torres-Sanchez, J., Lopez-Granados, F., & Pena, J. M. (2015). An automatic object-based method for optimal thresholding in UAV images: Application for vegetation detection in herbaceous crops. Computers and Electronics in Agriculture, 114, 43–52. https://doi.org/f7jhbp
• Trimble. (2025, March 26). eCognition suite documentation. https://docs.ecognition.com
• TÜİK (2023, April 12). İl ve ilçe merkezlerine göre nüfus ve yüzölçümü verileri. https://bit.ly/4pw7Dh2
• Weichert, A., & Bürger, G. (1998). Linear versus nonlinear techniques in downscaling. Climate Research, 10, 83–93. https://doi.org/10.3354/cr010083
• Whiteside, T. G., Boggs, G. S., & Maier, S. W. (2011). Comparing object-based and pixel-based classifications for mapping savannas. International Journal of Applied Earth Observation and Geoinformation, 13(6), 884–893. https://doi.org/10.1016/j.jag.2011.06.008
• Woolson, R. F., Bean, J. A., & Rojas, P. B. (1986). Sample size for case-control studies using Cochran's statistic. Biometrics, 42(4), 927–932. https://doi.org/10.2307/2530706
• Wu, B., Zheng, H., Xu, Z., Wu, Z., & Zhao, Y. (2022). Forest burned area detection using a novel spectral index based on multi-objective optimization. Forests, 13(11), 1787–1807. https://doi.org/10.3390/f13111787
• Xi, Y., Thinh, N. X., & Li, C. (2019). Preliminary comparative assessment of various spectral indices for built-up land derived from Landsat-8 OLI and Sentinel-2A MSI imageries. European Journal of Remote Sensing, 52(1), 240–252. https://doi.org/10.1080/22797254.2019.1584737
• Zha, Y., Gao, J., & Ni, S. (2003). Use of normalized difference built-up index in automatically mapping urban areas from TM imagery. International Journal of Remote Sensing, 24(3), 583–594. https://doi.org/10.1080/01431160304987
• Zhang, K., Chen, Y., Wang, W., Wu, Y., Wang, B., & Yan, Y. (2023). A method for remote sensing image classification by combining Pixel Neighbourhood Similarity and optimal feature combination. Geocarto International, 38, 2158948. https://doi.org/10.1080/10106049.2022.2158948
• Zhang, T.-X., Su, J.-Y., Liu, C.-J., & Chen, W.-H. (2019). Potential Bands of Sentinel-2A Satellite for Classification Problems in Precision Agriculture. International Journal of Automation and Computing, 16(1), 16–26. https://doi.org/10.1007/s11633-018-1143-x