BibTex RIS Cite

Determination of Rose Plantation Using by High Resolution Satellite Imagery

Year 2017, Volume: 23 Issue: 1, 22 - 33, 01.01.2017

Abstract

The purpose of this study is to investigate mapping of oil rose Rosa damascena parcels in high-resolution satellite imagery using two different methods. This study was carried out within boundaries of Güneykent Municipality in Isparta in where was produced most of oil rose production in Turkey. Quickbird-2 satellite image was used as base cartographic, and ERDAS and e-Cognition software were used classification of satellite imagery. This purpose; rectify, pan-sharpen and histogram equalization processes were made in the satellite data. The base map including borders of parcel at 1/5000 scale was produced to orient in field work. Then field survey was carried out using these bases. In field survey, Land Use Type LUT was determined for each parcel. The digital LUT map was produced using ArcGIS software. Then satellite image was classified to separate the rose parcels. In classification, the methods of pixel and object-based classification were performed on 4, 3 and 2 band combination of Quickbird-2 satellite data. The most appropriate classification method was selected to apply in study. The manufacturer accuracy, user accuracy and kappa value of oil rose class were found respectively as 48.72%, 18.63% and 0.1539 using maximum likelihood decision rule algorithm of supervised classification method. The boundaries of rose parcels were determined best accuracy by using scale: 100, compactness: 0.5, shape: 0.1 parameters in object-based classification. In the thematic maps, accuracy of rose parcels was found 60.78%. In addition, rose rows were separated by using scale: 25, compactness: 0.5, shape: 0.1 parameters. In the pixel-based classification methods, the rose parcels were mixed with other LUT using high-resolution satellite image. These classification methods were not enough successful for determining of rose parcels. But object-based classification methods were found as applicable to identify rose parcels.

References

  • Anonim (2012). http://www.guneykent.bel.tr/gulkenti/ kasabamiz.php (Erişim tarihi: 16.06.2012)
  • Anonim (2014). https://directory.eoportal.org/web/eoportal/ satellite-missions/q/quickbird-2/ 20.06.2014) (Erişim tarihi
  • Basayigit L, Ersan R & Dedeoglu M (2013). Monitoring vegetation growth of oil rose (Rosa damascena Mill.) by hyperspectral sensing. Bulgarian Journal of Agricultural Science 19(6): 1219-1224
  • Blaschke T (2010). Object based image analysis for remote sensing. International Society for Photogrammetry and Remote Sensing Journal of Photogrammetry and Remote Sensing 65(1): 2-16
  • Bobillet W, Da Costa J P, Germain C, Lavialle O & Grenier G (2003). Row detection in high resolution remote sensing images of vine fields. In: Papers from the 4th European Conference on Precision Agriculture, 15-19 June 2003, Berlin, Germany, pp. 81-87
  • Castilla G & Hay G J (2008). Image objects and geographic objects. In Blaschke Thomas, S Lang & Geoffrey J Hay (Eds.), Object-based image analysis Berlin, Heidelberg, pp. 91–110. http:// www.springerlink. com/content/g403k30318784w36/ (Erişim tarihi: 01.01.2011)
  • Çelik H (2006). İstanbul Sarıyer ilçesine ait uzaktan algılama uydu verileri ile mekansal veri analizleri. Yüksek lisans tezi, Onsekiz Mart Üniversitesi, Fen Bilimleri Enstitüsü (Basılmamış), Çanakkale
  • Delenne C, Rabatel G & Deshayes M (2008). An automatized frequency analysis for vine plot detection and delineation in remote sensing. Institute of Electrical and Electronical Engineers Geoscience and Remote Sensing Letters 5(3): 341-345
  • Dengiz O & Demirağ Turan İ (2014). Uzaktan algılama ve coğrafi bilgi sistem teknikleri kullanılarak arazi örtüsü/ arazi kullanımı zamansal değişimin belirlenmesi: Samsun Merkez İlçesi örneği (1984-2011). Türkiye Tarımsal Araştırmalar Dergisi 1: 78-90
  • Devi Y A S & Krishna M (2012). Pixel-based and object-oriented classification of high resolution satellite images. Canadian Journal on Electrical and Electronics Engineering 3(1): 31-34
  • Duro D J, Franklin S E & Dube 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
  • Ersan R (2013). Gül tarım alanlarının yüksek çözünürlüklü uydu verileri ile belirlenebilirliği. Yüksek lisans tezi, Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü (Basılmamış), Isparta
  • GTB (2011). Gülçiçeği Raporu. T.C Sanayi ve Ticaret Bakanlığı Teşkilatlandırma Genel Müdürlüğü, Mart, 2011, Ankara
  • Lu D & Weng Q (2007). A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing 28(5): 823-870
  • Mallinis G, Koutsias N, Tsakiri-Strati M & Karteris M (2008). Object-based classification using quickbird imagery for delineating forest vegetation polygons in a mediterranean test site. ISPRS Journal of Photogrammetry & Remote Sensing 63: 237-250
  • Moran E F (2010). Land cover classification in a complex urban-rural landscape with quickbird imagery. Photogrammetric Engineering and Remote Sensing 76(10): 1159-1168
  • 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
  • Nelson D M (2005). Remote sensing classification of brownfields in the phoenix metropolitan area. 5th International Symposium Remote Sensing of Urban Areas (URS 2005), 14-16 March, Tempe, AZ, USA Volume 36, part8/W27
  • Smith A (2010). Image segmentation scale parameter optimization and land cover classification using the random forest algorithm. Journal of Spatial Science 55(1): 69-79
  • Veljanovski T, Kanjir U & Ostir K (2011). Object-based image analyses of remote sensing data. Geodetski Vestnik 55(4): 665-688
  • Wassenaar T, Robbez-Masson J M, Andrieux P & Baret F (2000). Vineyard spatial structure analysis by per- field aerial photograph processing. International Archives of Photogrammetry and Remote Sensing 33(Part B7): 1692-1699
  • Wassenaar T, Robbez-Masson J M, Andrieux P & Baret F (2002). Vineyard identification and description of spatial crop structure by per-field frequency analysis. International Journal of Remote Sensing 23(17): 3311-3325
  • Whiteside T G, Boggs G S & Maier S W (2011). Comparing object-based and pixelbased classifications for mapping savannas. International Journal of Applied Earth Observation and Geoinformation 13(6): 884- 893
  • Yan G, Mas J F, Maathuis B H P, Xiangmin Z & Van Dijk P M (2006). Comparison of pixel-based and object- oriented image classification approaches-A case study in a coal fire area, Wuda, Inner Mongolia, China. International Journal of Remote Sensing 27: 4039- 4055
  • Yu Q, Gong P, Clinton N, Biging G, Kelly M & Schirokauer D (2006). Object-based detailed vegetation classification with airborne high spatial resolution remote sensing imagery. Photogrammetric Engineering and Remote Sensing 72: 799-811

Yüksek Çözünürlüklü Uydu Görüntülerinde Farklı Görüntü İşleme Yöntemleri ile Yağ Gülü Parsellerinin Belirlenmesi

Year 2017, Volume: 23 Issue: 1, 22 - 33, 01.01.2017

Abstract

Bu çalışmada amaç, yüksek çözünürlüklü uydu verisinde iki farklı yöntem kullanılarak yağ gülü Rosa damascena dikili alanların parsel bazında belirlenebilirliğini araştırmaktır. Çalışma, Türkiye’de yağ gülü üretiminin yoğun olarak yapıldığı Isparta ili Güneykent Belediyesi sınırları içerisinde yürütülmüştür. Çalışmada temel kartografik olarak Quickbird-2 uydu verisi, uydu verilerinin sınıflandırmasında ERDAS ve e-Cognition yazılımları kullanılmıştır. Bu amaçla öncelikle uydu verisinde geometrik düzeltme rectify , görüntü keskinleştirme pan-sharp ve görüntü zenginleştirme histogram equalization işlemleri yapılmış, arazide kullanılmak üzere parsellerin yer aldığı 1/5000 ölçekli altlık veriler oluşturulmuştur. Bu veriler araziye oryantasyon amacıyla kullanılmış ve arazi çalışmaları yürütülmüştür. Arazi çalışmalarında parsel bazında Arazi Kullanım Türleri AKT belirlenmiş, ArcGIS yazılımı ile sayısal AKT haritası hazırlanmıştır. Daha sonra Quickbird-2 uydu verisinin 4, 3 ve 2 bant kombinasyonunda piksel ve obje tabanlı sınıflama metotları kullanılarak gül parselleri belirlenmiş ve en uygun sınıflandırma metodu seçilmiştir. Kontrollü sınıflandırma yöntemi maksimum olabilirlik karar kuralı algoritması ile yapılan sınıflandırmada oluşturulan tematik haritada gül parsellerinin üretici doğruluğu % 48.72, kullanıcı doğruluğu % 18.63, kappa değeri 0.1539 olarak bulunmuştur. Obje tabanlı sınıflandırmada ölçek: 100, bütünlük: 0.5, biçim: 0.1 parametreleri kullanılarak gül parsel sınırlarının en iyi belirlendiği, bu yöntem ile oluşturulan tematik haritada gül parsellerinin % 60.78 doğrulukta ayırt edilebildiği belirlenmiştir. Ayrıca obje tabanlı sınıflandırmada ölçek: 25, bütünlük: 0.5, biçim: 0.1 parametreleri kullanılarak yapılan sınıflamada gül sıralarının ayırt edilebildiği görülmüştür. Yüksek çözünürlüklü uydu verileri kullanılarak yapılan piksel tabanlı sınıflandırmada gül parsellerinin diğer parsellerle karıştığı, bu sınıflama yöntemlerinin gül parsellerinin belirlenmesinde iyi sonuç vermediği, bunun yerine gül parsellerinin daha iyi ayırt edilebildiği obje tabanlı sınıflandırmanın kullanılabileceği tespit edilmiştir

References

  • Anonim (2012). http://www.guneykent.bel.tr/gulkenti/ kasabamiz.php (Erişim tarihi: 16.06.2012)
  • Anonim (2014). https://directory.eoportal.org/web/eoportal/ satellite-missions/q/quickbird-2/ 20.06.2014) (Erişim tarihi
  • Basayigit L, Ersan R & Dedeoglu M (2013). Monitoring vegetation growth of oil rose (Rosa damascena Mill.) by hyperspectral sensing. Bulgarian Journal of Agricultural Science 19(6): 1219-1224
  • Blaschke T (2010). Object based image analysis for remote sensing. International Society for Photogrammetry and Remote Sensing Journal of Photogrammetry and Remote Sensing 65(1): 2-16
  • Bobillet W, Da Costa J P, Germain C, Lavialle O & Grenier G (2003). Row detection in high resolution remote sensing images of vine fields. In: Papers from the 4th European Conference on Precision Agriculture, 15-19 June 2003, Berlin, Germany, pp. 81-87
  • Castilla G & Hay G J (2008). Image objects and geographic objects. In Blaschke Thomas, S Lang & Geoffrey J Hay (Eds.), Object-based image analysis Berlin, Heidelberg, pp. 91–110. http:// www.springerlink. com/content/g403k30318784w36/ (Erişim tarihi: 01.01.2011)
  • Çelik H (2006). İstanbul Sarıyer ilçesine ait uzaktan algılama uydu verileri ile mekansal veri analizleri. Yüksek lisans tezi, Onsekiz Mart Üniversitesi, Fen Bilimleri Enstitüsü (Basılmamış), Çanakkale
  • Delenne C, Rabatel G & Deshayes M (2008). An automatized frequency analysis for vine plot detection and delineation in remote sensing. Institute of Electrical and Electronical Engineers Geoscience and Remote Sensing Letters 5(3): 341-345
  • Dengiz O & Demirağ Turan İ (2014). Uzaktan algılama ve coğrafi bilgi sistem teknikleri kullanılarak arazi örtüsü/ arazi kullanımı zamansal değişimin belirlenmesi: Samsun Merkez İlçesi örneği (1984-2011). Türkiye Tarımsal Araştırmalar Dergisi 1: 78-90
  • Devi Y A S & Krishna M (2012). Pixel-based and object-oriented classification of high resolution satellite images. Canadian Journal on Electrical and Electronics Engineering 3(1): 31-34
  • Duro D J, Franklin S E & Dube 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
  • Ersan R (2013). Gül tarım alanlarının yüksek çözünürlüklü uydu verileri ile belirlenebilirliği. Yüksek lisans tezi, Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü (Basılmamış), Isparta
  • GTB (2011). Gülçiçeği Raporu. T.C Sanayi ve Ticaret Bakanlığı Teşkilatlandırma Genel Müdürlüğü, Mart, 2011, Ankara
  • Lu D & Weng Q (2007). A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing 28(5): 823-870
  • Mallinis G, Koutsias N, Tsakiri-Strati M & Karteris M (2008). Object-based classification using quickbird imagery for delineating forest vegetation polygons in a mediterranean test site. ISPRS Journal of Photogrammetry & Remote Sensing 63: 237-250
  • Moran E F (2010). Land cover classification in a complex urban-rural landscape with quickbird imagery. Photogrammetric Engineering and Remote Sensing 76(10): 1159-1168
  • 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
  • Nelson D M (2005). Remote sensing classification of brownfields in the phoenix metropolitan area. 5th International Symposium Remote Sensing of Urban Areas (URS 2005), 14-16 March, Tempe, AZ, USA Volume 36, part8/W27
  • Smith A (2010). Image segmentation scale parameter optimization and land cover classification using the random forest algorithm. Journal of Spatial Science 55(1): 69-79
  • Veljanovski T, Kanjir U & Ostir K (2011). Object-based image analyses of remote sensing data. Geodetski Vestnik 55(4): 665-688
  • Wassenaar T, Robbez-Masson J M, Andrieux P & Baret F (2000). Vineyard spatial structure analysis by per- field aerial photograph processing. International Archives of Photogrammetry and Remote Sensing 33(Part B7): 1692-1699
  • Wassenaar T, Robbez-Masson J M, Andrieux P & Baret F (2002). Vineyard identification and description of spatial crop structure by per-field frequency analysis. International Journal of Remote Sensing 23(17): 3311-3325
  • Whiteside T G, Boggs G S & Maier S W (2011). Comparing object-based and pixelbased classifications for mapping savannas. International Journal of Applied Earth Observation and Geoinformation 13(6): 884- 893
  • Yan G, Mas J F, Maathuis B H P, Xiangmin Z & Van Dijk P M (2006). Comparison of pixel-based and object- oriented image classification approaches-A case study in a coal fire area, Wuda, Inner Mongolia, China. International Journal of Remote Sensing 27: 4039- 4055
  • Yu Q, Gong P, Clinton N, Biging G, Kelly M & Schirokauer D (2006). Object-based detailed vegetation classification with airborne high spatial resolution remote sensing imagery. Photogrammetric Engineering and Remote Sensing 72: 799-811
There are 25 citations in total.

Details

Primary Language Turkish
Journal Section Research Article
Authors

Rabia Ersan This is me

Levent Başayiğit This is me

Publication Date January 1, 2017
Published in Issue Year 2017 Volume: 23 Issue: 1

Cite

APA Ersan, R., & Başayiğit, L. (2017). Yüksek Çözünürlüklü Uydu Görüntülerinde Farklı Görüntü İşleme Yöntemleri ile Yağ Gülü Parsellerinin Belirlenmesi. Journal of Agricultural Sciences, 23(1), 22-33.

Journal of Agricultural Sciences is published open access journal. All articles are published under the terms of the Creative Commons Attribution License (CC BY).