Identification of Corn and Cotton Fields Using Multi-temporal Spot6 NDVI Data

Celik Y. B., Sertel E., Üstündağ B. B.

Fourth International Conference on Agro Geoinformatics, İstanbul, Turkey, 20 - 24 July 2015 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/agro-geoinformatics.2015.7248136
  • City: İstanbul
  • Country: Turkey
  • Keywords: object based classification, crop mapping, multi-temporal analysis, high resolution satellite images, NDVI, CROP DISCRIMINATION, PARCEL-LEVEL, CLASSIFICATION
  • Istanbul Technical University Affiliated: Yes

Abstract

In this research, parcel based identification of cotton and corn fields was conducted using single dated and multi-temporal SPOT6 NDVI images in three selected districts (Harran, Ceylanpinar and Viransehir) within Sanliurfa, Turkey. Four different applications were conducted in order to find out the most accurate method for the identification of spatial distribution and crop type of agricultural parcels. NDVI images for three different data acquisition dates for SPOT6 were produced, and then object-based classification approach was applied to multi-temporal NDVI image to accurately identify corn, and cotton fields in parcel level for the first application. For the next three applications, three different single date SPOT 6 images, which were acquired in June, July and September, were classified by using object based classification approach for identification of same crop types. Accuracy assessments for all four applications were conducted using confusion matrix and kappa statistics to analyze the accuracy of the proposed approaches.