Research Papers

Vineyard parcel identification from Worldview-2 images using object-based classification model

[+] Author Affiliations
Elif Sertel

Istanbul Technical University, Center for Satellite Communication and Remote Sensing, Maslak 34469, Turkey

Istanbul Technical University, Geomatics Engineering Department, Maslak 34469, Turkey

Irmak Yay

Istanbul Technical University, Center for Satellite Communication and Remote Sensing, Maslak 34469, Turkey

J. Appl. Remote Sens. 8(1), 083535 (Nov 03, 2014). doi:10.1117/1.JRS.8.083535
History: Received June 12, 2014; Revised September 16, 2014; Accepted September 17, 2014
Text Size: A A A

Abstract.  Accurate identification of spatial distribution and characteristics of vineyard parcels is an important task for the effective management of vineyard areas, precision viticulture, and farmer registries. This study aimed to develop rule sets to be used in object-based classification of Worldview-2 satellite images to accurately delineate the boundaries of vineyards having different plantation styles. Multilevel segmentation was applied to Worldview-2 images to create different sizes of image objects representing different land cover categories with respect to scale parameter. Texture analysis and several new spectral indices were applied to objects at different segmentation levels to accurately classify land cover classes of forest, cultivated areas, harvested areas, impervious, bareland, and vineyards. A specific attention was given to vineyard class to identify vine areas at the parcel level considering their different plantation styles. The results illustrated that the combined usage of a newly developed decision tree and image segmentation during the object-based classification process could provide highly accurate results for the identification of vineyard parcels. Linearly planted vineyards could be classified with 100% producer’s accuracy due to their regular textural characteristics, whereas regular gridwise and irregular gridwise (distributed) vineyard parcels could be classified with 94.87% producer’s accuracy in this research.

Figures in this Article
© 2014 Society of Photo-Optical Instrumentation Engineers

Citation

Elif Sertel and Irmak Yay
"Vineyard parcel identification from Worldview-2 images using object-based classification model", J. Appl. Remote Sens. 8(1), 083535 (Nov 03, 2014). ; http://dx.doi.org/10.1117/1.JRS.8.083535


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.