Share Email Print

Journal of Applied Remote Sensing

Vineyard parcel identification from Worldview-2 images using object-based classification model
Author(s): Elif Sertel; Irmak Yay
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper 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.

Paper Details

Date Published: 3 November 2014
PDF: 17 pages
J. Appl. Rem. Sens. 8(1) 083535 doi: 10.1117/1.JRS.8.083535
Published in: Journal of Applied Remote Sensing Volume 8, Issue 1
Show Author Affiliations
Elif Sertel, Istanbul Technical Univ. (Turkey)
Irmak Yay, Istanbul Technical Univ. (Turkey)

© SPIE. Terms of Use
Back to Top