Share Email Print

Proceedings Paper

Tests with VHR images for the identification of olive trees and other fruit trees in the European Union
Author(s): Josiane Masson; Pierre Soille; Rick Mueller
Format Member Price Non-Member Price
PDF $17.00 $21.00
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

In the context of the Common Agricultural Policy (CAP) there is a strong interest of the European Commission for counting and individually locating fruit trees. An automatic counting algorithm developed by the JRC (OLICOUNT) was used in the past for olive trees only, on 1m black and white orthophotos but with limits in case of young trees or irregular groves. This study investigates the improvement of fruit tree identification using VHR images on a large set of data in three test sites, one in Creta (Greece) and one in the south-east of France with a majority of olive trees and associated fruit trees, and the last one in Florida on citrus trees. OLICOUNT was compared with two other automatic tree counting, applications, one using the CRISP software on citrus trees and the other completely automatic based on regional minima (morphological image analysis). Additional investigation was undertaken to refine the methods. This paper describes the automatic methods and presents the results derived from the tests.

Paper Details

Date Published: 26 October 2004
PDF: 14 pages
Proc. SPIE 5568, Remote Sensing for Agriculture, Ecosystems, and Hydrology VI, (26 October 2004); doi: 10.1117/12.562439
Show Author Affiliations
Josiane Masson, European Commission Joint Research Ctr. (Italy)
Pierre Soille, European Commission Joint Research Ctr. (Italy)
Rick Mueller, U.S. Dept. of Agriculture/ National Agricultural Statistics Service (United States)

Published in SPIE Proceedings Vol. 5568:
Remote Sensing for Agriculture, Ecosystems, and Hydrology VI
Manfred Owe; Guido D'Urso; Ben T. Gouweleeuw; Anne M. Jochum, Editor(s)

© SPIE. Terms of Use
Back to Top