Observatorio de I+D+i UPM

Memorias de investigación
Communications at congresses:
CHARACTERIZATION OF VINEYARD\'S CANOPY THROUGH FUZZY CLUSTERING AND SVM OVER COLOR IMAGES
Year:2012
Research Areas
  • Information technology and adata processing,
  • Agriculture automatization
Information
Abstract
Introduction: In recent years several studies have been conducted in order to asses features from the vineyard?s canopies. It is desirable to quantify features such as leaves, vine shoots, trunks and grapes areas, because this information allows, for example, to predict yields and quality, to perform smart sprayings or to determine the vineyard\'s vigor. However, previous researches are aimed at solving one problem at a time, because these kinds of algorithms usually are time consuming and are unfeasible in real time. Material and Methods: In this work we propose an image processing methodology (framework) developed for performance in-field grapes and leaves detection and quantification, based on a seven step methodology: 1) image segmentation through Fuzzy C-Means with Gustafson Kessel (FCM-GK) clustering; 2) obtaining of FCM-GK outputs (centroids) for acting as seeding for K-Means clustering; 3) Identification of the clusters generated by K-Means using a Support Vector Machine (SVM) classifier. 4) Performance of morphological operations over the grapes and leaves clusters in order to fill holes and to eliminate small pixels clusters; 5) Creation of a mosaic image by Scale-Invariant Feature Transform (SIFT) in order to avoid overlapping between images; 6) Calculation of the areas of leaves and grapes and finding of the centroids in the grape bunches; 7) and geo-referentiation of the generated data using a simple KML (Keyhole Markup Language) file. Image data are collected using a color camera fixed to a mobile platform. This platform was developed to give a stabilized surface to guarantee that the images were acquired parallel to de vineyard rows. In this way, the platform avoids the distortion of the images that lead to poor estimation of the areas. Results/Conclusions: Our preliminary results are promissory as shown in Fig. 1, although they still have shown that it is necessary to implement a camera stabilization system to avoid undesired camera movements, and also a parallel processing procedure in order to speed up the mosaicking process.
International
Si
Congress
3rd CIGR International Conference of Agricultural Engineering (CIGR-AgEng2012)
960
Place
Valencia
Reviewers
Si
ISBN/ISSN
84-615-9654-4
http://cigr.ageng2012.org/images/fotosg/tabla_137_
Start Date
09/07/2012
End Date
13/07/2012
From page
1
To page
6
proceeding of3rd CIGR International Conference of Agricultural Engineering (CIGR-AgEng2012)
Participants
  • Autor: Christian Correa Farias (UPM)
  • Autor: Constantino Valero Ubierna (UPM)
  • Autor: Pilar Barreiro Elorza (UPM)
Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: LPF-TAGRALIA: Técnicas Avanzadas en Agroalimentación
S2i 2020 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNCIDE 2011 (OTR-2011-0236)
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)