Grapevine yield and leaf area estimation using supervised classification methodology on RGB images taken under field conditions

  1. Diago, M.-P. 2
  2. Correa, C. 1
  3. Millán, B. 2
  4. Barreiro, P. 1
  5. Valero, C. 1
  6. Tardaguila, J. 23
  1. 1 Universidad Politécnica de Madrid
    info

    Universidad Politécnica de Madrid

    Madrid, España

    ROR https://ror.org/03n6nwv02

  2. 2 Instituto de Ciencias de la Vid y del Vino
    info

    Instituto de Ciencias de la Vid y del Vino

    Logroño, España

    ROR https://ror.org/01rm2sw78

  3. 3 Universidad de La Rioja
    info

    Universidad de La Rioja

    Logroño, España

    ROR https://ror.org/0553yr311

Journal:
Sensors

ISSN: 1424-8220

Year of publication: 2012

Volume: 12

Issue: 12

Pages: 16988-17006

Type: Article

DOI: 10.3390/S121216988 SCOPUS: 2-s2.0-84871686486 WoS: WOS:000312607500056 GOOGLE SCHOLAR lock_openOpen access editor

More publications in: Sensors

Institutional repository: lock_openOpen access Editor

Abstract

The aim of this research was to implement a methodology through the generation of a supervised classifier based on the Mahalanobis distance to characterize the grapevine canopy and assess leaf area and yield using RGB images. The method automatically processes sets of images, and calculates the areas (number of pixels) corresponding to seven different classes (Grapes, Wood, Background, and four classes of Leaf, of increasing leaf age). Each one is initialized by the user, who selects a set of representative pixels for every class in order to induce the clustering around them. The proposed methodology was evaluated with 70 grapevine (V. vinifera L. cv. Tempranillo) images, acquired in a commercial vineyard located in La Rioja (Spain), after several defoliation and de-fruiting events on 10 vines, with a conventional RGB camera and no artificial illumination. The segmentation results showed a performance of 92% for leaves and 98% for clusters, and allowed to assess the grapevine's leaf area and yield with R2 values of 0.81 (p < 0.001) and 0.73 (p = 0.002), respectively. This methodology, which operates with a simple image acquisition setup and guarantees the right number and kind of pixel classes, has shown to be suitable and robust enough to provide valuable information for vineyard management. © 2012 by the authors; licensee MDPI, Basel, Switzerland.