Grapevine Yield and Leaf Area Estimation Using Supervised Classification Methodology on RGB Images Taken under Field Conditions

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.

Influence of the training system on the agronomic behavior and grape composition of Albariño in Rías Baixas apellation

The aim of this study was to evaluate if early defoliation can be an alternative to bunch thinning in limiting yield and improving quality in grapes of the white cultivar Loureiro (Vitis vinifera L.), grafted onto 1103P. The field trial had been set up in a commercial vineyard in Vinhos Verdes Region (Northwest of Portugal, 41º 48? 53? N, 8º 24? 42? W). Treatments studied, performed five days before full bloom were: LR5 ? Leaf removal of the first five basal leaves, performed manually, LR8 ? Leave removal of the first eight basal leaves, LRM ? mechanical leaf removal and C ? the control, without defoliation. This paper reports the results of four years (2010-2013). The results presented a significant removal of main leaf area after defoliation principally in the most intensive treatment (LR8) but at harvest, the total leaf area had been compensated by lateral regrowth and no statistical differences between the treatments and the control were found. Early defoliation caused a decrease in fruit set and also a significant reduction in the diameter of the berry within the more severe defoliation treatments (LR5 and LR8). Yield factors were also significantly affected by the defoliation, causing a reduction of bunch weight and in 2013 a yield reduction in LR8 and LRM, and in 2010 in LR8. Conversely, LR5 presented a yield always similar to the control C. The reduction of cluster compactness and the substantial improvement of the microclimate at the cluster level significantly reduced bunch rot incidence in the defoliated modalities compared to control. No carry-over effects, along the four years trial were observed Early defoliation proved to be a canopy management technique that can have a strong impact in the final quality of grapes, reducing the compactness and lower the incidence and intensity of bunch rot, even if the reduction of yield observed in other papers had not been observed in all modalities.