Search Results (4)

Yield forecasting is of immeasurable value in modern viticulture to optimize harvest scheduling and quality management. Traditionally, this task is carried out through manual and destructive sampling of production components and their accurate assessment is expensive, time-consuming, and error-prone, resulting in erroneous projections. The number of inflorescences and flowers per vine is one of the main components and serves as an early predictor. The adoption of new non-invasive technologies can automate this task and drive viticulture yield forecasting to higher levels of accuracy. In this study, different Single Stage Instance Segmentation models from the state-of-the-art You Only Look Once (YOLO) family, such as YOLOv5 and YOLOv8, were benchmarked on a dataset of RGB images for grapevine inflorescence detection and segmentation, with the aim of validating and subsequently implementing the solution for counting the number of inflorescences and flowers. All models obtained promising results, with the YOLOv8s and the YOLOv5s models standing out with an F1-Score of 95.1% and 97.7% for the detection and segmentation tasks, respectively. Moreover, the low inference times obtained demonstrate the models’ ability to be deployed in real-time applications, allowing for non-destructive predictions in uncontrolled environments. Full article

Aureobasidium pullulans is a yeast-like fungus found on the surface of the grape berries that has been proven to act as a biocontrol agent for the management of grey mould disease caused by Botrytis cinerea. In this work, an indigenous strain of A. pullulans isolated from grape berries and selected according to the in vitro activity against B. cinerea, was used in vineyards of the winery where it originated, in comparison with a commercial product containing two A. pullulans strains with the aim of assessing its effectiveness as a biocontrol agent. The experimental design included daily meteorological data registration and the early defoliation of grapevines as treatments. The monitoring of A. pullulans strains on grape berries by plate counts and molecular methods as well as of B. cinerea symptoms on grape bunches was performed in the different trials from the end of flowering to the harvest time. Results highlighted that although no significant differences (p < 0.05) in the occurrence of B. cinerea were detected according to different treatments, the mean incidence of symptomatic berries ranged from 7 to 16%, with the lowest values recorded in bunches treated with the indigenous A. pullulans strain. The efficacy of the biocontrol agent was affected more by meteorological conditions than the defoliation practice. Full article

In the present study, we analyzed the main parameters related with the potential fertilization ability of two grapevine varieties, Godello and Mencía, during the years 2017 and 2018. The research was carried out in two vineyards of the Galician winegrowing Designation of Origin areas of Ribeiro and Ribeira Sacra. Ten vines of each variety were selected for bunch and flower counting, pollen calculations, pollen viability studies by means of aceto-carmine (AC) stain and 2, 3, 5-triphenyl tetrazolium chloride (TTC) methods, and the determination of their germination rate. In all vineyards the 50% fruitset was reached, except for Godello in Cenlle during 2017. The mean coulure value was higher for Godello (40.5%) than for Mencía (31%). Analyzing the pollen production per plant and airborne pollen levels, we observed important discordances between them, which can be due to the influence of weather conditions and be related with self-pollination processes. We found important differences on pollen viability depending on the applied method and variety, with higher values for the AC method than the TTC for both varieties in all study plots, and higher values for Mencía variety than Godello. Regarding germination rates, we observed a marked reduction in 2017 with respect to 2018, in all study sites and for both varieties. The analyzed parameters were useful to explain the different productive abilities of Godello and Mencía varieties in the two studied bioclimatic regions of Ribeiro and Ribeira Sacra. Full article

Grapevine flowering and fruit set greatly determine crop yield. This paper presents a new smartphone application for automatically counting, non-invasively and directly in the vineyard, the flower number in grapevine inflorescence photos by implementing artificial vision techniques. The application, called vitisFlower^®, firstly guides the user to appropriately take an inflorescence photo using the smartphone’s camera. Then, by means of image analysis, the flowers in the image are detected and counted. vitisFlower^® has been developed for Android devices and uses the OpenCV libraries to maximize computational efficiency. The application was tested on 140 inflorescence images of 11 grapevine varieties taken with two different devices. On average, more than 84% of flowers in the captures were found, with a precision exceeding 94%. Additionally, the application’s efficiency on four different devices covering a wide range of the market’s spectrum was also studied. The results of this benchmarking study showed significant differences among devices, although indicating that the application is efficiently usable even with low-range devices. vitisFlower is one of the first applications for viticulture that is currently freely available on Google Play. Full article