English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Yield estimation and forecasting are of special interest in the field ofgrapevine breeding and viticulture. The number of harvested berries per plantis strongly correlated with the resulting quality. Therefore, early yieldforecasting can enable a focused thinning of berries to ensure a high qualityend product. Traditionally yield estimation is done by extrapolating from asmall sample size and by utilizing historic data. Moreover, it needs to becarried out by skilled experts with much experience in this field. Berrydetection in images offers a cheap, fast and non-invasive alternative to theotherwise time-consuming and subjective on-site analysis by experts. We applyfully convolutional neural networks on images acquired with the Phenoliner, afield phenotyping platform. We count single berries in images to avoid theerror-prone detection of grapevine clusters. Clusters are often overlapping andcan vary a lot in the size which makes the reliable detection of themdifficult. We address especially the detection of white grapes directly in thevineyard. The detection of single berries is formulated as a classificationtask with three classes, namely 'berry', 'edge' and 'background'. A connectedcomponent algorithm is applied to determine the number of berries in one image.We compare the automatically counted number of berries with the manuallydetected berries in 60 images showing Riesling plants in vertical shootpositioned trellis (VSP) and semi minimal pruned hedges (SMPH). We are able todetect berries correctly within the VSP system with an accuracy of 94.0 \% andfor the SMPH system with 85.6 \%.

Detection of Single Grapevine Berries in Images Using Fully Convolutional Neural Networks