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

Yield estimation and forecasting are of special interest in the field of grapevine breeding and viticulture. The number of harvested berries per plant is strongly correlated with the resulting quality. Therefore, early yield forecasting can enable a focused thinning of berries to ensure a high qual- ity end product. Traditionally yield estimation is done by extrapolating from a small sample size and by utilizing his- toric data. Moreover, it needs to be carried out by skilled ex- perts with much experience in this field. Berry detection in images offers a cheap, fast and non-invasive alternative to the otherwise time-consuming and subjective on-site anal- ysis by experts. We apply fully convolutional neural net- works on images acquired with the Phenoliner, a field phe- notyping platform. We count single berries in images to avoid the error-prone detection of grapevine clusters. Clus- ters are often overlapping and can vary a lot in the size which makes the reliable detection of them difficult. We ad- dress especially the detection of white grapes directly in the vineyard. The detection of single berries is formulated as a classification task with three classes, namely ’berry’, ’edge’ and ’background’. A connected component algorithm is ap- plied to determine the number of berries in one image. We compare the automatically counted number of berries with the manually detected berries in 60 images showing Ries- ling plants in vertical shoot positioned trellis (VSP) and semi minimal pruned hedges (SMPH). We are able to detect berries correctly within the VSP system with an accuracy of 94.0 % and for the SMPH system with 85.6 %.