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/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Agricultural applications such as yield prediction, precision agriculture andautomated harvesting need systems able to infer the crop state from low-costsensing devices. Proximal sensing using affordable cameras combined withcomputer vision has seen a promising alternative, strengthened after the adventof convolutional neural networks (CNNs) as an alternative for challengingpattern recognition problems in natural images. Considering fruit growingmonitoring and automation, a fundamental problem is the detection, segmentationand counting of individual fruits in orchards. Here we show that for winegrapes, a crop presenting large variability in shape, color, size andcompactness, grape clusters can be successfully detected, segmented and trackedusing state-of-the-art CNNs. In a test set containing 408 grape clusters fromimages taken on a trellis-system based vineyard, we have reached an F 1 -scoreup to 0.91 for instance segmentation, a fine separation of each cluster fromother structures in the image that allows a more accurate assessment of fruitsize and shape. We have also shown as clusters can be identified and trackedalong video sequences recording orchard rows. We also present a public datasetcontaining grape clusters properly annotated in 300 images and a novelannotation methodology for segmentation of complex objects in natural images.The presented pipeline for annotation, training, evaluation and tracking ofagricultural patterns in images can be replicated for different crops andproduction systems. It can be employed in the development of sensing componentsfor several agricultural and environmental applications.

Grape detection, segmentation and tracking using deep neural networks and three-dimensional association