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

Instance segmentation, an important image processing operation for automationin agriculture, is used to precisely delineate individual objects of interestwithin images, which provides foundational information for various automated orrobotic tasks such as selective harvesting and precision pruning. This studycompares the one-stage YOLOv8 and the two-stage Mask R-CNN machine learningmodels for instance segmentation under varying orchard conditions across twodatasets. Dataset 1, collected in dormant season, includes images of dormantapple trees, which were used to train multi-object segmentation modelsdelineating tree branches and trunks. Dataset 2, collected in the early growingseason, includes images of apple tree canopies with green foliage and immature(green) apples (also called fruitlet), which were used to train single-objectsegmentation models delineating only immature green apples. The results showedthat YOLOv8 performed better than Mask R-CNN, achieving good precision andnear-perfect recall across both datasets at a confidence threshold of 0.5.Specifically, for Dataset 1, YOLOv8 achieved a precision of 0.90 and a recallof 0.95 for all classes. In comparison, Mask R-CNN demonstrated a precision of0.81 and a recall of 0.81 for the same dataset. With Dataset 2, YOLOv8 achieveda precision of 0.93 and a recall of 0.97. Mask R-CNN, in this single-classscenario, achieved a precision of 0.85 and a recall of 0.88. Additionally, theinference times for YOLOv8 were 10.9 ms for multi-class segmentation (Dataset1) and 7.8 ms for single-class segmentation (Dataset 2), compared to 15.6 msand 12.8 ms achieved by Mask R-CNN's, respectively.

Comparing YOLOv8 and Mask RCNN for object segmentation in complex orchard environments