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

Labor shortages in fruit crop production have prompted the development ofmechanized and automated machines as alternatives to labor-intensive orchardoperations such as harvesting, pruning, and thinning. Agricultural robotscapable of identifying tree canopy parts and estimating geometric andtopological parameters, such as branch diameter, length, and angles, canoptimize crop yields through automated pruning and thinning platforms. In thisstudy, we proposed a machine vision system to estimate canopy parameters inapple orchards and determine an optimal number of fruit for individualbranches, providing a foundation for robotic pruning, flower thinning, andfruitlet thinning to achieve desired yield and quality.Using color and depthinformation from an RGB-D sensor (Microsoft Azure Kinect DK), a YOLOv8-basedinstance segmentation technique was developed to identify trunks and branchesof apple trees during the dormant season. Principal Component Analysis wasapplied to estimate branch diameter (used to calculate limb cross-sectionalarea, or LCSA) and orientation. The estimated branch diameter was utilized tocalculate LCSA, which served as an input for crop-load estimation, with largerLCSA values indicating a higher potential fruit-bearing capacity.RMSE forbranch diameter estimation was 2.08 mm, and for crop-load estimation, 3.95.Based on commercial apple orchard management practices, the target crop-load(number of fruit) for each segmented branch was estimated with a mean absoluteerror (MAE) of 2.99 (ground truth crop-load was 6 apples per LCSA). This studydemonstrated a promising workflow with high performance in identifying trunksand branches of apple trees in dynamic commercial orchard environments andintegrating farm management practices into automated decision-making.

Machine Vision-Based Crop-Load Estimation Using YOLOv8