AerialYield-B2D: A Greenhouse Blueberry Dataset with Five-Stage Ripeness Masks and Fruit Counts

Not provided in the abstract

datasetimage segmentationberry countingagriculture

2608.16973

Builder Relevance

80%

2h ago

Abstract

AerialYield-B2D is a curated dataset containing 514 RGB images of blueberries with detailed annotations for five ripeness stages.

Reality Card

Core Claim

The dataset provides a comprehensive resource for blueberry ripeness segmentation and berry counting with 30,195 annotated instances across five stages.

Method / Result

The dataset includes 514 RGB images and 30,195 annotated blueberry instances.

Limitations

The dataset does not provide harvest weight, fruit mass, or per-area yield measurements, limiting its use for yield estimation.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.

← Back to all papers