New AI Tool Gives Blueberry Growers a Heads up on the Best Time to Harvest

Blueberry picking season will soon be in high gear in North Carolina. This season, growers are getting closer to having a new advantage to maximize their harvest. North Carolina State University Assistant Professor Jing Zhang has been leading the way on developing a way to help farmers better gauge which bushes are the most productive and when they’ll be ready to pick — using computer vision and artificial intelligence.

Zhang can simply snap a picture of a blueberry bush and upload it to an app on her phone. Within seconds, an AI system tells her how many berries are on the bush and what percentage of them are ripe.

In using the technology, farmers can better plan their harvests, says Cody Craddock, a Randolph County agricultural Extension agent who has been working with Zhang and growers to beta test the app.

That’s because blueberries don’t ripen all at once. They must be picked several times over the course of the season, and each time requires labor. Blueberries don’t continue ripening after picking, so harvesting too early means they won’t be as sweet, while waiting too long makes for soft or shriveled fruit.

“If farmers can make sure that the bushes are at peak ripeness before sending crews out into the field and estimate how many berries they’ll bring to market, they can maximize their labor,” Craddock says.

“It’s a decision tool,” Zhang adds.

To build the system, they trained a computer vision model to identify individual berries and distinguish ripe ones from unripe ones by feeding it thousands of labeled images.

To test and refine their models, last summer Craddock and other members of the N.C. PSI Extension Agent Network collected images from 10 commercial blueberry farms across North Carolina using handheld cameras and cellphones.

Afterward, they picked every berry from the bushes, sorting and counting them by hand, and compared their results with the automated counts based on the images.

Zhang uses similar approaches to tackle a range of other farm problems, including Neopestalotiopsis, an emerging disease in strawberries.

While the blueberry app isn’t publicly accessible for anyone to upload their photos yet, she’s working on that. In the meantime, she’s training the model on additional blueberry varieties.

For more, continue reading at cals.ncsu.edu.