Library Categories


New strawberry plant sorter

Researchers at Carnegie Mellon University’s National Robotics Engineering Center, or NREC, in Pittsburgh have developed a plant-sorting machine that uses computer vision and machine learning to inspect and grade harvested strawberry plants. Then, it mechanically sorts them by quality — tasks that, until now, could only be done manually. In a successful field test this fall, the machine classified and sorted harvested plants more consistently and faster than workers could, with a comparable error rate.

Key Points

• New machine classifies and sorts harvested plants fast and consistently.

• The project is backed by 85% of the California strawberry plant market.

• Rate of 5,000 plants per hour is much faster than human sorting.

California sponsors

“We’re looking forward to using the system,” says Liz Ponce, CEO of Lassen Canyon Nursery, based in Redding, Calif., one of five strawberry plant producers that is sponsoring the NREC project. “All of our stakeholders feel that it has a lot of potential.”

The other sponsors are Driscoll Nursery Associates, Nor Cal Nursery Inc., Plant Sciences Inc., and Crown Nursery LLC. Together, the five producers represent about 85% of the California strawberry-plant nursery market.

To maintain good strawberry yields, commercial berry growers must replace their plants every year. During the fall harvest season, strawberry-plant nursery farms use manual labor to sort several hundred million strawberry plants into good and bad categories — a tedious and costly process.

The strawberry plant sorter uses computer vision to examine harvested plants that pass by on a conveyor belt. The sorter’s novel machine learning algorithms allow it to be taught how to classify strawberry plants of different sizes, varieties, and stages of growth, beyond the simple classification of good and bad plants. This introduces dramatic new efficiencies for strawberry nursery farms, helping them improve quality, streamline production, and deliver better strawberry plants to berry growers — which, in turn, produce better strawberries for consumers.

“The sorter can adapt to plants that vary from year to year, or even within the same growing season,” says Christopher Fromme, the project’s manager and lead engineer. “It’s very flexible.”

Tested in the field

During a 10-day field test in October, NREC engineers tested the strawberry plant sorter under realistic conditions, where rain and frost could change plants’ appearance and roots might contain mud and debris. The prototype system had to sort plants of different varieties and maturity levels. While in the field, it sorted, on average, over 75,000 strawberry plants at 5,000 plants per hour — several times faster than human sorting rates.

02102440 A.tif

FIELD-TESTED: This is the strawberry plant sorter in action at the field test. The workers are feeding strawberry plants into the sorter. The sorter’s novel machine learning algorithms allow it to be taught how to classify strawberry plants of different sizes, varieties and stages of growth.

02102440 B.tif

QUALITY CONTROL: Strawberry plants pass through the sorter on a conveyor belt. An air jet sorts strawberry plants into bins, according to their quality.

This article published in the February, 2010 edition of CALIFORNIA FARMER.

All rights reserved. Copyright Farm Progress Cos. 2010.