Claim · model-written summary
The vision system reached a recall of 93.5% in greenhouse trials.
Not reportedTaxonMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentComparatorDirectionQualifier
Verbatim
e0“Experimental trials conducted under practical greenhouse conditions demonstrated a fruit detection precision of 96.9%, recall of 93.5%, and mean Intersection-over-Union of 79.2%”
Title
Autonomous Tomato Harvesting System Integrating AI-Controlled Robotics in Greenhouses
Mihai Gabriel Matache; Florin Bogdan Marin; Catalin Ioan Persu; et al. Agriculture 2026. doi:10.3390/agriculture16080847
Other claims from this paper (6)
- Method / resource The vision system reached a fruit detection precision of 96.9% in greenhouse trials.
- Method / resource The vision system reached a mean Intersection-over-Union of 79.2% in greenhouse trials.
- Method / resource The robotic platform achieved an overall harvesting success rate of 78.5%.
- Method / resource The harvesting success rate reached 85% for unobstructed fruits.
- Method / resource The average cycle time was 15 s per fruit in direct harvesting scenarios.
- Method / resource Rail-guided mobility significantly improved positioning stability and repeatability during manipulation compared with fully mobile platforms.