Validation of commercially available systems for yield and quality forecasting in apple cultivation

Abstract

Manual yield estimation usually requires a lot of work and is expensive. With the help of modern image recognition systems, it is already possible to create yield forecasts to determine area-related yield capacity and fruit size distribution. This makes it possible to apply cultivation measures in a more targeted way and to optimize storage and logistics. Therefore, in this paper, five different commercially available systems were tested for their precision and practicality with different varieties and at different locatins. For this purpose, the data obtained were compared with manually determined data and the deviation was calculated. It was found that there were large differences between the various systems, although some systems already showed sufficient accuracy. Most of the systems, however, had too much deviation and the time required to collect the data was often higher than that required for manual measurement.

Keywords

• fruit production
• yield prognosis
• yield estimation
• yield forecasting
• fruit sizing
• fruit storage
• sizing
• size class distribution
• image recognition
• artificial intelligence