Public summary

Optimization of harvest quality with smart technology

Oxbo

February 27, 2025

Smarter harvesting processes through advanced detection

The use of smart technology can help improve the efficiency and sustainability of harvesting. Oxbo tested a prototype harvesting machine equipped with detection technology and artificial intelligence to optimize harvest quality. This study focuses on reducing dependence on human operators and enhancing automated monitoring in the harvesting process.

Innovation package, use case, and type of trial

    Status: evaluation report

    Technical functionality

    Menu card category

    Broad research question

    How can detection technology improve harvest quality?

    A more efficient harvest requires precise monitoring and automated adjustments. This project investigates how sensors and AI models can help reduce harvest losses and optimize machine performance while maintaining crop quality.

    Approach

    Testing detection technology in practice

    A prototype harvesting machine was equipped with advanced detection equipment and tested under various conditions. The system monitored harvest quality and investigated the impact of different machine settings. Experts reviewed the results and evaluated the potential for automatic adjustments.

    Goal

    Validation of technology for precision harvesting

    The goal of this test was to determine how detection technology can be used to measure and improve harvest quality. This helps reduce harvest losses, increase precision in crop handling, and optimize the performance of harvesting machines.

    Results and reflection

    Valuable insights into harvest quality and areas for improvement

    The technology provided valuable insights into crop processing and the influence of machine settings.

    Successes:

    • Sensors collected detailed data on the processed product.

    • The AI model detected vegetables with high accuracy.

    • Two of the eight tested machine settings had a measurable effect on processing.

    Lessons learned:

    • Detection of contaminants in the crop was less effective and requires further refinement.

    • Additional tests are needed to make the technology more broadly applicable under varying conditions.

    Leading Partners involved