Efficient Long-Term Crop Monitoring

IP3: Efficient Sensing for Long-Term Crop Monitoring

Lead: Maren Bennewitz

PhD student: Sicong Pan

Central Question: How to efficiently measure the relevant traits over a crop’s life cycle?

Achievements: Fast and Complete 3D Modelling of Unknown Objects

    • One-Shot View Planning for Fast and Complete Unknown Object Reconstruction to the Video.

Prior Works on View Planning:

  • A Global Max-Flow-Based Multi-Resolution Next-Best-View Method for Reconstruction of 3D Unknown Objects to the Video.
    • Sicong Pan and Hui Wei.
    • In: IEEE Robotics and Automation Letters (RA-L), 2022, to the Presentation and Code
  • SCVP: Learning One-Shot View Planning via Set Covering for Unknown Object
    Reconstruction to the Video.

    • Sicong Pan, Hao Hu and Hui Wei.
    • In: IEEE Robotics and Automation Letters (RA-L), 2022, to the Presentation and Code
  • A Global Generalized Maximum Coverage-based Solution to the Non-model-based View Planning Problem for Object Reconstruction to the Video.
    • Sicong Pan and Hui Wei.
    • In: Computer Vision and Image Understanding (CVIU), 2023, to the Code

Work Program
WP1: Efficient Sensing of Relevant Crop Parts
WP2: Exploiting Prior Information to Speed Up Data Acquisition Over Time
WP3: Input Optimization for Forecasting and Decision Making

Highlight