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.
- Sicong Pan, Hao Hu, Hui Wei, Nils Dengler, Tobias Zaenker and Maren Bennewitz.
- ArXiv preprint, 2023
- Code available!
- 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