Efficient View Planning Guided by Previous-Session Reconstruction for Repeated Plant Monitoring
This addresses the need for efficient and consistent crop growth tracking in agriculture, though it is incremental as it builds on existing view planning methods.
The paper tackles the problem of costly 3D reconstruction for repeated plant monitoring by proposing efficient view planning that reuses a previous-session model, achieving comparable or higher surface coverage with fewer views and shorter robot paths in experiments on real datasets.
Repeated plant monitoring is essential for tracking crop growth, and 3D reconstruction enables consistent comparison across monitoring sessions. However, rebuilding a 3D model from scratch in every session is costly and overlooks informative geometry already observed previously. We propose efficient view planning guided by a previous-session reconstruction, which reuses a 3D model from the previous session to improve active perception in the current session. Based on this previous-session reconstruction, our method replaces iterative next-best-view planning with one-shot view planning that selects an informative set of views and computes the globally shortest execution path connecting them. Experiments on real multi-session datasets, including public single-plant scans and a newly collected greenhouse crop-row dataset, show that our method achieves comparable or higher surface coverage with fewer executed views and shorter robot paths than iterative and one-shot baselines.