Efficient View Planning Guided by Previous-Session Reconstruction for Repeated Plant Monitoring

Abstract

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.

Plant phenotyping relevance

植物の反復モニタリング向けに、過去セッションの3D再構成を利用した視点計画とロボット撮影経路を開発・評価しており、植物形状取得の方法が中心です。

Code and data availability

The paper references two paper-specific public assets: the authors' greenhouse multi-session row dataset on Kaggle and their implementation on GitHub (HumanoidsBonn/TPVP). However, neither URL is present in the allowed_urls list (only https://poly.cam/ is allowed, which is the acquisition tool, not a paper-specificphen

No evidence-backed public reproduction asset is currently recorded.