Temporal-Prior-Guided View Planning for Periodic 3D Plant Reconstruction

2025-10-08

AI Summary

To address resource inefficiency from redundant modeling and the neglect of temporal priors in periodic 3D plant reconstruction, this paper proposes a temporal-prior-guided incremental reconstruction framework. Methodologically, it leverages the previous-cycle reconstruction as geometric and structural prior, adapts to plant growth deformation via non-rigid alignment and controllable geometric dilation, and jointly optimizes view selection using set cover and TSP-based path planning to generate a minimal yet complete view set and shortest acquisition trajectory. Experiments on maize and tomato datasets demonstrate a 20–35% reduction in required views compared to baselines, with maintained or improved coverage and comparable motion cost—yielding significantly enhanced overall acquisition efficiency. The core contribution is the first integration of temporal geometric priors into the closed-loop view-planning pipeline, enabling efficient, adaptive incremental reconstruction.

Technology Category

• Planning, Routing, and Scheduling: Temporal Planning
• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Periodic 3D reconstruction is essential for crop monitoring, but costly when each cycle restarts from scratch, wasting resources and ignoring information from previous captures. We propose temporal-prior-guided view planning for periodic plant reconstruction, in which a previously reconstructed model of the same plant is non-rigidly aligned to a new partial observation to form an approximation of the current geometry. To accommodate plant growth, we inflate this approximation and solve a set covering optimization problem to compute a minimal set of views. We integrated this method into a complete pipeline that acquires one additional next-best view before registration for robustness and then plans a globally shortest path to connect the planned set of views and outputs the best view sequence. Experiments on maize and tomato under hemisphere and sphere view spaces show that our system maintains or improves surface coverage while requiring fewer views and comparable movement cost compared to state-of-the-art baselines.

Problem

• Optimizing view planning for periodic 3D plant reconstruction
• Reducing resource waste by leveraging prior reconstruction data
• Minimizing required views while maintaining surface coverage accuracy

Innovation

• Temporal-prior-guided view planning for reconstruction
• Non-rigid alignment of previous models to current observations
• Set covering optimization for minimal view selection