4D Crop Monitoring: Spatio-Temporal Reconstruction for Agriculture

Abstract

Autonomous crop monitoring at high spatial and temporal resolution is a critical problem in precision agriculture. While Structure from Motion and Multi-View Stereo algorithms can finely reconstruct the 3D structure of a field with low-cost image sensors, these algorithms fail to capture the dynamic nature of continuously growing crops. In this paper we propose a 4D reconstruction approach to crop monitoring, which employs a spatio-temporal model of dynamic scenes that is useful for precision agriculture applications. Additionally, we provide a robust data association algorithm to address the problem of large appearance changes due to scenes being viewed from different angles at different points in time, which is critical to achieving 4D reconstruction. Finally, we collected a high quality dataset with ground truth statistics to evaluate the performance of our method. We demonstrate that our 4D reconstruction approach provides models that are qualitatively correct with respect to visual appearance and quantitatively accurate when measured against the ground truth geometric properties of the monitored crops.

Code and data availability

The paper's peanut field dataset (images, IMU/GPS, ground truth crop height and chlorophyll measurements) is described as a contribution, but the authors only state it 'will make publicly available' in the future tense, with no URL or deposit identifier. The GTSAM library is a generic third-party tool, and the CMU/UMIC

No evidence-backed public reproduction asset is currently recorded.