Advanced workflows for UAV-based crop height estimation using structure from motion (SfM) point clouds

Abstract

Crop height is a key biophysical parameter closely linked to plant growth, biomass, and yield. With the advancement of remote sensing technologies, unmanned aerial vehicles (UAV) have emerged as a promising tool for estimating crop height using structure from motion (SfM) point clouds. However, accurately mapping the digital terrain model (DTM) beneath dense canopies remains a major challenge, as existing methods struggle to capture the soil surface effectively under full vegetation cover. This study aimed to develop and evaluate efficient workflows for generating DTMs from UAV-derived point clouds for in-season crop height estimation, with a focus on eliminating the need for pre-season UAV flights. The experiment was conducted during the 2023 maize growing season in Temple, TX, and compared three workflows: (i) UAV-B CH , which used UAV-derived bare soil surfaces as the DTM; (ii) Sent CH , which used Sentinel-1A-derived surfaces from the dormant season; and (iii) UAV-P CH , a novel approach that applied a low-pass filter to select the lowest 1 % of elevation points within a moving window, followed by fitting a 2.5D regression surface to generate the DTM. Results showed that UAV-P CH consistently outperformed the other methods across two fields with varying elevation patterns, achieving higher accuracy (R 2 ≈ 0.89) compared to UAV-B CH (R 2 ≈ 0.66) and Sent CH (R 2 ≈ 0.69). UAV-P DTM effectively minimized temporal inconsistencies and vertical misalignments commonly associated with multi-date UAV acquisitions. This approach offers a scalable and efficient solution for crop height estimation using a single UAV flight. Future research should explore its applicability across diverse crop types and canopy structures to enhance its utility in precision agriculture.

Plant phenotyping relevance

UAV-SfM点群から作物高を推定するDTM生成ワークフローを開発・比較評価しており、植物形質の取得方法が研究の中心である。

Code and data availability

公開論文であることは確認できましたが、現在の公式API・許可済み取得経路では本文を自動取得できませんでした。

No evidence-backed public reproduction asset is currently recorded.