Estimating Plant Height in Castor Bean Using RPA-Derived DEM from RGB Images

Abstract This study aimed to assess the applicability of plant height estimation in castor bean using remotely piloted aircraft (RPA) imagery as a high-throughput phenotyping approach. RGB images (20 MP; DJI Mavic 3 Enterprise Multispectral; GSD = 1.84 cm pixel–1; 40 m flight altitude) were acquired at four phenological stages for four genotypes. Digital elevation models and orthomosaics were generated in Agisoft Metashape (Educational version), and individual plant height was extracted using FieldImageR in QGIS. Estimated heights showed strong agreement with direct field measurements, particularly at 118 days after sowing (DAS), where the smallest bias (–0.07 m), lowest RMSE (0.11 m), and high correlation (r = 0.94; p < 0.001) were observed. Limits of agreement derived from a mixed-effects framework indicated reduced prediction error during this stage. Estimation accuracy improved when plants exceeded 1.2 m in height and exhibited a denser canopy structure, corresponding to the production stage. Overall, RGB imagery tended to underestimate plant height. These findings highlight the importance of aligning flight parameters, especially GSD and altitude, with plant phenology, as well as considering environmental conditions that may influence image reconstruction accuracy.

Authors

Institutions

Publication Details

Journal
ACS Agricultural Science & Technology
Published
2026-11-17
DOI
https://doi.org/10.1021/acsagscitech.5c01054
Primary Topic
Remote Sensing in Agriculture
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Estimating Plant Height in Castor Bean Using RPA-Derived DEM from RGB Images

Ilneide Braz Santos de Jesus, Elienay Dutra, Diego Fernando Marmolejo Cortes, Denise Barreto dos Santos et al.
2 links
ACS Agricultural Science & Technology
Remote Sensing in Agriculture
article

Estimating Plant Height in Castor Bean Using RPA-Derived DEM from RGB Images

Ilneide Braz Santos de Jesus, Elienay Dutra, Diego Fernando Marmolejo Cortes, Denise Barreto dos Santos, Everton Luís Poelking, Andreia Simões Santos, Myriam El Adas, Diego Andrade Santos, Simone Alves Silva
article en

Abstract

Abstract This study aimed to assess the applicability of plant height estimation in castor bean using remotely piloted aircraft (RPA) imagery as a high-throughput phenotyping approach. RGB images (20 MP; DJI Mavic 3 Enterprise Multispectral; GSD = 1.84 cm pixel–1; 40 m flight altitude) were acquired at four phenological stages for four genotypes. Digital elevation models and orthomosaics were generated in Agisoft Metashape (Educational version), and individual plant height was extracted using FieldImageR in QGIS. Estimated heights showed strong agreement with direct field measurements, particularly at 118 days after sowing (DAS), where the smallest bias (–0.07 m), lowest RMSE (0.11 m), and high correlation (r = 0.94; p < 0.001) were observed. Limits of agreement derived from a mixed-effects framework indicated reduced prediction error during this stage. Estimation accuracy improved when plants exceeded 1.2 m in height and exhibited a denser canopy structure, corresponding to the production stage. Overall, RGB imagery tended to underestimate plant height. These findings highlight the importance of aligning flight parameters, especially GSD and altitude, with plant phenology, as well as considering environmental conditions that may influence image reconstruction accuracy.

ACS Agricultural Science & Technology
Universidade Federal do Recôncavo da Bahia (BR)
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Petrobras, Fundação de Amparo à Pesquisa do Estado da Bahia
Zero hunger
Remote Sensing in Agriculture
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon