Abstract
Abstract The accurate estimation of soybean ( Glycine max ) stand establishment is essential for evaluating crop emergence and informing early‐season management practices. Recent advances in unmanned aerial vehicle (UAV) imagery and computer vision offer opportunities to automate plant population assessments; however, limited information exists on their accuracy in soybeans. This study evaluated two commercial UAV‐based plant counting platforms, a point‐based (convolutional neural network–derived) and a line‐based (Hough transform–derived) approach across two growing seasons, three flight altitudes (15.2, 45.7, and 91.4 m), and seven plant removal treatments, including a control (no removal). UAV imagery was collected at 7‐ to 10‐day intervals from 10 to 36 days after planting (DAP), and predictions were compared to manual on‐ground counts. The point‐based method provided the highest accuracy (within ±12% of ground‐truth; R 2 = 0.81) when imagery was collected between 14 and 20 DAP at 15.2‐m altitude. Accuracy declined beyond 27 DAP as canopy overlap increased. The line‐based method remained more stable across altitudes and later growth stages but consistently overestimated plant counts, particularly in dense and narrow row canopies. Incorporating on‐ground calibration areas improved accuracy by an average of 28% and up to 48% for the line‐based approach in narrow rows. Row spacing and plant removal patterns had minimal effects on prediction error, although short repeating gaps were poorly detected by the line‐based method. Overall, UAV‐based plant counts in soybean are feasible and dependable when flights are timed during early vegetative growth and supported by calibration, providing a practical tool for in‐season management and field‐based crop monitoring.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by-nc. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 8
Claim · model-written summary
The point-based UAV counting method gave its highest accuracy, within ±12% of ground-truth with R 2 = 0.81, when imagery was collected 14 to 20 DAP at 15.2-m altitude.
- Taxon
- soybean
Glycine maxt0 - Outcome
- accuracye1
- Direction
- higheste1
- Value
- within ±12% of ground‐truth; R 2 = 0.81e1
- Qualifier
- between 14 and 20 DAP at 15.2‐m altitudee1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“stand counts in soybean”
e1“The point‐based method provided the highest accuracy (within ±12% of ground‐truth; R 2 = 0.81) when imagery was collected between 14 and 20 DAP at 15.2‐m altitude”
Claim · model-written summary
UAV count accuracy declined beyond 27 DAP as canopy overlap increased.
- Taxon
- soybeanGlycine maxt0
- Organ / stage
- 27 DAPe1
- Outcome
- Accuracye1
- Direction
- declinede1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“stand counts in soybean”
e1“Accuracy declined beyond 27 DAP as canopy overlap increased”
Claim · model-written summary
The line-based method remained more stable across altitudes and later growth stages.
- Taxon
- soybeanGlycine maxt0
- Outcome
- stable across altitudes and later growth stagese1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“stand counts in soybean”
e1“The line‐based method remained more stable across altitudes and later growth stages”
Claim · model-written summary
The line-based method consistently overestimated plant counts, particularly in dense and narrow row canopies.
- Taxon
- soybeanGlycine maxt0
- Outcome
- plant countse1
- Direction
- overestimatede1
- Qualifier
- dense and narrow row canopiese1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“stand counts in soybean”
e1“consistently overestimated plant counts, particularly in dense and narrow row canopies”
Claim · model-written summary
On-ground calibration areas improved accuracy by an average of 28% and up to 48% for the line-based approach in narrow rows.
- Taxon
- soybeanGlycine maxt0
- Treatment
- on‐ground calibration arease1
- Outcome
- accuracye1
- Direction
- improvede1
- Value
- an average of 28% and up to 48%e1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“stand counts in soybean”
e1“Incorporating on‐ground calibration areas improved accuracy by an average of 28% and up to 48% for the line‐based approach in narrow rows”
Claim · model-written summary
Row spacing and plant removal patterns had minimal effects on UAV prediction error.
- Taxon
- soybeanGlycine maxt0
- Treatment
- Row spacing and plant removal patternse1
- Outcome
- prediction errore1
- Direction
- minimal effectse1
Not reportedComparator
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“stand counts in soybean”
e1“Row spacing and plant removal patterns had minimal effects on prediction error”
Claim · model-written summary
Short repeating gaps were poorly detected by the line-based method.
- Taxon
- soybeanGlycine maxt0
- Outcome
- short repeating gaps were poorly detectede1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
t0“stand counts in soybean”
e1“short repeating gaps were poorly detected by the line‐based method”
Claim · model-written summary
The authors conclude that UAV-based plant counts in soybean are feasible and dependable when flights are timed during early vegetative growth and supported by calibration.
- Taxon
- soybeanGlycine maxe1
- Outcome
- feasible and dependablee1
- Qualifier
- flights are timed during early vegetative growth and supported by calibratione1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“UAV‐based plant counts in soybean are feasible and dependable when flights are timed during early vegetative growth and supported by calibration”