What question did this study set out to answer?

To evaluate the effectiveness of the YOLOv9-small object detection model for identifying and counting corn plants across multiple soil background colors, growth stages, and drone flight altitudes.

December 20, 2025Remote SensingOpen Access

Corn Plant Detection Using YOLOv9 Across Different Soil Background Colors, Growth Stages, and UAV Flight Heights

View Full Paper

Ask AI

Bookmark

Authors

TBThiago O. C. Barboza ASAdão Felipe dos Santos EBEmily K. Bedwell

Discussion

Member takes

Overview

Machine learning evaluation demonstrates accurate corn plant detection using YOLOv9 from drone imagery, indicating optimal performance at specific growth stages and lower flight altitudes.

Key Points

To evaluate the effectiveness of the YOLOv9-small object detection model for identifying and counting corn plants across multiple soil background colors, growth stages, and drone flight altitudes.
Captured UAV imagery across three distinct fields featuring three soil backgrounds, two flight altitudes (30 m and 70 m), and four growth stages (V2, V3, V5, and V6).
Cropped aerial images to 640 × 640 pixels and partitioned data into training (70%), validation (20%), and testing (10%) sets.
Evaluated model performance using precision, recall, classification loss, and mean average precision thresholds (mAP50 and mAP50–90).
Detection accuracy peaked at the V3 and V5 growth stages, achieving mAP50 values exceeding 85% in conventional tillage fields, with slight decreases over gray and red-brown soils due to visual interference.
Increasing UAV flight height from 30 m to 70 m reduced detection accuracy by 8% to 12%, though precision remained high at the V5 stage.
Model detection performance was lowest during the earliest (V2) and latest (V6) vegetative growth stages.

Cite This Study

Barboza et al. (2025) studied this question.

synapsesocial.com/papers/6a725311c2d7c309082735af https://doi.org/10.3390/rs18010014

View Full Paper

Ask AI

Bookmark

December 20, 2025Remote SensingOpen Access

Corn Plant Detection Using YOLOv9 Across Different Soil Background Colors, Growth Stages, and UAV Flight Heights

View Full Paper

Ask AI

Bookmark

Authors

TBThiago O. C. Barboza ASAdão Felipe dos Santos EBEmily K. Bedwell

Discussion

Member takes

Overview

Machine learning evaluation demonstrates accurate corn plant detection using YOLOv9 from drone imagery, indicating optimal performance at specific growth stages and lower flight altitudes.

Key Points

To evaluate the effectiveness of the YOLOv9-small object detection model for identifying and counting corn plants across multiple soil background colors, growth stages, and drone flight altitudes.
Captured UAV imagery across three distinct fields featuring three soil backgrounds, two flight altitudes (30 m and 70 m), and four growth stages (V2, V3, V5, and V6).
Cropped aerial images to 640 × 640 pixels and partitioned data into training (70%), validation (20%), and testing (10%) sets.
Evaluated model performance using precision, recall, classification loss, and mean average precision thresholds (mAP50 and mAP50–90).
Detection accuracy peaked at the V3 and V5 growth stages, achieving mAP50 values exceeding 85% in conventional tillage fields, with slight decreases over gray and red-brown soils due to visual interference.
Increasing UAV flight height from 30 m to 70 m reduced detection accuracy by 8% to 12%, though precision remained high at the V5 stage.
Model detection performance was lowest during the earliest (V2) and latest (V6) vegetative growth stages.

Cite This Study

Barboza et al. (2025) studied this question.

synapsesocial.com/papers/6a725311c2d7c309082735af https://doi.org/10.3390/rs18010014

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark