What question did this study set out to answer?

This research aims to enhance wheat yield estimation by automating spike and spikelet detection using deep learning techniques.

June 17, 2026Scientific ReportsOpen Access

Wheat spike and spikelet detection and counting from high-resolution digital imagery using YOLO with Oriented Bounding Boxes

View Full Paper

Ask AI

Bookmark

Authors

HGHillson GhimireSouth Dakota State University MMMaitiniyazi MaimaitijiangSouth Dakota State University STSubash ThapaSouth Dakota State University

Discussion

Member takes

Overview

Randomized trial evaluates spike and spikelet detection accuracy in wheat using advanced AI methods, suggesting a scalable solution for crop management.

Key Points

This research aims to enhance wheat yield estimation by automating spike and spikelet detection using deep learning techniques.
Evaluated YOLOv11 and YOLOv12 variants for wheat spike and spikelet counting using high-resolution digital imagery.
Introduced a benchmark dataset with 48,521 spike and 60,404 spikelet instances and oriented bounding box annotations.
Compared detection accuracy and performance metrics between pre-trained and non-pretrained YOLO models.
YOLOv11 achieved superior spike detection accuracy (mAP@0.5 = 95.8%, Pearson r = 0.993) with faster training times than YOLOv12.
Non-pretrained YOLOv11 exhibited higher spikelet detection accuracy (mAP@0.5 = 99.0%).
Counting performance was comparable across both YOLO models.

Cite This Study

Ghimire et al. (2026) studied this question.

synapsesocial.com/papers/6a323e9ed50b63ecad207d64 https://doi.org/10.1038/s41598-026-55761-w

View Full Paper

Ask AI

Bookmark

June 17, 2026Scientific ReportsOpen Access

Wheat spike and spikelet detection and counting from high-resolution digital imagery using YOLO with Oriented Bounding Boxes

View Full Paper

Ask AI

Bookmark

Authors

HGHillson GhimireSouth Dakota State University MMMaitiniyazi MaimaitijiangSouth Dakota State University STSubash ThapaSouth Dakota State University

Discussion

Member takes

Overview

Randomized trial evaluates spike and spikelet detection accuracy in wheat using advanced AI methods, suggesting a scalable solution for crop management.

Key Points

This research aims to enhance wheat yield estimation by automating spike and spikelet detection using deep learning techniques.
Evaluated YOLOv11 and YOLOv12 variants for wheat spike and spikelet counting using high-resolution digital imagery.
Introduced a benchmark dataset with 48,521 spike and 60,404 spikelet instances and oriented bounding box annotations.
Compared detection accuracy and performance metrics between pre-trained and non-pretrained YOLO models.
YOLOv11 achieved superior spike detection accuracy (mAP@0.5 = 95.8%, Pearson r = 0.993) with faster training times than YOLOv12.
Non-pretrained YOLOv11 exhibited higher spikelet detection accuracy (mAP@0.5 = 99.0%).
Counting performance was comparable across both YOLO models.

Cite This Study

Ghimire et al. (2026) studied this question.

synapsesocial.com/papers/6a323e9ed50b63ecad207d64 https://doi.org/10.1038/s41598-026-55761-w

Also Consider

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

View Full Paper

Ask AI

Bookmark