Comparative Analysis of Transformer-Based and CNN Models for High-Throughput Wheat Head Detection

Abstract

Wheat head or spike detection is significant for phenotyping because it can be directly correlated to yield and is an indicator of yield potential. Historically, wheat head counting was a labor-intensive and error prone process. Use of Deep Learning (DL) techniques has automated this process allowing automated wheat head detection and counting using high resolution imagery, allowing large-scale, High Throughput Phenotyping (HTP). Despite the use of advanced technologies, wheat head detection is a challenging task due to high environmental variability, cultivar differences, and head overlap. Several attempts have been made to make the DL models more robust and the wheat head datasets more diverse to improve the detection accuracy and reliability. With the introduction of advanced DL architectures, there has been continuous improvement in accuracy of head detection. In this study, we have evaluated the performance of three different cutting-edge DL models - YOLOv10x, RetinaNet, and MM-Grounding DINO for wheat head detection. We have also combined two different wheat datasets, Global Wheat Head Detection (GWHD) 2021 and SPIKE dataset to get a diverse dataset with a wide range of genotypes. This study aims to contribute to the ongoing evolution of wheat head detection techniques and provide an insight into how these three models perform for this task.

Plant phenotyping relevance

コムギ穂の検出・計数という植物形態形質の画像解析手法を対象に、複数の深層学習モデルを評価し、異なるデータセットを統合して性能を比較しているため、フェノタイピング手法が中心である。

Code and data availability

The paper uses the public GWHD_2021 and SPIKE datasets (cited prior community datasets, not paper-specific deposits) and describes training YOLOv10, RetinaNet, and MM-Grounding DINO on Kaggle, but provides no authors' public code, trained checkpoints, merged dataset release, or supplement with a URL. No qualifying, ver

No evidence-backed public reproduction asset is currently recorded.