High-Throughput Spike Detection in Greenhouse Cultivated Grain Crops with Attention Mechanisms-Based Deep Learning Models.

Abstract

Detection of spikes is the first important step toward image-based quantitative assessment of crop yield. However, spikes of grain plants occupy only a tiny fraction of the image area and often emerge in the middle of the mass of plant leaves that exhibit similar colors to spike regions. Consequently, accurate detection of grain spikes renders, in general, a non-trivial task even for advanced, state-of-the-art deep neural networks (DNNs). To improve pattern detection in spikes, we propose architectural changes to Faster-RCNN (FRCNN) by reducing feature extraction layers and introducing a global attention module. The performance of our extended FRCNN-A vs. conventional FRCNN was compared on images of different European wheat cultivars, including "difficult" bushy phenotypes from 2 different phenotyping facilities and optical setups. Our experimental results show that introduced architectural adaptations in FRCNN-A helped to improve spike detection accuracy in inner regions. The mean average precision (mAP) of FRCNN and FRCNN-A on inner spikes is 76.0% and 81.0%, respectively, while on the state-of-the-art detection DNNs, Swin Transformer mAP is 83.0%. As a lightweight network, FRCNN-A is faster than FRCNN and Swin Transformer on both baseline and augmented training datasets. On the FastGAN augmented dataset, FRCNN achieved a mAP of 84.24%, FRCNN-A attained a mAP of 85.0%, and the Swin Transformer achieved a mAP of 89.45%. The increase in mAP of DNNs on the augmented datasets is proportional to the amount of the IPK original and augmented images. Overall, this study indicates a superior performance of attention mechanisms-based deep learning models in detecting small and subtle features of grain spikes.

Plant phenotyping relevance

穂を画像から検出し収量の定量評価につなげる深層学習手法を開発・比較評価しており、植物表現型取得が研究の中心である。

Code and data availability

The paper uses PSI/IPK greenhouse wheat images with spike bounding-box annotations and custom DNN models (FRCNN-A/ASpikeNet, FastGAN augmentation), but no public repository or URL for these datasets, annotations, code, or trained models is provided. The only availability statement points to example images in the (unver

No evidence-backed public reproduction asset is currently recorded.