A Detection Approach for Wheat Spike Recognition and Counting Based on UAV Images and Improved Faster R-CNN.

Abstract

This study presents an innovative unmanned aerial vehicle (UAV)-based intelligent detection method utilizing an improved Faster Region-based Convolutional Neural Network (Faster R-CNN) architecture to address the inefficiency and inaccuracy inherent in manual wheat spike counting. We systematically collected a high-resolution image dataset (2000 images, 4096 × 3072 pixels) covering key growth stages (heading, grain filling, and maturity) of winter wheat ( Triticum aestivum L.) during 2022-2023 using a DJI M300 RTK equipped with multispectral sensors. The dataset encompasses diverse field scenarios under five fertilization treatments (organic-only, organic-inorganic 7:3 and 3:7 ratios, inorganic-only, and no fertilizer) and two irrigation regimes (full and deficit irrigation), ensuring representativeness and generalizability. For model development, we replaced conventional VGG16 with ResNet-50 as the backbone network, incorporating residual connections and channel attention mechanisms to achieve 92.1% mean average precision (mAP) while reducing parameters from 135 M to 77 M (43% decrease). The GFLOPS of the improved model has been reduced from 1.9 to 1.7, an decrease of 10.53%, and the computational efficiency of the model has been improved. Performance tests demonstrated a 15% reduction in missed detection rate compared to YOLOv8 in dense canopies, with spike count regression analysis yielding R 2 = 0.88 ( p 2 ) and varying illumination conditions, maintaining >85% accuracy even under cloudy weather. Furthermore, by integrating spike recognition with agronomic parameters (e.g., grain weight), we developed a comprehensive yield estimation model achieving 93.5% accuracy under optimal water-fertilizer management (70% ETc irrigation with 3:7 organic-inorganic ratio). This work systematically addresses key technical challenges in automated spike detection through standardized data acquisition, lightweight model design, and field validation, offering significant practical value for smart agriculture development.

Plant phenotyping relevance

UAV画像からコムギ穂を認識・計数する画像解析手法を開発し、データセット、モデル改良、比較検証、圃場性能評価まで行っており、植物形質取得が研究の中心です。

Code and data availability

The paper's self-collected UAV wheat spike dataset (2000 images) and trained model have no public deposit; the Data Availability Statement says 'Data are contained within the article.' The only public dataset mentioned is the pre-existing Global Wheat Head Detection Dataset (GWHD) from Kaggle, which is a cited prior/外部

No evidence-backed public reproduction asset is currently recorded.