Plot-Level Maize Early Stage Stand Counting and Spacing Detection Using Advanced Deep Learning Algorithms Based on UAV Imagery

• Published in: Agronomy (Basel) Vol. 13; no. 7; p. 1728
• Main Authors: Wang, Biwen, Zhou, Jing, Costa, Martin, Kaeppler, Shawn M., Zhang, Zhou
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.07.2023
• Subjects: Accuracy; Agricultural production; Agricultural research; Algorithms; Analysis; Corn; Crop production; Crop yield; Crop yields; Data mining; Decision making; Deep learning; Food industry; Food security; Food supply; Genotypes; Industrial applications; Information management; Learning algorithms; Machine learning; maize stand counting; Neural networks; Object recognition; Performance evaluation; Phenotyping; Plant breeding; plant spacing variability detection; Raw materials; Seeds; unmanned aerial vehicle; Unmanned aerial vehicles; United States > US; Wisconsin
• ISSN: 2073-4395; 2073-4395
• DOI: 10.3390/agronomy13071728

Phenotyping is one of the most important processes in modern breeding, especially for maize, which is an important crop for food, feeds, and industrial uses. Breeders invest considerable time in identifying genotypes with high productivity and stress tolerance. Plant spacing plays a critical role in determining the yield of crops in production settings to provide useful management information. In this study, we propose an automated solution using unmanned aerial vehicle (UAV) imagery and deep learning algorithms to provide accurate stand counting and plant-level spacing variabilities (PSV) in order to facilitate the breeders’ decision making. A high-resolution UAV was used to train three deep learning models, namely, YOLOv5, YOLOX, and YOLOR, for both maize stand counting and PSV detection. The results indicate that after optimizing the non-maximum suppression (NMS) intersection of union (IoU) threshold, YOLOv5 obtained the best stand counting accuracy, with a coefficient of determination (R2) of 0.936 and mean absolute error (MAE) of 1.958. Furthermore, the YOLOX model subsequently achieved an F1-score value of 0.896 for PSV detection. This study shows the promising accuracy and reliability of processed UAV imagery for automating stand counting and spacing evaluation and its potential to be implemented further into real-time breeding decision making.