Quantitative Evaluation of Maize Emergence Using UAV Imagery and Deep Learning

• Published in: Remote sensing (Basel, Switzerland) Vol. 15; no. 8; p. 1979
• Main Authors: Liu, Minguo, Su, Wen-Hao, Wang, Xi-Qing
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.04.2023
• Subjects: Accuracy; Agricultural production; Algorithms; case studies; Cereal crops; Climate change; Coefficient of variation; Color imagery; Corn; Cotton; crop emergence; Crop yields; Crops; Data collection; Data processing; Deep learning; Drone aircraft; Environmental aspects; Experiments; field phenotyping; Food; Genotypes; Global positioning systems; GPS; Growth; Growth stage; Image acquisition; Image processing; Irrigation; Machine learning; Mathematical analysis; Mean square errors; Methods; Morphology; Performance prediction; phenotype; Phenotyping; Planting; Planting density; prediction; Predictions; quantitative analysis; Remote sensing; Seeding; seedling emergence; Seedlings; Software; Spatial distribution; TOPSIS analysis; Unmanned aerial vehicles; unmanned aerial vehicles (UAV); Variation; Wheat; YOLO model; China

Accurate assessment of crop emergence helps breeders select appropriate crop genotypes, and farmers make timely field management decisions to increase maize yields. Crop emergence is conventionally quantified by manual calculations to quantify the number and size of seedlings, which is laborious, in...