A novel deep learning framework for High-Throughput peanut seedling identification across diverse germplasm and complex field environments

• A robust deep learning model (P-YOLOv11s) is proposed for peanut seedling detection. • The model excels across 1025 genotypes and varying field conditions. • UAV flight altitude is the most critical factor for detection accuracy. • The framework enables high-throughput seedling counting for genetic breeding programs. Accurate peanut seedling recognition is essential for quantifying emergence rates, a key phenotyping task in breeding programs for this important global oilseed. This task is challenged by field heterogeneity from morphological variation (genotype, growth stage, planting density) and imaging variability (flight altitude, solar angle). To address this, object-based image analysis (OBIA) and deep learning approaches were evaluated using UAV remote sensing imagery collected under systematically varied field conditions. An enhanced framework, P-YOLOv11s, was developed for UAV-based peanut seedling detection, incorporating a P2 layer for fine-scale features, an asymptotic feature pyramid network for multi-scale fusion, and an iEMA attention mechanism for occlusion robustness. The experimental design encompassed significant agronomic diversity (1025 genotypes, nitrogen regimes, planting years, densities, and eco-zones), developmental stages (three- to six-leaf), and flight configurations (15, 25, 40 m altitudes; four diurnal intervals). P-YOLOv11s demonstrated strong robustness, achieving a mean Average Precision (AP) of 93.5 %, with 62 % fewer false detections than OBIA and a 4.8 % higher AP than other YOLO variants. Flight altitude was the most influential factor, with 15 m yielding the best results. Peak accuracy (99.4 %) occurred at the four- to five-leaf stage, while solar angle had a minimal effect (<1.7 % variation). The framework achieved subplot-level precision (μ = 0.42 plants), addressing the challenge of accurate field-based phenotyping under real-world constraints.