Accurate detection and counting of wheat spikes are crucial for yield estimation and variety selection in precision agriculture. However, challenges such as complex field environments, morphological variations, and small target sizes hinder the performance of existing models in real-world applications. This study proposes FEWheat-YOLO, a lightweight and efficient detection framework optimized for deployment on agricultural edge devices. The architecture integrates four key modules: (1) FEMANet, a mixed aggregation feature enhancement network with Efficient Multi-scale Attention (EMA) for improved small-target representation; (2) BiAFA-FPN, a bidirectional asymmetric feature pyramid network for efficient multi-scale feature fusion; (3) ADown, an adaptive downsampling module that preserves structural details during resolution reduction; and (4) GSCDHead, a grouped shared convolution detection head for reduced parameters and computational cost. Evaluated on a hybrid dataset combining GWHD2021 and a self-collected field dataset, FEWheat-YOLO achieved a COCO-style AP of 51.11%, AP@50 of 89.8%, and AP scores of 18.1%, 50.5%, and 61.2% for small, medium, and large targets, respectively, with an average recall (AR) of 58.1%. In wheat spike counting tasks, the model achieved an R² of 0.941, MAE of 3.46, and RMSE of 6.25, demonstrating high counting accuracy and robustness. The proposed model requires only 0.67 M parameters, 5.3 GFLOPs, and 1.6 MB of storage, while achieving an inference speed of 54 FPS. Compared to YOLOv11n, FEWheat-YOLO improved AP@50, AP_s, AP_m, AP_l, and AR by 0.53%, 0.7%, 0.7%, 0.4%, and 0.3%, respectively, while reducing parameters by 74%, computation by 15.9%, and model size by 69.2%. These results indicate that FEWheat-YOLO provides an effective balance between detection accuracy, counting performance, and model efficiency, offering strong potential for real-time agricultural applications on resource-limited platforms.

Accurate detection and counting of open cotton bolls from unmanned aerial vehicle (UAV) RGB imagery are essential for organ-level cotton phenotyping and field monitoring, but remain challenging in high-density cotton fields because open bolls are small, densely distributed, partially occluded, and visually similar to plastic mulch, branches, senescent leaves, shadows, and drip-irrigation belts. To address these challenges, this study proposes OpenBoll-YOLO, a lightweight small-object detector designed for open cotton boll detection and counting in UAV nadir-view images. A UAV RGB dataset was collected at the boll-opening stage in Alar, Xinjiang, China, covering two cotton varieties and two acquisition dates. Based on YOLOv11s, OpenBoll-YOLO integrates three task-oriented components: a multi-kernel small-object enhancement pyramid (MSOEP) to preserve shallow spatial details and strengthen multi-scale feature fusion, a cross-stage partial block with a dynamic mixing layer (C2DML) to improve local structural discrimination under complex backgrounds, and a lightweight mixed aggregation network (LMANet) to enhance contextual representation with reduced model complexity. On the independent test set, OpenBoll-YOLO achieved 86.7% precision, 84.5% recall, 85.6% F1-score, 92.9% mAP@0.5, 81.5% mAP@0.75, and 71.7% mAP@0.5:0.95, with only 3.1 M parameters and an inference speed of 86 frames s⁻¹. Compared with YOLOv11s, it improved mAP@0.5 and mAP@0.5:0.95 by 2.4 and 5.9 percentage points, respectively, while reducing the parameter count by 67.0%. Counting evaluation further showed that OpenBoll-YOLO reduced the mean absolute error from 11.98 to 10.12 bolls image⁻¹ and increased R² from 0.87 to 0.91. These results demonstrate that OpenBoll-YOLO provides an accurate and lightweight solution for dense open cotton boll detection and counting in high-density field conditions.