关键词: YOLO, 注意力机制, 特征融合, 油菜角果计数, 小目标检测

Abstract:

[Objective] Rapeseed is the largest oilseed crop in China, and increasing its yield is the core objective of breeding efforts. As a central component of rapeseed yield, the number of effective siliques per plant is an indispensable phenotypic trait in the phenotyping process. Its rapid and accurate counting is crucial for the breeding of high-yield and superior varieties. Although object detection and counting research has made significant progress in the agricultural field, it still faces some challenges in actual detached phenotyping scenarios. Therefore, aiming at the accurate counting difficulties caused by the widespread dense clustering, local overlapping of branches, and tiny silique beak targets in detached rapeseed phenotyping scenarios, a rapeseed silique detection and counting method is proposed based on YOLO11n-A³ (YOLO11n with Area Attention and Aligned Fusion). This method improves detection accuracy and feature extraction efficiency while maintaining a lightweight design, providing edge-side technical support for rapeseed phenotyping and the breeding of high-yield, high-quality varieties. [Methods] The proposed method adopted the lightweight convolutional structure of YOLOv11n as its backbone. To further enhance the global representation capability of silique features, the cross stage partial with spatial attention (C2PSA) module was embedded in the high-level layers of the backbone for joint channel-spatial modeling. This approach significantly improved the representation of multi-scale features while retaining the receptive-field-expansion advantage of the spatial pyramid pooling fast (SPPF) module, without substantially increasing computational costs. Secondly, the Area Attention module was introduced to locally enhance the neck feature fusion network. By replacing specific convolutions with the Area Attention module, the network leverages local region perception to improve feature extraction and anti-interference capabilities for densely overlapping small targets, while keeping training and deployment risks controllable. Finally, a bidirectional feature alignment and fusion architecture consisting of aligned feature pyramid network (Align-FPN) and aligned path aggregation network (Align-PAN) were constructed to replace the standard feature fusion path. In the Align-FPN stage, high-level semantic features were effectively transmitted to lower levels via the area-attention enhanced cross-feature (A2C2f) module and tiny multi-scale context (TMC) block (P3), the soft nearest neighbor interpolation (SNI) module were introduced to alleviate spatial inconsistencies among multi-scale features. In the Align-PAN stage, the extended spatial-window down-sampling (ESD) module was further combined for feature separation and enhancement, highlighting key scale features through an adaptive weighted fusion mechanism to significantly enhance the interaction and consistency of multi-scale features. [Results and Discussions] The precision, recall, and mAP_0.5-0.95 of YOLOv11n-A³ reached 92.6%, 85.1%, and 47.1%, respectively, showing increases of 1.8, 2.5, and 12.5 percentage points over the baseline model. The computational load, parameter count, and detection speed of the model reached 6.39 GFLOPs, 2.58 M, and 625.3 f/s, respectively. In the silique counting task, the coefficient of determination (R²) reached 0.937; the mean absolute error (MAE) was only 2.61; the root mean square error (RMSE) was 3.7; and the mean absolute percentage error (MAPE) was 11.37%. Furthermore, to meet the application requirements of real-time field phenotyping, the lightweight model was encapsulated and deployed in a custom-developed artificial intelligence (AI) tool to achieve fast and accurate counting of rapeseed siliques. This effectively verified the engineering application potential of the proposed lightweight algorithm on edge devices. [Conclusions] The YOLOv11n-A³ model successfully improves counting accuracy while maintaining a lightweight design, effectively detecting small targets in densely distributed scenarios. The rapeseed breeding AI tool developed based on this model achieves the rapid and accurate detection and counting of rapeseed siliques, providing reliable technical support for rapeseed phenotyping and the breeding of high-yield, high-quality varieties. In summary, YOLO11n-A3 achieved an excellent balance among detection accuracy, counting precision, and computational overhead, fully demonstrating its lightweight and highly efficient superiority.

Key words: YOLO, attention mechanism, feature fusion, rapeseed silique counting, small object detection