Kidney bean detection in complex agricultural scenarios based on the kidneyB-YOLO model

This study addresses the problem of detecting multiple targets and occluded kidney beans in the complex agricultural scenarios under the open-field trellis cultivation.

A target detection model based on kidneyB-YOLO is proposed. The model integrated the dynamic convolution module, the Deformable Attention Transformer (DAT) attention mechanism, the feature fusion detection head improved Adaptively Spatial Feature Fusion (ASFF) detection method, and the Focaler-SIoU loss function. The dynamic convolution module adaptively adjusted parameters based on the input. The DAT attention mechanism introduced a deformable attention mechanism, focusing only on a small key region of the image. The feature fusion detection head ASFF, an adaptive spatial feature fusion method, filtered out conflicting target information. The new loss function module, Focaler-SIoU, was formed by combining the SIoU loss function with the Focaler-IoU algorithm. An open-canopy environment bean pod dataset was constructed for model training and validation.

The results showed that the KidneyB-YOLO model exhibited significant improvements compared to the original YOLOv8n, especially in occluded scenarios. The model achieved a detection performance of 85.90% mAP with a computational complexity of 12.4 GFLOPs, a model size of 12 MB, and operated at 32.5 FPS.

The enhancements improved the accuracy and robustness of bean pod detection. The model demonstrated strong robustness and generalization capability in the fruit detection task for kidney bean harvesting under open-air trellises.