The bruising of fruits occurs at various stages, including picking, transportation, and sale. For fruits with large kernels that occupy a significant portion of their overall volume, considering the impact of the kernel is crucial in elucidating the mechanisms of bruising and controlling bruise formation. This study employs reverse engineering to develop a composite finite element model of loquat peel, flesh, and kernels. Bruise formation during collisions is analyzed from the perspectives of contact force, equivalent stress, energy, bruise volume, and bruise susceptibility, aiming to reveal the significant role of the fruit core in the bruise formation process. In this paper, we propose the use of 3D printing technology to accurately quantify bruise measurement for fruits with large kernels. The results showed that the maximum contact force, equivalent stress, and internal energy between loquat and steel/wood were essentially consistent, but all exceeded those observed when using rubber. Due to the blocking of stress transmission by the kernel, the susceptibility of loquats to bruising increases with height before decreasing. This study elucidates the mechanism of bruise formation in fruits with large kernels and provides methods and ideas for the research and precise measurement of complex fruit bruising characteristics.

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