基于深度学习的葡萄果穗检测

果穗检测是农业自动化采摘作业的热门关键技术。针对成熟期葡萄易腐烂、成熟状况不一，以及葡萄果园背景复杂、光照条件多变的问题，基于YOLO v5s算法提出一种轻量化改进的检测识别方法。首先，采用Efficientnet-v2网络作为特征提取主干并在其中融合了不降维局部跨信道交互模块，在保障精度的前提下大幅度缩减模型大小以及参数量，加快模型推理速度；其次，为了进一步弥补模型简化造成的精度损失，在模型特征融合关键位置引入坐标注意力模块，强化对目标的关注度，提升模型应对密集目标检测以及对抗复杂背景干扰的能力，保障算法的综合性能及可靠性。实验结果表明：改进后的算法平均准确率达98.7%,平均检测速度为0.028 s,模型大小仅为12.01 MB,相较于改进前的算法准确率提升了0.41%,检测速度快了22%,模型减小了13.2%。在果园场景图像检测测试中，所提出算法能够良好地检测出葡萄果穗并辨别其状况，对不同环境影响也具有较强适应能力，为自动化采摘技术的发展提供了参考。

Grape fruit detection based on deep learning

Fruit detection is a popular key technology in agricultural automatic picking. Aiming at the problems of perishable grapes at maturity, different ripening conditions, complex background of grape orchards and changeable lighting conditions, a lightweight improved detection and recognition method based on Yolo v5s algorithm is proposed in this paper. Firstly, the method uses Efficientnet-v2 network as the backbone of feature extraction and integrates the no dimensionality reduction local cross-channel interaction mechanism, which greatly reduces the size of the model and the amount of parameters on the premise of ensuring the accuracy, and speeds up the model reasoning speed; Secondly, in order to further compensate for the accuracy loss caused by model simplification, coordinate attention mechanism is introduced at the key position of model feature fusion to strengthen the attention to the target, improve the model''s ability to detect dense targets and resist complex background interference, and ensure the comprehensive performance and reliability of the algorithm. The experimental results show that the average accuracy of the improved algorithm is 98.7%, the average detection speed is 0.028 seconds, and the model size is only 12.01MB. Compared with the improved algorithm, the accuracy is increased by 0.41%, the detection speed is increased by 22%, and the model is reduced by 13.2%. In the orchard scene image detection test, the algorithm proposed in this paper can well detect the grape fruit and identify its status, and has strong adaptability to different environmental impacts, which provides a reference for the development of automatic picking technology.