Zhou Wenqi, Song Chao, Song Kai, Wen Nuan, Sun Xiaobo, Gao Pengxiang
College of Engineering, Northeast Agricultural University, Harbin 150030, China.
Foods. 2023 Feb 13;12(4):793. doi: 10.3390/foods12040793.
Carrots are a type of vegetable with high nutrition. Before entering the market, the surface defect detection and sorting of carrots can greatly improve food safety and quality. To detect defects on the surfaces of carrots during combine harvest stage, this study proposed an improved knowledge distillation network structure that took yolo-v5s as the teacher network and a lightweight network that replaced the backbone network with mobilenetv2 and completed channel pruning as a student network (mobile-slimv5s). To make the improved student network adapt to the image blur caused by the vibration of the carrot combine harvester, we put the ordinary dataset Dataset (T) and dataset Dataset (S), which contains motion blurring treatment, into the teacher network and the improved lightweight network, respectively, for learning. By connecting multi-stage features of the teacher network, knowledge distillation was carried out, and different weight values were set for each feature to realize that the multi-stage features of the teacher network guide the single-layer output of the student network. Finally, the optimal lightweight network mobile-slimv5s was established, with a network model size of 5.37 MB. The experimental results show that when the learning rate is set to 0.0001, the batch size is set to 64, and the dropout is set to 0.65, the model accuracy of mobile-slimv5s is 90.7%, which is significantly higher than other algorithms. It can synchronously realize carrot harvesting and surface defect detection. This study laid a theoretical foundation for applying knowledge distillation structures to the simultaneous operations of crop combine harvesting and surface defect detection in a field environment. This study effectively improves the accuracy of crop sorting in the field and contributes to the development of smart agriculture.
胡萝卜是一种营养丰富的蔬菜。在进入市场之前，对胡萝卜进行表面缺陷检测和分选能够极大地提高食品安全和质量。为了在联合收获阶段检测胡萝卜表面的缺陷，本研究提出了一种改进的知识蒸馏网络结构，该结构以yolo-v5s作为教师网络，并用mobilenetv2替换骨干网络并完成通道剪枝的轻量级网络作为学生网络（mobile-slimv5s）。为了使改进后的学生网络适应胡萝卜联合收割机振动引起的图像模糊，我们将普通数据集Dataset (T) 和经过运动模糊处理的数据集Dataset (S) 分别放入教师网络和改进后的轻量级网络中进行学习。通过连接教师网络的多阶段特征进行知识蒸馏，并为每个特征设置不同的权重值，以实现教师网络的多阶段特征指导学生网络的单层输出。最终建立了最优的轻量级网络mobile-slimv5s，网络模型大小为5.37 MB。实验结果表明，当学习率设置为0.0001、批量大小设置为64、随机失活设置为0.65时，mobile-slimv5s的模型准确率为90.7%，显著高于其他算法。它能够同步实现胡萝卜收获和表面缺陷检测。本研究为将知识蒸馏结构应用于田间环境下作物联合收获与表面缺陷检测的同步作业奠定了理论基础。本研究有效提高了田间作物分选的准确率，为智慧农业的发展做出了贡献。
