李康顺, 杨振盛, 江梓锋, 等. 基于改进YOLOX-Nano的农作物叶片病害检测与识别方法[J]. 华南农业大学学报, 2023, 44(4): 593-603. DOI: 10.7671/j.issn.1001-411X.202207039
    引用本文: 李康顺, 杨振盛, 江梓锋, 等. 基于改进YOLOX-Nano的农作物叶片病害检测与识别方法[J]. 华南农业大学学报, 2023, 44(4): 593-603. DOI: 10.7671/j.issn.1001-411X.202207039
    LI Kangshun, YANG Zhensheng, JIANG Zifeng, et al. Detection and identification of crop leaf diseases based on improved YOLOX-Nano[J]. Journal of South China Agricultural University, 2023, 44(4): 593-603. DOI: 10.7671/j.issn.1001-411X.202207039
    Citation: LI Kangshun, YANG Zhensheng, JIANG Zifeng, et al. Detection and identification of crop leaf diseases based on improved YOLOX-Nano[J]. Journal of South China Agricultural University, 2023, 44(4): 593-603. DOI: 10.7671/j.issn.1001-411X.202207039

    基于改进YOLOX-Nano的农作物叶片病害检测与识别方法

    Detection and identification of crop leaf diseases based on improved YOLOX-Nano

    • 摘要:
      目的 实现精确迅速的农作物病害检测,减少人工诊断成本,降低病害带来的农作物产量和品质影响。
      方法 根据对农作物病害和病斑特征的分析,提出一种基于卷积注意力机制改进的YOLOX-Nano智能检测与识别模型,该模型采用CSPDarkNet作为主干网络,将卷积注意力模块CBAM引入到YOLOX-Nano网络结构的特征金字塔(Feature pyramid network,FPN)中,并在训练中引入Mixup数据增强方式,同时将分类的损失函数由二分类交叉熵损失函数(Binary cross entropy loss,BCE Loss)替换为焦点损失函数Focal Loss、回归损失函数由GIOU Loss替换为本文设计的CenterIOU Loss函数,采用迁移学习策略训练改进的YOLOX-Nano模型,以此提升农作物病害检测的精度。
      结果 改进后的YOLOX-Nano模型仅有0.98×106的参数量,在移动端测试单张图片检测时间约为0.187 s,平均识别精度达到99.56%。实践结果表明,其能快速有效地检测与识别苹果、玉米、葡萄、草莓、马铃薯和番茄等农作物的常见病害,且达到了精度与速度的平衡。
      结论 改进后的模型不仅对农作物叶片病害识别具有较高的精度和较快的检测速度,参数量和计算量较少,还易于部署在手机等移动端设备。该模型实现了在田间复杂环境对多种农作物病害精准定位与识别,对于指导早期农作物病害的防治具有十分重要的现实意义。

       

      Abstract:
      Objective To identify crop diseases accurately and quickly, reduce the cost of artificial diagnosis, and reduce the impacts of crop diseases on crop yield and quality.
      Method Based on the analysis of the characteristics of crop diseases and spots, an improved YOLOX-Nano intelligent detection and recognition model based on convolution attention mechanism was proposed. The model employed CSPDarkNet as the backbone network, added convolutional attention module CBAM to the feature pyramid network (FPN) of the YOLOX-Nano network structure, and then introduced the mixup data enhancement method in the training. At the same time, the classification loss function was replaced by the binary cross entropy loss function (BCE Loss) with the focus loss function, the regression loss function of GIOU Loss was replaced by the CenterIOU Loss function designed in this paper, and a transfer learning strategy was also used to train the modified YOLOX-Nano model so as to improve the accuracy of crop disease detection.
      Result The improved YOLOX-Nano model had parameters of 0.98×106, and the detection time of a single sheet was about 0.187 s at the mobile end, with a mean average precision of 99.56%. The practical results of introducing this method into mobile terminal deployment showed that it could quickly and effectively identify common diseases of crops such as apples, corns, grapes, strawberries, potatoes and tomatoes, and achieve the balance of accuracy and speed.
      Conclusion The improved model not only has higher accuracy and detection speed for crop leaf disease identification, but also has less parameters and calculation amount. The model was easy to be deployed on mobile devices such as mobile phones. In addition, the model achieves accurate positioning and identification of a variety of crop diseases in complex field environment, which is of great practical significance to guide the prevention and control of early crop diseases.

       

    /

    返回文章
    返回