基于深度卷积神经网络的水稻田杂草识别研究

    Research on paddy weed recognition based on deep convolutional neural network

    • 摘要:
      目的  利用深度卷积神经网络对水稻田杂草进行准确、高效、无损识别,得出最优的网络模型,为水稻田种植管理以及无人机变量喷施提供理论依据。
      方法  以水稻田杂草为主要研究对象,利用CCD感光相机采集杂草图像样本,构建水稻田杂草数据集(PFMW)。利用多种结构的深度卷积神经网络对PFMW数据集进行特征的自动提取,并进行建模与试验。
      结果  在各深度模型对比试验中,VGG16模型取得了最高精度,其在鬼针草、鹅肠草、莲子草、千金子、鳢肠和澎蜞菊6种杂草中的F值分别为0.957、0.931、0.955、0.955、0.923和0.992,其平均F值为0.954。在所设置的深度模型优化器试验中,VGG16-SGD模型取得了最高精度,其在上述6种杂草中的F值分别为0.987、0.974、0.965、0.967、0.989和0.982,其平均F值为0.977。在PFMW数据集的样本类别数量均衡试验中,无失衡杂草数据集训练出来的VGG16深度模型的准确率为0.900,而16.7%、33.3%和66.6%类别失衡的数据集训练的模型准确率分别为0.888、0.866和0.845。
      结论  利用机器视觉能够准确识别水稻田杂草,这对于促进水稻田精细化耕作以及无人机变量喷施等方面具有重要意义,可以有效地协助农业种植过程中的杂草防治工作。

       

      Abstract:
      Objective  To accurately, efficiently and non-destructively identify the weeds in rice field using deep convolutional neural network, obtain the optimal network model, and provide a theoretical basis for rice field planting management and variable drone spraying.
      Method  The weeds in rice field were taken as the main research object, and weed image samples were collected by CCD photosensitive camera to construct weed data set (PFMW) in rice field. The deep convolutional neural network with multiple structures was used to automatically extract the features of the PFMW data set, and then to model and test.
      Result  VGG16 model achieved the highest precision among all the deep learning models, the F values in Bidens, Goose Starwort, Gomphrena, Sprangle, Eclipta, Wedelia were 0.957, 0.931, 0.955, 0.955, 0.923 and 0.992 respectively, and the average F value was 0.954. The VGG16-SGD model achieved the highest precision in setted deep model optimizer experiments, the F values in each weed mentioned above were 0.987, 0.974, 0.965, 0.967, 0.989 and 0.982 respectively, and the average F value was 0.977. In the equilibrium experiments of sample category quantity in the dataset, the accuracy of the VGG16 model trained by the balanced weed dataset was 0.900, while those of the models trained by the 16.7%, 33.3% and 66.6% category imbalance dataset were 0.888, 0.866 and 0.845 respectively.
      Conclusion  The machine vision and other advanced technologies can accurately identify weeds in rice field. It is of great significance for promoting fine cultivation of rice field and variable drone spraying, etc., and the technology can effectively assist weed control in the process of agricultural planting.

       

    /

    返回文章
    返回