Jin Xiaojun, Bagavathiannan Muthukumar, Maity Aniruddha, Chen Yong, Yu Jialin
College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing, 210037, Jiangsu, China.
Peking University Institute of Advanced Agricultural Sciences, Weifang, 261325, Shandong, China.
Plant Methods. 2022 Jul 25;18(1):94. doi: 10.1186/s13007-022-00929-4.
Precision spraying of postemergence herbicides according to the herbicide weed control spectrum can substantially reduce herbicide input. The objective of this research was to evaluate the effectiveness of using deep convolutional neural networks (DCNNs) for detecting and discriminating weeds growing in turfgrass based on their susceptibility to ACCase-inhibiting and synthetic auxin herbicides.
GoogLeNet, MobileNet-v3, ShuffleNet-v2, and VGGNet were trained to discriminate the vegetation into three categories based on the herbicide weed control spectrum: weeds susceptible to ACCase-inhibiting herbicides, weeds susceptible to synthetic auxin herbicides, and turfgrass without weed infestation (no herbicide). ShuffleNet-v2 and VGGNet showed high overall accuracy (≥ 0.999) and F scores (≥ 0.998) in the validation and testing datasets to detect and discriminate weeds susceptible to ACCase-inhibiting and synthetic auxin herbicides. The inference time of ShuffleNet-v2 was similar to MobileNet-v3, but noticeably faster than GoogLeNet and VGGNet. ShuffleNet-v2 was the most efficient and reliable model among the neural networks evaluated.
These results demonstrated that the DCNNs trained based on the herbicide weed control spectrum could detect and discriminate weeds based on their susceptibility to selective herbicides, allowing the precision spraying of particular herbicides to susceptible weeds and thereby saving more herbicides. The proposed method can be used in a machine vision-based autonomous spot-spraying system of smart sprayers.
根据除草剂杂草防除谱精准喷施苗后除草剂可大幅减少除草剂用量。本研究的目的是评估使用深度卷积神经网络（DCNN）基于杂草对乙酰辅酶A羧化酶（ACCase）抑制型除草剂和合成生长素类除草剂的敏感性来检测和区分生长在草坪草中的杂草的有效性。
对GoogLeNet、MobileNet-v3、ShuffleNet-v2和VGGNet进行训练，以便根据除草剂杂草防除谱将植被分为三类：对ACCase抑制型除草剂敏感的杂草、对合成生长素类除草剂敏感的杂草以及无杂草侵染的草坪草（无需使用除草剂）。ShuffleNet-v2和VGGNet在验证数据集和测试数据集中检测和区分对ACCase抑制型除草剂和合成生长素类除草剂敏感的杂草时，显示出较高的总体准确率（≥0.999）和F分数（≥0.998）。ShuffleNet-v2的推理时间与MobileNet-v3相似，但明显快于GoogLeNet和VGGNet。在评估的神经网络中，ShuffleNet-v2是最有效且可靠的模型。
这些结果表明，基于除草剂杂草防除谱训练的DCNN能够根据杂草对选择性除草剂的敏感性来检测和区分杂草，从而实现对敏感杂草精准喷施特定除草剂，进而节省更多除草剂。所提出的方法可用于智能喷雾器基于机器视觉的自动精准点喷系统。
