Spot spraying POST herbicides is an effective approach to reduce herbicide input and weed control cost. Machine vision detection of grass or grass-like weeds in turfgrass systems is a challenging task due to the similarity in plant morphology. In this work, we explored the feasibility of using image classification with deep convolutional neural networks (DCNN), including AlexNet, GoogLeNet, and VGGNet, for detection of crabgrass species (Digitaria spp.), doveweed [Murdannia nudiflora (L.) Brenan], dallisgrass (Paspalum dilatatum Poir.), and tropical signalgrass [Urochloa distachya (L.) T.Q. Nguyen] in bermudagrass [Cynodon dactylon (L.) Pers.]. VGGNet generally outperformed AlexNet and GoogLeNet in detecting selected grassy weeds. For detection of P. dilatatum, VGGNet achieved high F1 scores (≥0.97) and recall values (≥0.99). A single VGGNet model exhibited high F1 scores (≥0.93) and recall values (1.00) that reliably detected Digitaria spp., M. nudiflora, P. dilatatum, and U. distachya. Low weed density reduced the recall values of AlexNet at detecting all weed species and GoogLeNet at detecting Digitaria spp. In comparison, VGGNet achieved excellent performances (overall accuracy = 1.00) at detecting all weed species in both high and low weed-density scenarios. These results demonstrate the feasibility of using DCNN for detection of grass or grass-like weeds in turfgrass systems.

中文翻译：

---

用深度卷积神经网络检测百慕大草中的杂草

点喷POST除草剂是减少除草剂投入和杂草控制成本的有效方法。由于植物形态学的相似性，机器视觉检测草坪系统中的草或类草杂草是一项具有挑战性的任务。在这项工作中，我们探索了使用包含 AlexNet、GoogLeNet 和 VGGNet 在内的深度卷积神经网络 (DCNN) 进行图像分类来检测马唐物种的可行性。数码管spp.), 鸽子草 [裸花海棠(L.) Brenan], dallisgrass (雀稗Poir.) 和热带信号草 [乌龙草(L.) TQ Nguyen] 在百慕大草 [狗牙根(L.) Pers.]。VGGNet 在检测选定的杂草方面通常优于 AlexNet 和 GoogLeNet。用于检测P. dilatatum，VGGNet 取得了较高的 F1 分数（≥0.97）和召回值（≥0.99）。单个 VGGNet 模型表现出高 F1 分数 (≥0.93) 和召回值 (1.00)，可以可靠地检测到数码管种，M. nudiflora,P. dilatatum， 和连翘. 低杂草密度降低了 AlexNet 在检测所有杂草时的召回值和 GoogLeNet 在检测时的召回值洋地黄属. 相比之下，VGGNet 在高杂草密度和低杂草密度场景中检测所有杂草物种时都取得了出色的性能（整体准确度 = 1.00）。这些结果证明了使用 DCNN 检测草坪系统中的草或类草杂草的可行性。