Accurately mapping farmlands is important for precision agriculture practices. Unmanned aerial vehicles (UAV) embedded with multispectral cameras are commonly used to map plants in agricultural landscapes. However, separating plantation fields from the remaining objects in a multispectral scene is a difficult task for traditional algorithms. In this connection, deep learning methods that perform semantic segmentation could help improve the overall outcome. In this study, state-of-the-art deep learning methods to semantic segment citrus-trees in multispectral images were evaluated. For this purpose, a multispectral camera that operates at the green (530–570 nm), red (640–680 nm), red-edge (730–740 nm) and also near-infrared (770–810 nm) spectral regions was used. The performance of the following five state-of-the-art pixelwise methods were evaluated: fully convolutional network (FCN), U-Net, SegNet, dynamic dilated convolution network (DDCN) and DeepLabV3 + . The results indicated that the evaluated methods performed similarly in the proposed task, returning F1-Scores between 94.00% (FCN and U-Net) and 94.42% (DDCN). It was also determined the inference time needed per area and, although the DDCN method was slower, based on a qualitative analysis, it performed better in highly shadow-affected areas. This study demonstrated that the semantic segmentation of citrus orchards is highly achievable with deep neural networks. The state-of-the-art deep learning methods investigated here proved to be equally suitable to solve this task, providing fast solutions with inference time varying from 0.98 to 4.36 min per hectare. This approach could be incorporated into similar research, and contribute to decision-making and accurate mapping of plantation fields.

中文翻译：

---

使用深度神经网络和基于多光谱无人机的图像对柑橘果园进行语义分割

准确绘制农田地图对于精准农业实践非常重要。嵌入多光谱相机的无人机 (UAV) 通常用于绘制农业景观中的植物图。然而，对于传统算法来说，将种植园与多光谱场景中的剩余物体分离是一项艰巨的任务。在这方面，执行语义分割的深度学习方法可以帮助改善整体结果。在这项研究中，评估了在多光谱图像中对柑橘树进行语义分割的最先进的深度学习方法。为此，在绿色 (530–570 nm)、红色 (640–680 nm)、红边 (730–740 nm) 和近红外 (770–810 nm) 光谱区域运行的多光谱相机是用过的。评估了以下五种最先进的像素方法的性能：完全卷积网络 (FCN)、U-Net、SegNet、动态扩张卷积网络 (DDCN) 和 DeepLabV3+。结果表明，评估的方法在所提出的任务中表现相似，返回 F1-Scores 在 94.00%（FCN 和 U-Net）和 94.42%（DDCN）之间。它还确定了每个区域所需的推理时间，尽管 DDCN 方法较慢，但基于定性分析，它在受阴影影响的区域表现更好。这项研究表明，柑橘园的语义分割可以通过深度神经网络实现。事实证明，这里研究的最先进的深度学习方法同样适用于解决此任务，提供推理时间从 0.98 到 4 不等的快速解决方案。每公顷 36 分钟。这种方法可以被纳入类似的研究中，并有助于人工林地的决策和准确测绘。