Accurate farmland segmentation is essential for modern agriculture and automated navigation. We propose an improved U-Net for farmland area segmentation. The wheat farmland data images were collected at the winter wheat experimental base of the Institute of Agricultural Economics and Information, Henan Academy of Agricultural Sciences. U-Net adopts the encoder–decoder structure and skips connection to achieve segmentation. The downsampling operation in the encoder stage weakens the detailed features. The semantic gap between the decoder and the encoder will cause the sparse wheat seedlings in the farmland cannot be captured. Based on the above problems, the improved U-Net uses a multiscale global attention module (MGA) in the bottleneck layer. MGA forms enhanced features by aggregating multiscale global context information and using an improved attention mechanism. An interaction mechanism (IM) is added between the decoder and the encoder. The encoder–decoder IM concatenates multiple attention units and fuses them with the original features on the encoder side to update the input features to the encoder. To lighten the model, we also define two multiplexed convolution kernel sequences in the code, which are shared by all encoders or decoders. The method proposed in this paper is evaluated on the farmland segmentation dataset. Significantly better segmentation results are achieved compared to classical models (U-Net, U-Net++, PSPNet, FPN, and DeepLabV3). In the case of obtaining similar segmentation results, with a smaller amount of parameters compared with State Of The Art (U-Net3+, ACSNet, PraNet, and CCBANet). We also use the farmland data provided by Sichuan Agricultural University for testing, the Dice is 93.88%, which has good generalization performance.

中文翻译：

---

无人机图像上改进 U-Net 的小麦农田分割

准确的农田分割对于现代农业和自动化导航至关重要。我们提出了一种改进的 U-Net 用于农田区域分割。小麦农田数据影像采集于河南省农业科学院农业经济与信息研究所冬小麦试验基地。U-Net采用encoder-decoder结构，跳过连接实现分割。编码器阶段的下采样操作削弱了细节特征。解码器和编码器之间的语义差距会导致农田中稀疏的小麦幼苗无法被捕获。基于上述问题，改进后的 U-Net 在瓶颈层使用了多尺度全局注意力模块（MGA）。MGA 通过聚合多尺度全局上下文信息并使用改进的注意力机制来形成增强的特征。在解码器和编码器之间增加了交互机制（IM）。编码器-解码器 IM 连接多个注意力单元，并将它们与编码器端的原始特征融合，以更新编码器的输入特征。为了减轻模型的重量，我们还在代码中定义了两个复用的卷积核序列，由所有编码器或解码器共享。本文提出的方法是在农田分割数据集上进行评估的。与经典模型（U-Net、U-Net++、PSPNet、FPN 和 DeepLabV3）相比，实现了明显更好的分割结果。在获得相似分割结果的情况下，与 State Of The Art (U-Net3+, ACSNet、PraNet 和 CCBANet）。我们还使用四川农业大学提供的农田数据进行测试，Dice 为 93.88%，具有良好的泛化性能。