Abstract. With the rapid increase of the world’s population, urban growth management and monitoring have become an important component in environmental, social, and economic terms. In general, automatic detection of buildings in urban areas from high-resolution satellite imagery has become an important issue. In recent years, the U-Net architecture has become one of the most popular convolutional neural networks in terms of pixel-based image segmentation. A new deep learning architecture has been developed by combining inception blocks with the convolutional layers of the original U-Net architecture to achieve remarkably high performance in building detection. First, the width of the network is increased by adding parallel filters of different sizes to the convolutional layers in the original U-Net model, and Inception UNet architecture is developed. For the proposed architecture, parallel layers were used only in feature extraction stage to reduce the number of parameters and computation time due to a large network size. In this context, performance comparisons were made with two different datasets. The results show that a significant improvement in F1 and kappa scores compared to the original U-Net was achieved using the proposed architecture, and model size is dramatically reduced according to Inception UNet-v1.

中文翻译：

---

改进的 U-Nets 与用于建筑物检测的初始块

摘要。随着世界人口的快速增长，城市增长管理和监测已成为环境、社会和经济方面的重要组成部分。总的来说，从高分辨率卫星图像中自动检测城市地区的建筑物已成为一个重要问题。近年来，在基于像素的图像分割方面，U-Net 架构已成为最流行的卷积神经网络之一。通过将初始块与原始 U-Net 架构的卷积层相结合，开发了一种新的深度学习架构，以在建筑物检测中实现非常高的性能。首先，通过在原始 U-Net 模型中的卷积层中添加不同大小的并行滤波器来增加网络的宽度，并开发了 Inception UNet 架构。对于所提出的架构，由于网络规模较大，并行层仅在特征提取阶段使用，以减少参数数量和计算时间。在这种情况下，对两个不同的数据集进行了性能比较。结果表明，与原始 U-Net 相比，使用所提出的架构实现了 F1 和 kappa 分数的显着提高，并且根据 Inception UNet-v1 显着减小了模型大小。