Abstract

Building footprint maps are useful for urban planning, infrastructural development, population estimation and disaster management. With the availability of very-high resolution satellite imagery, remote sensing community is pursuing automatic techniques for extracting building footprints for cities with varried building types. Recently, CNNs (Convolutional Neural Network) have been successfully applied for extraction of building footprint from satellite imagery. In this paper, we propose a novel CNN architecture termed UNet-AP inspired by UNet and the concept of Atrous Spatial Pyramid Pooling, for automatic extraction of building footprint from very-high resolution satellite imagery. We demonstrate extraction of building footprints from Cartosat-2 series 4-band (Blue, Green, Red and Near-Infrared) multispectral satellite imagery, pan-sharpened using the panchromatic image with less than 1-meter resolution. We also compare the performance of our proposed architecture with baseline implementation of recently proposed UNet and SegNet architectures. We present a comparative assessment of the architecture performance across different types of urban settlement classes such as dense built-up areas, slums and isolated buildings. We demonstrate that our proposed architecture outperforms SegNet and UNet in terms of overall mean intersection over union (0.75 vs 0.70 and 0.68 for UNet and SegNet respectively) and delivers consistent improvement across all three settlement classes.

摘要

建筑足迹图对城市规划、基础设施发展、人口估计和灾害管理很有用。随着超高分辨率卫星图像的可用性，遥感界正在寻求自动技术来提取具有不同建筑类型的城市的建筑足迹。最近，CNN（卷积神经网络）已成功应用于从卫星图像中提取建筑物足迹。在本文中，我们提出了一种新的 CNN 架构，称为 UNet-AP，其灵感来自于 UNet 和 Atrous Spatial Pyramid Pooling 的概念，用于从超高分辨率卫星图像中自动提取建筑物足迹。我们展示了从 Cartosat-2 系列 4 波段（蓝色、绿色、红色和近红外）多光谱卫星图像中提取建筑物足迹，使用分辨率小于 1 米的全色图像进行全色锐化。我们还将我们提出的架构的性能与最近提出的 UNet 和 SegNet 架构的基线实现进行了比较。我们对不同类型的城市住区类别（例如密集的建成区、贫民窟和孤立的建筑物）的建筑性能进行了比较评估。我们证明了我们提出的架构在联合上的总体平均交集方面优于 SegNet 和 UNet（UNet 和 SegNet 分别为 0.75 vs 0.70 和 0.68），并且在所有三个结算类别中都提供了一致的改进。我们对不同类型的城市住区类别（例如密集的建成区、贫民窟和孤立的建筑物）的建筑性能进行了比较评估。我们证明了我们提出的架构在联合上的总体平均交集方面优于 SegNet 和 UNet（UNet 和 SegNet 分别为 0.75 vs 0.70 和 0.68），并且在所有三个结算类别中都提供了一致的改进。我们对不同类型的城市住区类别（例如密集的建成区、贫民窟和孤立的建筑物）的建筑性能进行了比较评估。我们证明了我们提出的架构在联合上的总体平均交集方面优于 SegNet 和 UNet（UNet 和 SegNet 分别为 0.75 vs 0.70 和 0.68），并且在所有三个结算类别中都提供了一致的改进。