Buildings Detection in VHR SAR Images Using Fully Convolution Neural Networks
Buildings Detection in VHR SAR Images Using Fully Convolution Neural Networks
复制标题
DOI：
10.1109/tgrs.2018.2864716
复制
发表时间：
2018-08
影响因子：
8.2
通讯作者：
M. Shahzad;Michael Maurer;F. Fraundorfer;Yuanyuan Wang;Xiaoxiang Zhu
中科院分区：
文献类型：
--
作者：
M. Shahzad;Michael Maurer;F. Fraundorfer;Yuanyuan Wang;Xiaoxiang Zhu
本文解决了在极高分辨率（VHR）合成孔径雷达（SAR）图像中自动检测人造结构（尤其是建筑物）的高度挑战性问题。在此背景下，本文有两个主要贡献。首先，它提出了一种新颖且通用的工作流程，该工作流程首先借助辅助信息（即使用公开可用的二维建筑足迹或采用光学图像分类方案）将星载 SAR 层析成像 (TomoSAR) 点云（通过使用称为 TomoSAR 的先进干涉技术处理 VHR SAR 图像堆栈生成）分类为建筑物和非建筑物，然后将提取的建筑点反投影到 SAR 成像坐标上，以生成自动标记的大规模基准（建筑物/非建筑物）SAR 数据集。其次，这些标记数据集（即建筑掩模）已用于构建和训练最先进的深度全卷积神经网络，并附加条件随机场（表示为循环神经网络）以检测单个 VHR SAR 图像中的建筑区域。这种级联结构已成功应用于计算机视觉和遥感领域的光学图像分类，但据我们所知，尚未应用于SAR图像。建筑物检测的结果通过 TerraSAR-X VHR 聚光 SAR 图像进行说明和验证，该图像覆盖约 39 km 2（几乎整个柏林市），平均像素精度约为 93.84%。
This paper addresses the highly challenging problem of automatically detecting man-made structures especially buildings in very high-resolution (VHR) synthetic aperture radar (SAR) images. In this context, this paper has two major contributions. First, it presents a novel and generic workflow that initially classifies the spaceborne SAR tomography (TomoSAR) point clouds—generated by processing VHR SAR image stacks using advanced interferometric techniques known as TomoSAR—into buildings and nonbuildings with the aid of auxiliary information (i.e., either using openly available 2-D building footprints or adopting an optical image classification scheme) and later back project the extracted building points onto the SAR imaging coordinates to produce automatic large-scale benchmark labeled (buildings/nonbuildings) SAR data sets. Second, these labeled data sets (i.e., building masks) have been utilized to construct and train the state-of-the-art deep fully convolution neural networks with an additional conditional random field represented as a recurrent neural network to detect building regions in a single VHR SAR image. Such a cascaded formation has been successfully employed in computer vision and remote sensing fields for optical image classification but, to our knowledge, has not been applied to SAR images. The results of the building detection are illustrated and validated over a TerraSAR-X VHR spotlight SAR image covering approximately 39 km 2—almost the whole city of Berlin— with the mean pixel accuracies of around 93.84%.