MDAS: A New Multimodal Benchmark Dataset for Remote Sensing

In Earth observation, multimodal data fusion is an intuitive strategy to break the limitation of individual data. Complementary physical contents of data sources allow comprehensive and precise information retrieve. Future applications will have many options on data sources. Such privilege can be beneficial only if algorithms are ready to work with various data sources. However, current data fusion studies mostly focus on the fusion of two data sources. Thus, we provide the community a benchmark multimodal data set, MDAS, for the city of Augsburg, Germany. MDAS includes synthetic aperture radar (SAR) data, multispectral image, hyperspectral image, digital surface model (DSM), and geographic information system (GIS) data. All these data are collected on the same date, 7th May 2018. MDAS is a new benchmark data set that provides researchers rich options on data selections. We run experiments for three typical remote sensing applications, namely, resolution enhancement, spectral unmixing, and land cover classification, on MDAS data set. Our experiments demonstrate the performance of representative state-of-the-art algorithms whose outcomes can sever as baselines for further studies

在地球观测领域，多模态数据融合是突破单一数据模态局限性的直观有效策略。各数据源具备互补的物理内涵，可实现全面且精准的信息提取。未来的应用场景将拥有丰富的数据源选择空间，唯有算法能够适配多类数据源，这一优势才能得以充分发挥。然而，当前的数据融合研究大多仅聚焦于双数据源融合场景。为此，我们为学界构建了面向德国奥格斯堡市的基准多模态数据集MDAS。该数据集包含合成孔径雷达（Synthetic Aperture Radar, SAR）数据、多光谱影像、高光谱影像、数字表面模型（Digital Surface Model, DSM）以及地理信息系统（Geographic Information System, GIS）数据，所有数据均采集于2018年5月7日。MDAS作为一款新型基准数据集，为研究者提供了丰富的数据选择维度。我们基于MDAS数据集开展了三类典型遥感应用实验，分别为分辨率增强、光谱解混以及土地覆盖分类。实验验证了多款代表性当前最优（state-of-the-art）算法的性能，其结果可作为后续研究的基准参照。

搜集汇总

背景与挑战

背景概述

MDAS是一个多模态遥感基准数据集，包含SAR、多光谱/高光谱图像、DSM和GIS等多种同步采集的数据源，覆盖德国奥格斯堡地区，主要用于支持遥感数据融合算法的研究和评估。