Simultaneous contextual classification of multitemporal and multiscale remote sensing imagery based on existing GIS data for training

基于现有GIS数据对多时相、多尺度遥感影像进行同步上下文分类进行训练

• 批准号: 290281376
• 负责人: Professor Dr.-Ing. Christian Heipke
• 金额: --
• 依托单位: Institut für Photogrammetrie und GeoInformation (IPI)
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2016
• 资助国家: 德国
• 起止时间: 2015-12-31 至 2019-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/290281376?language=en
• 关键词: Simultaneous; contextual; classification; multitemporal; multiscale

It is the goal of the proposed project to develop a novel methodology for the supervised context-based classification of multitemporal and multiscale remote sensing imagery without any manually labelled training data. The main scientific contribution is the development of new training methods that are tolerant to label noise, i.e., to a considerable amount of training samples with erroneous class labels. Using these methods it should become possible to use existing land cover (LC) data to derive class labels to be used for training for all pixels of an image to be classified. Rather than using sparse hand-labelled training data, we propose using an abundance of training data generated automatically, along with methods that can deal with the inevitable errors in these data. The mathematical framework for the proposed methodology is given by Conditional Random Fields (CRF). We will build a CRF that can classify data from multiple epochs and having different geometrical resolutions simultaneously, considering the fact that LC data at multiple resolutions will be characterised by different class structures. We rely on the existence of both, global, regional and local LC data sets to derive training data. We will develop new probabilistic approaches for considering label noise in training in order to obtain not only the parameters of the classifiers linking the unknown class labels of the CRF with the data, but also the parameters linking the images at different epochs with each other. As an important contribution we will consider the fact that errors in LC data are spatially correlated. The suggested project constitutes the first application of the principles of label-noise tolerant training procedures in the context of graph-based image classification, and one of the most general techniques for considering interactions between objects modelled at different semantic levels of detail. As a consequence, it should become possible to cut the costs for the update of global or regional and local LC data sets, e.g. by using cheap imagery of low resolution to get hints for changes in the high-resolution data. The new methodology is evaluated on real data with a reference that was generated manually. In the frame of an existing Memorandum of Understanding with the National Geomatics Center of China (NGCC) we will investigate the methodology in different test sites in Germany and China. We will use the global land cover data set GLC30 with 30 m geometrical resolution, developed by NGCC and available free of charge, as the coarse-resolution data set in our test cases. The high-resolution data sets we will use are those from the German Survey Authorities and NGCC, respectively.

该项目的目的是开发一种新的方法，用于基于上下文的多阶段和多尺度遥感图像的分类，而无需任何手动标记的培训数据。主要的科学贡献是开发新的训练方法，这些方法耐受标签噪声，即对具有错误类标签的大量训练样本。使用这些方法，应该有可能使用现有的土地覆盖（LC）数据来得出用于培训的班级标签，以用于分类的图像的所有像素。我们建议使用自动生成的大量培训数据以及可以处理这些数据中不可避免的错误的方法，而不是使用稀疏的手工训练数据。提出方法的数学框架由条件随机场（CRF）给出。我们将构建一个CRF，可以从多个时期分类数据，并同时具有不同的几何分辨率，考虑到多个分辨率的LC数据将以不同的类结构为特征。我们依靠全球，区域和本地LC数据集的存在来得出培训数据。我们将开发新的概率方法来考虑训练中的标签噪声，以便不仅获得将CRF的未知类标签与数据联系起来的分类器的参数，还可以获得将图像在不同时期链接的参数。作为重要的贡献，我们将考虑以下事实：LC数据中的错误在空间上相关。建议的项目构成了在基于图的图像分类的背景下的标签 - 噪声耐受训练程序原理的首次应用，也是考虑以不同语义级别模型的对象之间相互作用的最通用技术之一。结果，应该有可能削减更新全球或区域和本地LC数据集的成本，例如通过使用低分辨率的廉价图像来获取更改高分辨率数据的提示。在实际数据上评估新方法，并用手动生成的参考。在中国国家地理中心（NGCC）的现有谅解备忘录中，我们将研究德国和中国不同测试地点的方法。我们将使用由NGCC开发的30 m几何分辨率的全球土地覆盖数据集GLC30，并免费提供，作为我们测试用例中的粗分辨率数据集。我们将使用的高分辨率数据集分别来自德国调查当局和NGCC。

项目成果

Classification Under Label Noise Based on Outdated Maps

基于过时地图的标签噪声下的分类

• DOI: 10.5194/isprs-annals-iv-1-w1-215-2017
• 发表时间: 2017
• 期刊: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
• 作者: Rottensteiner;Heipke
• 通讯作者: Heipke

Multitemporal Classification Under Label Noise Based on Outdated Maps

基于过时地图的标签噪声下的多时相分类

• DOI: 10.14358/pers.84.5.263
• 发表时间: 2018
• 期刊: Photogrammetric Engineering and Remote Sensing
• 影响因子: 1.3
• 作者: Rottensteiner;Alobeid;Heipke
• 通讯作者: Heipke

AUTOMATIC CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGERY – ACASE STUDY FOR URBAN AREAS IN THE KINGDOM OF SAUDI ARABIA

高分辨率卫星图像的自动分类——沙特阿拉伯王国城市地区的案例研究

• DOI: 10.5194/isprs-archives-xlii-1-w1-11-2017
• 发表时间: 2017
• 期刊: ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
• 作者: Alrajhi;Alobeid;Heipke C.
• 通讯作者: Heipke C.

A label noise tolerant random forest for the classification of remote sensing data based on outdated maps for training

• DOI: 10.1016/j.cviu.2019.07.002
• 发表时间: 2019-11
• 期刊: Comput. Vis. Image Underst.
• 作者: Alina E. Maas;F. Rottensteiner;C. Heipke

USING LABEL NOISE ROBUST LOGISTIC REGRESSION FOR AUTOMATED UPDATING OF TOPOGRAPHIC GEOSPATIAL DATABASES

使用标签噪声鲁棒逻辑回归进行地形地理空间数据库的自动更新

• DOI: 10.5194/isprs-annals-iii-7-133-2016
• 发表时间: 2016
• 期刊: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
• 作者: Rottensteiner;Heipke
• 通讯作者: Heipke