Logo Leibniz Universität Hannover
Logo: Institut für Photogrammetrie und Geoinformatik/Leibniz Universität Hannover
Logo Leibniz Universität Hannover
Logo: Institut für Photogrammetrie und Geoinformatik/Leibniz Universität Hannover
  • Zielgruppen
  • Suche

Investigation and evaluation on automatic methodologies for updating and verification of geospatial databases

Bearbeitung:C. Yang, P. Humburg
Laufzeit:seit 2017
Förderung durch:LGLN¹, LVermGeo², LaiV-MV³

Part I: update and verify land cover/land use database

Geospatial land use databases contain important information with high benefit for several users, especially in the field of urban management and planning. The number of possible applications of such data increases with a higher level of detail, both in terms of the size of geometrical entities as well as the diversity of land use classes. Because of the fast changes of the land use due to urban growth and land use conversion, such geospatial databases become outdated quickly. This observation motivates the development of an automatic update process for large-scale land use databases. In contrast to land use, which reveals the socio-economic function of a piece of land (e.g. residential, agricultural), land cover describes the physical material of the earth’s surface (e.g. grass, asphalt). The both terms of land cover and land use relate to themselves, which means, a land use object could contain many different land cover elements to form complex structures and meanwhile, a specific land cover can be a part of different land use objects. Thus, land cover and land use classification based on remote sensing data are tasks that pursue different objectives. 

Generally speaking, the assignment of class labels to image sites is land cover classification, whereas the assignment of labels to larger spatial entities, typical functional units represented by polygons, is the goal of land use classification. In our project, high-resolution aerial images are the data source for extracting the land use and land cover information, and we employ deep convolutional neural networks (CNN) to achieve these both goals with high quality results. Firstly, we do classification of land cover (semantic segmentation), and then use the generated land cover map as well as the original imageries to do classification of land use. Figure 1 shows a flowchart of this process:

Fig. 1: Classification of land cover and land use


Part II: update and verify road database

Similar to the land use and land cover database, road database also become outdated quickly, for a number of reasons. New roads may be constructed, old roads may be demolished, or existing roads may be altered, leading to a discrepancy between the real world and the dataset. Additionally, the existing databases for road data, ALKIS and ATKIS, represent the roads in different ways. While ALKIS represents them as areas, usually without storing topographic elements, such as the middle axis, ATKIS stores the roads as lines with attributes, such as the width. Furthermore, as a result of this difference, the existing roads in both datasets do not always match. Therefore, these datasets should be updated and adjusted, resulting in a current and corresponding representation of the road network. In order to achieve that, the goal of this project is the automatic creation of a complete and correct road network, consisting of two sub-goals: the verification of roads in places where the data is still up-to-date, and the proposal of new roads in places where it is not.

This above formulated goal corresponds to a classification, in which all road areas should be labeled as such. In this project, a convolutional neural network (CNN) is employed to achieve this, using aerial images as the main input, and the existing road databases as ground truth.



  • ¹ Landesamt für Geoinformation und Landesvermessung Niedersachsen
  • ² Landesamt für Vermessung und Geoinformation Schleswig Holstein
  • ³ Landesamt für innere Verwaltung Mecklenburg-Vorpommern


Yang, C.; Rottensteiner, F.; Heipke, C. (2018): Classification of land cover and land use based on convolution neural networks. In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences IV-3, pp. 251-258.

back to list