Roof type selection based on patch-based classification using deep learning for high resolution satellite imagery

T. Partovi*, F. Fraundorfer, S. Azimi, D. Marmanis, P. Reinartz

*Korrespondierende/r Autor/-in für diese Arbeit

Publikation: Beitrag in einer FachzeitschriftArtikelBegutachtung

Abstract

3D building reconstruction from remote sensing image data from satellites is still an active research topic and very valuable for 3D city modelling. The roof model is the most important component to reconstruct the Level of Details 2 (LoD2) for a building in 3D modelling. While the general solution for roof modelling relies on the detailed cues (such as lines, corners and planes) extracted from a Digital Surface Model (DSM), the correct detection of the roof type and its modelling can fail due to low quality of the DSM generated by dense stereo matching. To reduce dependencies of roof modelling on DSMs, the pansharpened satellite images as a rich resource of information are used in addition. In this paper, two strategies are employed for roof type classification. In the first one, building roof types are classified in a state-of-the-art supervised pre-trained convolutional neural network (CNN) framework. In the second strategy, deep features from deep layers of different pre-trained CNN model are extracted and then an RBF kernel using SVM is employed to classify the building roof type. Based on roof complexity of the scene, a roof library including seven types of roofs is defined. A new semi-automatic method is proposed to generate training and test patches of each roof type in the library. Using the pre-trained CNN model does not only decrease the computation time for training significantly but also increases the classification accuracy.

Originalspracheenglisch
Seiten (von - bis)653-657
Seitenumfang5
FachzeitschriftThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Jahrgang42
Ausgabenummer1W1
DOIs
PublikationsstatusVeröffentlicht - 30 Mai 2017

ASJC Scopus subject areas

  • Information systems
  • Geografie, Planung und Entwicklung

Fingerprint

Untersuchen Sie die Forschungsthemen von „Roof type selection based on patch-based classification using deep learning for high resolution satellite imagery“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren