Volume IV-2
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2, 177-184, 2018
https://doi.org/10.5194/isprs-annals-IV-2-177-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-2, 177-184, 2018
https://doi.org/10.5194/isprs-annals-IV-2-177-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  28 May 2018

28 May 2018

NEURAL NETWORKS FOR THE CLASSIFICATION OF BUILDING USE FROM STREET-VIEW IMAGERY

D. Laupheimer1, P. Tutzauer1, N. Haala1, and M. Spicker2 D. Laupheimer et al.
  • 1Institute for Photogrammetry, University of Stuttgart, Germany
  • 2Visual Computing Group, University of Konstanz, Germany

Keywords: Urban Data, Image Classification, Convolutional Neural Networks, Feature Learning, Class Activation Maps

Abstract. Within this paper we propose an end-to-end approach for classifying terrestrial images of building facades into five different utility classes (commercial, hybrid, residential, specialUse, underConstruction) by using Convolutional Neural Networks (CNNs). For our examples we use images provided by Google Street View. These images are automatically linked to a coarse city model, including the outlines of the buildings as well as their respective use classes. By these means an extensive dataset is available for training and evaluation of our Deep Learning pipeline. The paper describes the implemented end-to-end approach for classifying street-level images of building facades and discusses our experiments with various CNNs. In addition to the classification results, so-called Class Activation Maps (CAMs) are evaluated. These maps give further insights into decisive facade parts that are learned as features during the training process. Furthermore, they can be used for the generation of abstract presentations which facilitate the comprehension of semantic image content. The abstract representations are a result of the stippling method, an importance-based image rendering.