Volume IV-4 | Copyright
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., IV-4, 187-192, 2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  19 Sep 2018

19 Sep 2018


C. Sebastian1, B. Boom2, T. van Lankveld2, E. Bondarev1, and P. H. N. De With1 C. Sebastian et al.
  • 1Eindhoven University of Technology, Eindhoven, The Netherlands
  • 2Cyclomedia B.V., Zaltbommel, The Netherlands

Keywords: bootstrapping, deep learning, building segmentation, aerial imagery

Abstract. Detection of buildings and other objects from aerial images has various applications in urban planning and map making. Automated building detection from aerial imagery is a challenging task, as it is prone to varying lighting conditions, shadows and occlusions. Convolutional Neural Networks (CNNs) are robust against some of these variations, although they fail to distinguish easy and difficult examples. We train a detection algorithm from RGB-D images to obtain a segmented mask by using the CNN architecture DenseNet. First, we improve the performance of the model by applying a statistical re-sampling technique called Bootstrapping and demonstrate that more informative examples are retained. Second, the proposed method outperforms the non-bootstrapped version by utilizing only one-sixth of the original training data and it obtains a precision-recall break-even of 95.10% on our aerial imagery dataset.

Download & links