Hourglass-ShapeNetwork Based Semantic Segmentation for High Resolution Aerial Imagery

Yu Liu, Minh Duc Nguyen, Nikolaos Deligiannis, Wenrui Ding, Adrian Munteanu

Research output: Contribution to journalArticlepeer-review

108 Citations (Scopus)


A new convolution neural network (CNN) architecture for semantic segmentation of high resolution aerial imagery is proposed in this paper. The proposed architecture follows an hourglass-shaped network (HSN) design being structured into encoding and decoding stages. By taking advantage of recent advances in CNN designs, we use the composed inception module to replace common convolutional layers, providing the network with multi-scale receptive areas with rich context. Additionally, in order to reduce spatial ambiguities in the up-sampling stage, skip connections with residual units are also employed to feed forward encoding-stage information directly to the decoder. Moreover, overlap inference is employed to alleviate boundary effects occurring when high resolution images are inferred from small-sized patches. Finally, we also propose a post-processing method based on weighted belief propagation to visually enhance the classification results. Extensive experiments based on the Vaihingen and Potsdam datasets demonstrate that the proposed architectures outperform three reference state-of-the-art network designs both numerically and visually.
Original languageEnglish
Article number522
Number of pages24
JournalRemote Sensing
Issue number6
Publication statusPublished - 25 May 2017


  • semantic labeling
  • convolutional neural networks
  • remote sensing
  • deep learning
  • aerial images

Cite this