The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B3-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2022, 501–508, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-501-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2022, 501–508, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B3-2022-501-2022
 
30 May 2022
30 May 2022

PERFORMANCE EVALUATION OF FUSION TECHNIQUES FOR CROSS-DOMAIN BUILDING ROOFTOP SEGMENTATION

H. Li1,2, J. Tian1, Y. Xie1, C. Li2, and P. Reinartz1 H. Li et al.
  • 1German Aerospace Center (DLR), Remote Sensing Technology Institute, D-82234 Wessling, Germany
  • 2Sichuan Surveying and Mapping Product Quality Test & Control Center, MNR, Chengdu 610041, China

Keywords: Building roof segmentation, Neural network, Self-training, HRNet, OCRNet, Swin Transfomer

Abstract. Convolutional Neural Networks have been widely introduced to building rooftop segmentation using satellite and aerial imagery. Preparing efficient training data is still among the critical issues on this topic. Therefore, adopting available annotated cross-domain multisource dataset is needed. This paper evaluates the performance of fusing the state-of-art deep learning neural network architectures for cross-domain building rooftop segmentation. We have selected three semantic image segmentation neural networks, including Swin transformer, OCRNet and HRNet. The predictions from these three neural networks are combined with majority voting, max value and union fusion techniques, a refined building rooftop segmentation mask is therefore delivered. The experiments on two benchmark datasets show that the proposed fusion techniques outperform single models and other state-of-art cross-domain segmentation approaches.