Volume XLII-3
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3, 985-991, 2018
https://doi.org/10.5194/isprs-archives-XLII-3-985-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3, 985-991, 2018
https://doi.org/10.5194/isprs-archives-XLII-3-985-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  30 Apr 2018

30 Apr 2018

FULLY CONVOLUTIONAL NETWORK BASED SHADOW EXTRACTION FROM GF-2 IMAGERY

Z. Li1,2, G. Cai1,2, and H. Ren1,2 Z. Li et al.
  • 1School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing, China
  • 2The Key Laboratory for Urban Geomatics of National Administration of Surveying, Mapping and Geoinformation, Beijing University of Civil Engineeringand Architecture, Beijing, 100044, China

Keywords: Fully Convolutional Network, Shadow Extraction, Deep Learning, GF-2, Building Shadows

Abstract. There are many shadows on the high spatial resolution satellite images, especially in the urban areas. Although shadows on imagery severely affect the information extraction of land cover or land use, they provide auxiliary information for building extraction which is hard to achieve a satisfactory accuracy through image classification itself. This paper focused on the method of building shadow extraction by designing a fully convolutional network and training samples collected from GF-2 satellite imagery in the urban region of Changchun city. By means of spatial filtering and calculation of adjacent relationship along the sunlight direction, the small patches from vegetation or bridges have been eliminated from the preliminary extracted shadows. Finally, the building shadows were separated. The extracted building shadow information from the proposed method in this paper was compared with the results from the traditional object-oriented supervised classification algorihtms. It showed that the deep learning network approach can improve the accuracy to a large extent.