TY - GEN
T1 - CONDITIONAL GIS-AWARE NETWORK FOR INDIVIDUAL BUILDING SEGMENTATION IN A VHR SAR IMAGE
AU - Sun, Yao
AU - Hua, Yuansheng
AU - Mou, Lichao
AU - Zhu, Xiao Xiang
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - In this paper, we propose a network for individual building segmentation from a single VHR SAR image. The proposed network employs building footprints from GIS data in learning multi-level visual features to predict building masks in the SAR image. Experimental results over Berlin show that the proposed network effectively brings improvements with variant backbones. In addition, we propose an approach for generating building labels from an accurate digital elevation model (DEM), which can be used to generate large-scale SAR image datasets.
AB - In this paper, we propose a network for individual building segmentation from a single VHR SAR image. The proposed network employs building footprints from GIS data in learning multi-level visual features to predict building masks in the SAR image. Experimental results over Berlin show that the proposed network effectively brings improvements with variant backbones. In addition, we propose an approach for generating building labels from an accurate digital elevation model (DEM), which can be used to generate large-scale SAR image datasets.
KW - Building segmentation
KW - Deep convolutional neural network (CNN)
KW - GIS
KW - Large-scale
KW - Synthetic aperture radar (SAR)
UR - https://www.scopus.com/pages/publications/85126034812
U2 - 10.1109/IGARSS47720.2021.9553135
DO - 10.1109/IGARSS47720.2021.9553135
M3 - Conference contribution
AN - SCOPUS:85126034812
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 4532
EP - 4535
BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Y2 - 12 July 2021 through 16 July 2021
ER -