TY - GEN
T1 - END-TO-END SEMANTIC SEGMENTATION AND BOUNDARY REGULARIZATION OF BUILDINGS FROM SATELLITE IMAGERY
AU - Li, Qingyu
AU - Zorzi, Stefano
AU - Shi, Yilei
AU - Fraundorfer, Friedrich
AU - Zhu, Xiao Xiang
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Building footprint generation is a vital task of satellite imagery interpretation. However, the segmentation masks of buildings obtained by existing semantic segmentation networks often have blurred boundaries and irregular shapes. In this research, we propose a new boundary regularization network for building footprint generation in satellite images. More specifically, we consider semantic segmentation and boundary regularization in an end-to-end generative adversarial network (GAN). The learned building footprints are regularized by the interplay between the generator and discriminator. By doing so, the straight boundaries and geometric details of the building could be preserved. Experiments are conducted on a collected dataset of Planetscope satellite imagery (spatial resolution: 4.77 m/pixel). Our approach is much superior to the state-of-the-art methods in both quantitative and qualitative results.
AB - Building footprint generation is a vital task of satellite imagery interpretation. However, the segmentation masks of buildings obtained by existing semantic segmentation networks often have blurred boundaries and irregular shapes. In this research, we propose a new boundary regularization network for building footprint generation in satellite images. More specifically, we consider semantic segmentation and boundary regularization in an end-to-end generative adversarial network (GAN). The learned building footprints are regularized by the interplay between the generator and discriminator. By doing so, the straight boundaries and geometric details of the building could be preserved. Experiments are conducted on a collected dataset of Planetscope satellite imagery (spatial resolution: 4.77 m/pixel). Our approach is much superior to the state-of-the-art methods in both quantitative and qualitative results.
KW - Boundary regularization
KW - Building
KW - Generative adversarial network
KW - Satellite imagery
KW - Semantic segmentation
UR - http://www.scopus.com/inward/record.url?scp=85126019562&partnerID=8YFLogxK
U2 - 10.1109/IGARSS47720.2021.9555147
DO - 10.1109/IGARSS47720.2021.9555147
M3 - Conference contribution
AN - SCOPUS:85126019562
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 2508
EP - 2511
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 -