Journal
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
Volume 57, Issue 2, Pages 1100-1116Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2018.2864716
Keywords
Building detection; fully convolution neural networks (CNNs); OpenStreetMap (OSM); synthetic aperture radar (SAR); SAR tomography (TomoSAR); TerraSAR-X/TanDEM-X
Categories
Funding
- European Research Council through the European Union's Horizon 2020 Research and Innovation Program (Acronym: So2Sat) [ERC-2016-StG-714087]
- Helmholtz Association through the Framework of the Young Investigators Group SiPEO [VH-NG-1018]
Ask authors/readers for more resources
This paper addresses the highly challenging problem of automatically detecting man-made structures especially buildings in very high-resolution (VHR) synthetic aperture radar (SAR) images. In this context, this paper has two major contributions. First, it presents a novel and generic workflow that initially classifies the spaceborne SAR tomography (TomoSAR) point clouds-generated by processing VHR SAR image stacks using advanced interferometric techniques known as TomoSAR-into buildings and nonbuildings with the aid of auxiliary information (i.e., either using openly available 2-D building footprints or adopting an optical image classification scheme) and later back project the extracted building points onto the SAR imaging coordinates to produce automatic largescale benchmark labeled (buildings/nonbuildings) SAR data sets. Second, these labeled data sets (i.e., building masks) have been utilized to construct and train the state-of-the-art deep fully convolution neural networks with an additional conditional random field represented as a recurrent neural network to detect building regions in a single VHR SAR image. Such a cascaded formation has been successfully employed in computer vision and remote sensing fields for optical image classification but, to our knowledge, has not been applied to SAR images. The results of the building detection are illustrated and validated over a TerraSAR-X VHR spotlight SAR image covering approximately 39 km(2)-almost the whole city of Berlin-with the mean pixel accuracies of around 93.84%.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available