User: Guest  Login
Author(s):
Mou, Lichao; Schmitt, M.; Wang, Yuanyuan; Zhu, Xiao Xiang
Title:
A {CNN} for the identification of corresponding patches in {SAR} and optical imagery of urban scenes
Abstract:
In this paper we propose a convolutional neural network (CNN), which allows to identify corresponding patches of very high resolution (VHR) optical and SAR imagery of complex urban scenes. Instead of a siamese architecture as conventionally used in CNNs designed for image matching, we resort to a pseudo-siamese configuration with no interconnection between the two streams for SAR and optical imagery. The network is trained with automatically generated training data and does not resort to any han...     »
Keywords:
Adaptive optics, automatically generated training data, convolutional neural network, geophysical image processing, hand-crafted features, image matching, image resolution, Integrated optics, multisensor matching procedure, neural nets, Optical distortion, optical imagery, Optical imaging, Optical interferometry, Optical sensors, pseudosiamese configuration, remote sensing by radar, SAR imagery, siamese architecture, Synthetic aperture radar, Three-dimensional displays, urban scenes, very high r...     »
Book / Congress title:
2017 {Joint} {Urban} {Remote} {Sensing} {Event} ({JURSE})
Year:
2017
Month:
mar
Pages:
1--4
Reviewed:
ja
Fulltext / DOI:
doi:10.1109/JURSE.2017.7924548
 BibTeX