English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Building segmentation in high-resolution InSAR images is a challenging taskthat can be useful for large-scale surveillance. Although complex-valued deeplearning networks perform better than their real-valued counterparts forcomplex-valued SAR data, phase information is not retained throughout thenetwork, which causes a loss of information. This paper proposes a FullyComplex-valued, Fully Convolutional Multi-feature Fusion Network(FC2MFN) forbuilding semantic segmentation on InSAR images using a novel, fullycomplex-valued learning scheme. The network learns multi-scale features,performs multi-feature fusion, and has a complex-valued output. For theparticularity of complex-valued InSAR data, a new complex-valued pooling layeris proposed that compares complex numbers considering their magnitude andphase. This helps the network retain the phase information even through thepooling layer. Experimental results on the simulated InSAR dataset show thatFC2MFN achieves better results compared to other state-of-the-art methods interms of segmentation performance and model complexity.

Fully Complex-valued Fully Convolutional Multi-feature Fusion Network (FC2MFN) for Building Segmentation of InSAR images