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 height retrieval from synthetic aperture radar (SAR) imagery is ofgreat importance for urban applications, yet highly challenging owing to thecomplexity of SAR data. This paper addresses the issue of building heightretrieval in large-scale urban areas from a single TerraSAR-X spotlight orstripmap image. Based on the radar viewing geometry, we propose that thisproblem can be formulated as a bounding box regression problem and thereforeallows for integrating height data from multiple data sources in generatingground truth on a larger scale. We introduce building footprints fromgeographic information system (GIS) data as complementary information andpropose a bounding box regression network that exploits the locationrelationship between a building's footprint and its bounding box, allowing forfast computation. This is important for large-scale applications. The method isvalidated on four urban data sets using TerraSAR-X images in bothhigh-resolution spotlight and stripmap modes. Experimental results show thatthe proposed network can reduce the computation cost significantly whilekeeping the height accuracy of individual buildings compared to a Faster R-CNNbased method. Moreover, we investigate the impact of inaccurate GIS data on ourproposed network, and this study shows that the bounding box regression networkis robust against positioning errors in GIS data. The proposed method has greatpotential to be applied to regional or even global scales.

Large-scale Building Height Retrieval from Single SAR Imagery based on Bounding Box Regression Networks