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

Understanding urban dynamics and promoting sustainable development requirescomprehensive insights about buildings. While geospatial artificialintelligence has advanced the extraction of such details from Earthobservational data, existing methods often suffer from computationalinefficiencies and inconsistencies when compiling unified building-relateddatasets for practical applications. To bridge this gap, we introduce theMulti-task Building Refiner (MT-BR), an adaptable neural network tailored forsimultaneous extraction of spatial and attributional building details fromhigh-resolution satellite imagery, exemplified by building rooftops, urbanfunctional types, and roof architectural types. Notably, MT-BR can befine-tuned to incorporate additional building details, extending itsapplicability. For large-scale applications, we devise a novel spatial samplingscheme that strategically selects limited but representative image samples.This process optimizes both the spatial distribution of samples and the urbanenvironmental characteristics they contain, thus enhancing extractioneffectiveness while curtailing data preparation expenditures. We furtherenhance MT-BR's predictive performance and generalization capabilities throughthe integration of advanced augmentation techniques. Our quantitative resultshighlight the efficacy of the proposed methods. Specifically, networks trainedwith datasets curated via our sampling method demonstrate improved predictiveaccuracy relative to those using alternative sampling approaches, with noalterations to network architecture. Moreover, MT-BR consistently outperformsother state-of-the-art methods in extracting building details across variousmetrics. The real-world practicality is also demonstrated in an applicationacross Shanghai, generating a unified dataset that encompasses both the spatialand attributional details of buildings.

Multi-task deep learning for large-scale building detail extraction from high-resolution satellite imagery