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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Scene change detection which is defined as identifying the difference in semantic categories of multi-temporal remote sensing images at the scene level recognizes the functional changes such as industrial region to commercial region. The integration of remote sensing images and social data for scene change detection often provides higher accuracy than using images alone, as not only physical attributes of ground objects but also socioeconomic information can be used. However, the existing approaches fail to fully exploit the deep features of multi-source input data as well as the temporal features. To achieve more reliable results in scene change detection, this letter proposes a multi-branch fusion network. It simultaneously accepts the very high resolution images and the kernel density maps of the reclassified points of interest data as inputs, which is helpful for comprehensively mining the deep features. In addition, a temporal difference embedded module was developed to extract the temporal features between the input bi-temporal feature cubes. The proposed method was validated on a typical area in Nanjing City, China, and the results showed its superiority over the comparison methods.

Scene-level change detection by integrating VHR images and POI data using a multiple-branch fusion network