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/

Zendy Plus

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

Zendy Tools

Zendy Open

Land use as contained in geospatial databases constitutes an essential inputfor different applica-tions such as urban management, regional planning andenvironmental monitoring. In this paper, a hierarchical deep learning frameworkis proposed to verify the land use information. For this purpose, a two-stepstrategy is applied. First, given high-resolution aerial images, the land coverinformation is determined. To achieve this, an encoder-decoder basedconvolutional neural net-work (CNN) is proposed. Second, the pixel-wise landcover information along with the aerial images serves as input for another CNNto classify land use. Because the object catalogue of geospatial databases isfrequently constructed in a hierarchical manner, we propose a new CNN-basedmethod aiming to predict land use in multiple levels hierarchically andsimultaneously. A so called Joint Optimization (JO) is proposed wherepredictions are made by selecting the hier-archical tuple over all levels whichhas the maximum joint class scores, providing consistent results across thedifferent levels. The conducted experiments show that the CNN relying on JOoutperforms previous results, achieving an overall accuracy up to 92.5%. Inaddition to the individual experiments on two test sites, we investigatewhether data showing different characteristics can improve the results of landcover and land use classification, when processed together. To do so, wecombine the two datasets and undertake some additional experiments. The resultsshow that adding more data helps both land cover and land use classification,especially the identification of underrepre-sented categories, despite theirdifferent characteristics.

A hierarchical deep learning framework for the consistent classification of land use objects in geospatial databases