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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Rapid globalization and the interdependence of humanity that engendertremendous in-flow of human migration towards the urban spaces. With advent ofhigh definition satellite images, high resolution data, computational methodssuch as deep neural network, capable hardware; urban planning is seeing aparadigm shift. Legacy data on urban environments are now being complementedwith high-volume, high-frequency data. In this paper we propose a novelclassification method that is readily usable for machine analysis and showapplicability of the methodology on a developing world setting. Thestate-of-the-art is mostly dominated by classification of building structures,building types etc. and largely represents the developed world which areinsufficient for developing countries such as Bangladesh where the surroundingis crucial for the classification. Moreover, the traditional methods proposesmall-scale classifications, which give limited information with poorscalability and are slow to compute. We categorize the urban area in terms ofinformal and formal spaces taking the surroundings into account. 50 km x 50 kmGoogle Earth image of Dhaka, Bangladesh was visually annotated and categorizedby an expert. The classification is based broadly on two dimensions:urbanization and the architectural form of urban environment. Consequently, theurban space is divided into four classes: 1) highly informal; 2) moderatelyinformal; 3) moderately formal; and 4) highly formal areas. In total 16sub-classes were identified. For semantic segmentation, Google's DeeplabV3+model was used which increases the field of view of the filters to incorporatelarger context. Image encompassing 70% of the urban space was used for trainingand the remaining 30% was used for testing and validation. The model is able tosegment with 75% accuracy and 60% Mean IoU.

Deep-learning coupled with novel classification method to classify the urban environment of the developing world