Computer Vision

Sustainable Cities and Society publishes our novel method to multimodal prediction of climatic parameters using street-level and satellite imagery.

Building and Environment publishes our novel method to assess the impressions of architecture at the urban scale.

A big open dataset with 10M images, together with a paper in the ISPRS Journal of Photogrammetry and Remote Sensing. And more.

Cities publishes our new comprehensive literature review, which was semi-automated to analyse the rich body of knowledge.

Computers, Environment and Urban Systems publishes our new research on using unsupervised machine learning in understanding the urban form.

Landscape and Urban Planning publishes our work on a new use case of street-level imagery and its temporal aspect.

Cities publishes our work on using unconventional (off-road) street-level imagery for a new use case.

ISPRS Journal of Photogrammetry and Remote Sensing publishes our work ‘A Two Layer Spatially Dependent Graph Neural Networks to Identify Urban Functions with Time-series Street View Image’.

Sustainable Cities and Society publishes our novel work on spatio-temporal-explicit GeoAI to predict human outdoor comfort.

ISPRS Journal of Photogrammetry and Remote Sensing publishes our novel work on synthesising morphologically accurate geospatial data for urban form analysis, transfer, and quality control.