A study by Prof. Qihao WENG, Associate Director of the Research Institute for Land and Space (RILS), Director of Research Centre for Artificial Intelligence in Geomatics, Member of the Otto Poon Charitable Foundation Smart Cities Research Institute (SCRI) and Chair Professor of Geomatics and Artificial Intelligence, and his research team, titled “A deep learning-based super-resolution method for building height estimation at 2.5 m spatial resolution in the Northern Hemisphere” was recently published in the journal Remote Sensing of Environment.
Building height is an important indicator for assessing the level of urban development along the vertical dimension. Existing large-scale building height estimation studies focusing on coarse spatial resolution cannot reveal height variations across buildings in urban areas.
The team proposed a deep learning-based super-resolution method to generate building height maps. The researchers created an open building height dataset with 45,000 samples covering 301 cities in the Northern Hemisphere, including China, the conterminous United States, and Europe. The dataset generated provides great potential in high-resolution database updating, urban planning, and natural disaster assessment, as well as a new perspective of how cutting-edge satellite imaging technology can be utilised in urban observation, measurement, monitoring, and management.
Read the full paper: https://www.sciencedirect.com/science/article/pii/S0034425724002591
| Research Units | Research Institute for Land and Space |
|---|
