Green Infrastructure Analysis Using Segmentation Models
Identyfikator grantu: PT01183
Kierownik projektu: Khansa Gulshad
Politechnika Gdańska
Wydział Inżynierii Lądowej i Środowiska
Gdańsk
Data otwarcia: 2024-08-27
Streszczenie projektu
The primary aim of this project is to develop a methodology for accurately quantifying and mapping green infrastructure (GI) within urban areas, such as trees, grass, and other vegetation. Urban green infrastructure plays a critical role in mitigating the effects of climate change, flood management, and improving the overall livability of cities. However, accurately assessing and mapping these green spaces on a large scale remains challenging. Traditional methods are often labor-intensive and lack the precision required for effective urban planning and policy-making.
This project aims to leverage state-of-the-art deep learning models to automate the process of green infrastructure mapping. The project will create detailed maps of green infrastructure across Gdańsk, Poland, by applying semantic segmentation techniques to street view images. Furthermore, the present work inspects whether reconstructed spectral images add relevant information to segmentation networks for improving urban GI identification. This will involve generating and processing multispectral data using cGANs. This research outcome will benefit urban planners, flood management authorities, and policy-makers who require accurate and up-to-date information on urban green spaces.
This project aims to leverage state-of-the-art deep learning models to automate the process of green infrastructure mapping. The project will create detailed maps of green infrastructure across Gdańsk, Poland, by applying semantic segmentation techniques to street view images. Furthermore, the present work inspects whether reconstructed spectral images add relevant information to segmentation networks for improving urban GI identification. This will involve generating and processing multispectral data using cGANs. This research outcome will benefit urban planners, flood management authorities, and policy-makers who require accurate and up-to-date information on urban green spaces.