Send message to Authors

Paper short abstract:

BEAM is an ai-based mapping tool for city planners to accelerate the spatial recognition of building structures on aerial imagery. The tool equips the city with up-to-date information on the location and extent of its informal settlements, to better target upgrading and service delivery projects.

Paper long abstract:

In the city of eThekwini almost 25% of its population lives in informal settings. To address this issue and strengthen community resilience, the city has embraced an ambitious upgrading programme. But outdated data on the location and extent of informal settlements make it difficult to plan interventions in an efficient way and to respond to resident needs. To develop a pipeline of upgrading and basic urban service delivery projects, the city is in need of access to evidence-based information. However, accurately mapping the growth of informal settlements is a time-consuming process and often involves manual digitization of aerial imagery. This raises the question, how a digital tool based on AI can help, to better understand dynamics of informal settlements?

To support eThekwini's efforts to improve its data accessibility and to assist the city in automating their building mapping process, the UNITAC Hamburg team developed the Building & Establishment Automated Mapper. BEAM is a mapping tool that uses machine learning, to accelerate the spatial recognition of building structures based on aerial imagery. It’s designed as an easy-to-use application to quickly visualize urban footprints and provide GIS layers of a specific area. BEAM accelerates mapping processes, makes workflows more efficient, and allows the city to keep track of changes in the built-up area or density.

To enable knowledge and skills transfer and ensure that the tool output is used to archive more efficient and evidence-based planning processes, so especially people and communities do benefit a community of practice was set up.