Mila Koeva (PGM); Caroline Gevaert (EOS)
3D modelling
The work is in collaboration with Alexandra Pedro from the Sao Paulo City Hall. UAV for several informal settlements is available. The topic is of interest for the colleagues from Sao Paulo (Brazil) therefore, additional information and data will be provided from them.
As it is reported for the SDG indicator 11.1.1 and according to UN-Habitat the number of urban population living in slums, informal settlements or inadequate housing is around one billion [1,2]. With the increasing population and urbanization the only option for many cities is to grow in a vertical dimension. The ability to access and manipulate 3D geo-data of complex situations as informal settlement areas is increasingly important for urban planning and decision making related to both existing and new developments. Areas as slums, informal settlement and inadequate housing are very dynamic places in terms of their physical dynamic as well as socio-economic dynamic. For the physical dynamic, most studies, if done at all, only analyse the expansion but not densification nor vertical development processes. Therefore, building a 3D model of such areas will provide critical information to the governmental, institutional or private organisations useful for variety of applications. There has been a research on using Remote Sensing data and innovative methods such as deep learning for estimations related to deprivation or housing in the slums [3-7]. Classification methods and algorithms for automatic 2D and 3D mapping based on RS data have also been recently investigated [8]. Recent years, the advent of Building Information Modelling (BIM), which incorporate detailed semantically rich 3D design of buildings gain popularity have alsobeen proven. However, research for slums including vertical dimension (3D) and especially to support BIM has not been done.
With this research topic, we aim in investigation of automated 2D and 3D maps as initial step towards BIM modelling. The topic can include work related to classification of UAV (or other RS data), visualization, methods and tools for integrated 3D data analysis.
The project involves the use innovative algorithms for 3D mapping based on RS data and GIS in an integrated manner.
1. UN-Habitat. Slums Almanac 2015-16. Tracking Improvement in the Lives of Slum Dwellers. Nairobi, 2016.
2. UN-Habitat. Metadata: Indicator 11.1.1: Proportion of urban population living in slums, informal settlements or inadequate housing. 2016.
3. Ajami, A.; Kuffer, M.; Persello, C.; Pfeffer, K. Identifying a Slums’ Degree of Deprivation from VHR Images Using Convolutional Neural Networks. Remote Sensing 2019, 11, 1282.
4. Thomson, D.; Kuffer, M.; Boo, G.; Hati, B.; Grippa, T.; Elsey, H.; Linard, C.; Mahabir, R.; Kyobutungi, C.; Mulandi, J., et al. Critical Commentary: Need for an Integrated Deprived Area “Slum” Mapping System (IDeAMapS) in LMICs. In Preprints 2019, 2019.
5. Liu, R.; Kuffer, M.; Persello, C. The Temporal Dynamics of Slums Employing a CNN-Based Change Detection Approach. Remote Sensing 2019, 11.
6. Wurm, M.; Stark, T.; Zhu, X.X.; Weigand, M.; Taubenböck, H. Semantic segmentation of slums in satellite images using transfer learning on fully convolutional neural networks. ISPRS Journal of Photogrammetry and Remote Sensing 2019, 150, 59-69.
7. Taubenböck, H.; Kraff, N.J.; Wurm, M. The morphology of the arrival city - A global categorization based on literature surveys and remotely sensed data. Appl. Geogr. 2018, 92, 150-167.
8. Nikoohemat, S., Diakité, A. A., Zlatanova, S., & Vosselman, G. (2020). Indoor 3D reconstruction from point clouds for optimal routing in complex buildings to support disaster management. Automation in construction, 113, 103109.