# URBAN-i: From urban scenes to mapping slums, transport modes, and pedestrians in cities using deep learning and computer vision

arXiv: https://arxiv.org/abs/1809.03609 · HTML: https://mlsanity.com/paper/1809.03609/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2018.

## Built on by (most cited first, 9 of 9)

- [CyclingNet: Detecting cycling near misses from video streams in complex urban scenes with deep learning](https://mlsanity.com/paper/2102.00565/) (2021)
- [Computer vision-based analysis of buildings and built environments: A systematic review of current approaches](https://mlsanity.com/paper/2208.00881/) (2022)
- [Self-supervised learning unveils change in urban housing from street-level images](https://mlsanity.com/paper/2309.11354/) (2023)
- [Deep Learning for Slum Mapping in Remote Sensing Images: A Meta-analysis and Review](https://mlsanity.com/paper/2406.08031/) (2024)
- [Urban Visual Intelligence: Studying Cities with AI and Street-level Imagery](https://mlsanity.com/paper/2301.00580/) (2023)
- [FaceTouch: Detecting hand-to-face touch with supervised contrastive learning to assist in tracing infectious disease](https://mlsanity.com/paper/2308.12840/) (2023)
- [RECITYGEN -- Interactive and Generative Participatory Urban Design Tool with Latent Diffusion and Segment Anything](https://mlsanity.com/paper/2602.07057/) (2026)
- [Examining the Associations between Visual and Non-Visual Elements and Cyclists' Route Choices for Various Trip Purposes](https://mlsanity.com/paper/2607.15808/) (2026)
- [Urban Boundaries, Social Barriers: A Benchmark and Vision-Centric Framework for Mapping Gated Communities and Equity Implications](https://mlsanity.com/paper/2609.03804/) (2026)

## Abstract (arXiv)

Within the burgeoning expansion of deep learning and computer vision across the different fields of science, when it comes to urban development, deep learning and computer vision applications are still limited towards the notions of smart cities and autonomous vehicles. Indeed, a wide gap of knowledge appears when it comes to cities and urban regions in less developed countries where the chaos of informality is the dominant scheme. How can deep learning and Artificial Intelligence (AI) untangle the complexities of informality to advance urban modelling and our understanding of cities? Various questions and debates can be raised concerning the future of cities of the North and the South in the paradigm of AI and computer vision. In this paper, we introduce a new method for multipurpose realistic-dynamic urban modelling relying on deep learning and computer vision, using deep Convolutional Neural Networks (CNN), to sense and detect informality and slums in urban scenes from aerial and street view images in addition to detection of pedestrian and transport modes. The model has been trained on images of urban scenes in cities across the globe. The model shows a good validation of understanding a wide spectrum of nuances among the planned and the unplanned regions, including informal and slum areas. We attempt to advance urban modelling for better understanding the dynamics of city developments. We also aim to exemplify the significant impacts of AI in cities beyond how smart cities are discussed and perceived in the mainstream. The algorithms of the URBAN-i model are fully-coded in Python programming with the pre-trained deep learning models to be used as a tool for mapping and city modelling in the various corner of the globe, including informal settlements and slum regions.