Pavement Type
The material composition and texture of the sidewalk surface
The material composition and texture of the sidewalk surface
The incline level of the sidewalk
Any blockage or barrier that reduces sidewalk width
The available space for pedestrian traffic
The total distance covered by the sidewalk
Evaluating sidewalk accessibility is a manual and time-consuming task that requires specialized personnel. In Sidewalk AI, we propose a web app that enables quick, crowd-sourced, and low-cost sidewalk assessment. Based on images collected with smartphone cameras, Sidewalk AI computer vision models automatically identify sidewalk features such as width, obstacles, and pavement conditions. Though not a replacement for high-resolution methods, Sidewalk AI gives a rapid assessment that empowers communities to engage in planning and designing more inclusive cities.
Carlo Ratti Director
Fábio Duarte Project Manager
Diego Morra Research and Project Lead
Xiaosheng (Jeffrey) ZhuSoftware Development
Chang LiuVisual AI Expert
Simone MoraResearch
Yinan DongVideo & Web
Morra, D., Zhu, X., Liu, C., Fu, K., Duarte, F., Mora, S., He, Z., & Ratti, C. (2024). Mapping sidewalks accessibility with smartphone imagery and visual AI: A participatory approach. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.
The material on this website can be used freely in any publication provided that:
1. it is duly credited as a project by the MIT Senseable City Lab
2. a PDF copy of the publication is sent to
senseable-press@mit.edu
