Maryam Hosseini

Computer vision, pedestrian accessibility, walkability, open-source tools.

Maryam Hosseini is assistant professor of City & Regional Planning at UC Berkeley. Central to her research is understanding how the built environment shapes urban experiences. She integrates urban systems, computer vision, and economics to improve walkability, accessibility, and equity in cities. She develops machine learning-driven, open-source tools that help planners design more inclusive and resilient urban environments. Before joining Berkeley, she was a postdoctoral researcher at MIT’s Department of Urban Studies and Planning and earned her PhD in Urban Systems from Rutgers University, conducting her dissertation research at NYU’s VIDA Lab. Hosseini’s work tackles critical challenges at the intersection of technology, environment, and urban design, from enhancing disability access to mitigating pedestrian exposure to extreme heat and flooding.

CP255 – Urban Informatics and Visualization

Mapping the walk: A scalable computer vision approach for generating sidewalk network datasets from aerial imagery

CitySurfaces: City-scale semantic segmentation of sidewalk materials

Routledge Handbook of Urban Public Space, "Joining the Party in Downtown Brooklyn."

Urban Mosaic: Visual Exploration of Streetscapes Using Large-Scale Image Data

The Urban Toolkit: A Grammar-Based Framework for Urban Visual Analytics

Urban Rhapsody: Large-scale exploration of urban soundscapes

Visual Analytics for Profiling Land Use Changes