Project Description

2016–Present
How can we use computer vision to analyze the accessibility of sidewalks at scale using online imagery such as streetscape and satellite data? In this project, we have a series of papers exploring this question.

Publications

Towards Fine-Grained Sidewalk Accessibility Assessment with Deep Learning: Initial Benchmarks and an Open Dataset

Alex Liu, Kevin Wu, Minchu Kulkarni, Mikey Saugstad, Peyton Rapo, Jeremy Freiburger, Maryam Hosseini, Chu Li, Jon E. Froehlich

Extended Abstract Proceedings of ASSETS 2024 | Acceptance Rate: 66.7% (58 / 87)

Towards Global-Scale Crowd+AI Techniques to Map and Assess Sidewalks for People with Disabilities

Maryam Hosseini, Mikey Saugstad, Fabio Miranda, Andres Sevtsuk, Cláudio T. Silva, Jon E. Froehlich

CVPR2022 Workshop: Accessibility, Vision, and Autonomy (AVA) 2022

Deep Learning for Automatically Detecting Sidewalk Accessibility Problems Using Streetscape Imagery

Galen Weld, Esther Jang, Anthony Li, Aileen Zeng, Kurtis Heimerl, Jon E. Froehlich

Proceedings of ASSETS 2019 | Acceptance Rate: 25.9% (41 / 158) | Best Paper Award