Project Sidewalk APIs #

Project Sidewalk is a web tool for mapping and assessing sidewalk conditions using a combination of crowdsourcing, artificial intelligence (AI), and online map imagery. Project Sidewalk's mission is to develop scalable, low-cost techniques that accurately map and assess every sidewalk in the world to help transform the walkability, rollability, and safety of cities and to enable new urban analytics and personalized mapping tools for varying mobility levels.

All Project Sidewalk data is public and can be accessed in popular formats like CSV, GeoJSON, or shape files or accessed programmatically via our APIs.

API Overview#

Our API is divided into four sections:

Metadata APIs: for describing our data structures and deployment cities
Data APIs: for our collected label data and validations
AccessScores APIs: for scoring of sidewalk accessibility of streets and regions
Stats APIs: for overall stats on users and collected data

We expand on each below. You can also navigate to the individual API pages on the left sidebar. Before describing the API endpoints, we first explain the core data type in Project Sidewalk: labels.

Labels#

In Project Sidewalk, users navigate street view imagery and label sidewalk features (like curb ramps) as well as barriers (like surface problems), which are then geo-located by our tool (i.e., assigned a lat,lng). For each label, users can provide tags, a severity rating, and an open-ended description. For quality control, labels are also validated by other users in tools like Validator, LabelMap, or Gallery. You can filter labels by their validation ratings.

You can download either the raw label dataset or label clusters.

Label Types #

Project Sidewalk has the following label types (see the Label Types API):

Label Tags #

Each label can have one or more tags for more detailed categorization. These tags are customizable per city, reflecting the diverse needs of different communities, geographies, and sidewalk designs. Below is a summary of available tags by label type (see the Label Tags API):

Metadata APIs#

We have four Metadata APIs:

Cities: lists Project Sidewalk deployment sites
Label Types: lists Project Sidewalk label types
Label Tags: lists tags associated with each label type
Street Types: lists Project Sidewalk street types

Label Data APIs#

We provide two different labeling datasets plus an aggregated version (by street) along with validation data.

Raw Labels: Individual geo-located labels provided by our users.
Label Clusters (recommended): Because the same sidewalk feature/barrier could be labeled by multiple users or even the same user from different street view images (i.e., from different perspectives), we use a custom clustering algorithm to group labels together.
Streets: Labeling data organized per street.
Validations: User judgments of label data.

Accessibility Score APIs#

Inspired by WalkScore, we also compute an aggregate "accessibility" index based on Project Sidewalk data. These scoring algorithms are experimental. You can compute your own scoring indices by using our Labels API.

We provide two different scoring approaches.

Note: The accessibility score version 3 APIs are not yet available.

StreetScore: A score that represents the accessibility of individual streets based on the presence of barriers and features.
NeighborhoodScore: An aggregated score that represents the overall accessibility of neighborhoods.

Stats API#

Finally, we also provide basic statistics about Project Sidewalk data and users.

Overall Stats: Basic data stats, including number of users, kilometers audited, label counts (broken down by label type), accuracy, severity.
User Stats: Basic user stats, including total labels placed, validations, meters explored. The IDs for users are anonymized but persist over time.

Terms of Use #

If you use Project Sidewalk data in your research, please cite the following paper (awarded 🏆 Best Paper at CHI 2019):

Manaswi Saha, Michael Saugstad, Hanuma Teja Maddali, Aileen Zeng, Ryan Holland, Steven Bower, Aditya Dash, Sage Chen, Anthony Li, Kotaro Hara, and Jon Froehlich. 2019. Project Sidewalk: A Web-based Crowdsourcing Tool for Collecting Sidewalk Accessibility Data At Scale. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI '19). Association for Computing Machinery, New York, NY, USA, Paper 62, 1–14. https://doi.org/10.1145/3290605.3300292

Contribute#

Project Sidewalk is an open-source project created by the Makeability Lab and hosted on GitHub. We welcome your contributions! If you found a bug or have a feature request, please open an issue on GitHub.

You can also email us at sidewalk@cs.uw.edu

Project Sidewalk in Your City!#

If you are interested in bringing Project Sidewalk to your city, please read our Wiki page.