Project Sidewalk: A Web-based Crowdsourcing Tool for Collecting Sidewalk Accessibility Data At Scale

@article{Saha2019ProjectSA,
  title={Project Sidewalk: A Web-based Crowdsourcing Tool for Collecting Sidewalk Accessibility Data At Scale},
  author={Manaswi Saha and Michael Saugstad and Hanuma Teja Maddali and Aileen Zeng and Ryan Holland and Steven Bower and Aditya Dash and Sage Chen and Anthony Li and Kotaro Hara and Jon Froehlich},
  journal={Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems},
  year={2019}
}
We introduce Project Sidewalk, a new web-based tool that enables online crowdworkers to remotely label pedestrian-related accessibility problems by virtually walking through city streets in Google Street View. To train, engage, and sustain users, we apply basic game design principles such as interactive onboarding, mission-based tasks, and progress dashboards. In an 18-month deployment study, 797 online users contributed 205,385 labels and audited 2,941 miles of Washington DC streets. We… 

Figures and Tables from this paper

Urban Immersion: A Web-based Crowdsourcing Platform for Collecting Urban Space Perception Data
TLDR
The design and implementation of the platform, which aims to help architects, urban researchers, or people in spatial management to understand their users' preferences, incorporates webVR and 360-video techniques to display both realistic and abstract representation of the urban environment.
Analyzing Workers Performance in Online Mapping Tasks Across Web, Mobile, and Virtual Reality Platforms
TLDR
A multi-platform system for mapping urban objects using street-level imagery with novel methods for geo-location estimation is designed, demonstrating that the type of task and execution platform can affect the worker performance in terms of worker accuracy, execution time, user engagement, and cognitive load.
A Crowdsourcing Platform for Constructing Accessibility Maps Supporting Multiple Participation Modes
TLDR
This paper proposes a crowdsourcing platform for constructing accessibility maps to support four participation modes: Reporter for people having plenty of free time and high motivation; Gaming reporter for peopleHaving plenty ofFreeTime but with low motivation; Walker for people lacking enough free time but with high motivated; and Gaming walker for people needing to move around more smoothly and with less risk.
CITIZEN PARTICIPATION & DIGITAL TOOLS TO IMPROVE PEDESTRIAN MOBILITY IN CITIES
TLDR
This work presents a framework supported by mobile and web apps and able to propose personalized pedestrian routes that match user mobility profile considering mobility impediments factors using a pedestrian-centric approach based on travel experiences as perceived in the field by senior citizens.
Deep Learning for Automatically Detecting Sidewalk Accessibility Problems Using Streetscape Imagery
TLDR
This paper investigates two application areas: automatically validating crowdsourced labels and automatically labeling sidewalk accessibility issues and introduces and uses a residual neural network modified to support both image and non-image (contextual) features (e.g., geography).
SmartBFA: A Passive Crowdsourcing System for Point-to-Point Barrier-Free Access
TLDR
SmartBFA (Smart Mobility and Accessibility for Barrier Free Access) - a publicly-funded initiative in Singapore that aims to design a scalable and sustainable system that can collect, classify and determine accessible point-to-point routes to address interconnection gaps in first and last mile BFA paths for persons requiring barrier-free access.
Accessibility and The Crowded Sidewalk: Micromobility's Impact on Public Space
TLDR
It is called for the HCI community to consider how innovation transforms as it moves out from centers of development toward peripheries of design consideration, and reflect on efforts to redistribute space, institute tech governance, and offer accountability to those who involuntarily encounter interventions on the ground.
Sidewalk Gallery: An Interactive, Filterable Image Gallery of Over 500,000 Sidewalk Accessibility Problems
TLDR
Sidewalk Gallery is introduced, an interactive, filterable gallery of over 500,000 crowdsourced sidewalk accessibility images that allows users to explore and interactively filter sidewalk images based on five primary accessibility problem types, 35 tag categories, and a 5-point severity scale.
4X: A Hybrid Approach for Scaffolding Data Collection and Interest in Low-Effort Participatory Sensing
TLDR
4X, a multi-stage data collection framework that first collects data opportunistically by requesting contributions at specific locations along users' routes and then uses collected data to direct users to locations of interest to make additional contributions that build data fidelity and coverage, is implemented.
Interactive computational tools for assessing and understanding urban accessibility at scale
  • Manaswi Saha
  • Computer Science
    ACM SIGACCESS Access. Comput.
  • 2020
TLDR
This dissertation research explores assessing urban accessibility and building interactive tools that support decision making processes (e.g., to influence city policy) using crowdsourcing, visualization, and data science techniques, with a specific focus on sidewalk accessibility.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 62 REFERENCES
Combining crowdsourcing and google street view to identify street-level accessibility problems
TLDR
This paper investigates the feasibility of using untrained crowd workers from Amazon Mechanical Turk (turkers) to find, label, and assess sidewalk accessibility problems in Google Street View imagery and demonstrates a promising new, highly scalable method for acquiring knowledge about sidewalk accessibility.
A crowdsourcing platform for the construction of accessibility maps
TLDR
A crowdsourcing platform that enables the collaborative creation of accessibility maps and provides means for integration of different kind of data, collected automatically or with user intervention, to augment standard maps with accessibility information is presented.
User Contribution Patterns and Completeness Evaluation of Mapillary, a Crowdsourced Street Level Photo Service
Mapillary is a Web 2.0 application which allows users to contribute crowdsourced street level photographs from all over the world. In the first part of the analysis this article reviews Mapillary
Tohme: detecting curb ramps in google street view using crowdsourcing, computer vision, and machine learning
TLDR
This work contributes the first CV-based curb ramp detection system, a custom machine-learning based workflow controller, a validation of GSV as a viable curb ramp data source, and a detailed examination of why curb ramps detection is a hard problem along with steps forward.
Interactively Modeling and Visualizing Neighborhood Accessibility at Scale: An Initial Study of Washington DC
TLDR
This poster paper explores the initial design and implementation of neighborhood accessibility models and visualizations for people with mobility impairments by using the Project Sidewalk API, which provides access to 255,000+ labels about the accessibility and location of DC sidewalks.
On the accuracy of urban crowd-sourcing for maintaining large-scale geospatial databases
TLDR
The extent to which crowd-sourcing can be relied upon to build and maintain an accurate map of the changing world is investigated by means of a thorough analysis and comparison between traditional web-based crowd-Sourcing ( as in Wikipedia) and urban crowd- sourcing (as in OpenStreetMap).
WheelieMap: an exploratory system for qualitative reports of inaccessibility in the built environment
TLDR
WheelieMap is proposed, a platform which uses the motion of manual wheelchair users to support the identification and documentation of potentially problematic locations and offers guidance on how to design and develop similar community driven reporting and annotation systems in the accessibility setting.
Using Google Street View to audit neighborhood environments.
Lurking? cyclopaths?: a quantitative lifecycle analysis of user behavior in a geowiki
TLDR
Analysis of user behavior in Cyclopath, a geographic wiki and route-finder for bicyclists, is reported on, to replicate and extend prior work on user lifecycles in Wikipedia and demonstrate the locality of geographic activity and how editing and viewing are geographically correlated.
...
1
2
3
4
5
...