How quickly are each of my city's streets deteriorating
New York City
Syracuse, NY
SQUID Bike
Next Steps

Team ARGO: Varun Adibhatla, Patrick Atwater

Published March 10, 2016 © CC BY-NC-ND

SQUID: Street Quality IDentification

A low-cost approach to perform digital street condition surveys continuously by integrating street imagery with ride quality data.

AdvancedWork in progress8,471

Things used in this project

Hardware components

Android device

Apple iPhone

Bike Phone Mount

Car windshield phone mount

Software apps and online services

Amazon Web Services AWS S3

Images and telemetry data are streamed to an S3 bucket

OpenCV

We use this for our automated approaches to detect cracks and other street defects

open street maps

Used for data publishing and cleaning.

OSMnx - Python for Street Networks

Geoff Boeing's creation allows us to quickly convert raw GPS data to actionable maps really quickly and in an open manner.

Open Street Cam

We use Telenav's Open Street Cam as a primary source for data collection

Story

The maintenance of city streets is a most visible indicator of a city government's performance.

Video courtesy Fox News

Every year, US cities spend $ Billions to maintain their local roads, that account for 77% of the nation's infrastructure.

New York City's Ten-Year Capital Strategy allocates $5.4 Billion for the rehabilitation of approximately 8,238 lane miles of its streets. This includes

$1.6 Billion for resurfacing (patching potholes)
$2.4 Billion for reconstruction.

Current methods used to survey streets range from:

Citizens calling in potholes on an ad-hoc basis, or reporting via smartphone apps.
“Windshield surveying” where a trained inspector assigns a score to the quality of a street based on his/her judgement along with a scoring methodology that dates back to the '70s. (Pavement Condition Index)
Bulky, expensive, military grade laser equipment that provide high precision data only for a small sample of streets. Even if a city commits to surveying all their streets, which can cost in the millions, this data is only a snapshot in time and significantly loses its value over time.

What's missing is a low-cost method to collect continuous street quality data for ALL city streets in a consistent and methodical manner.

Our goal is to help cities and public works managers answer a simple question:

How quickly are each of my city's streets deteriorating?

As cities witness the rise of mobility options in the form of scooters, e-bikes and autonomous vehicles, they need digital tools to ensure that streets, bike lanes and assets are accounted for and maintained at cost.

To this end, we develop SQUID, a low cost data platform that integrates open source technologies to combine street imagery and ride quality data to provide a visual ground truth for all the city's streets.

SQUID is a project of ARGO Labs, a non-profit organization that builds, operates, and maintains common-sense data infrastructures to help cities deliver public services.

SQUID was a recipient of the 2016 Prototyping fund from the Knight Foundation.

SQUID started out as a hardware device, a $30 Raspberry Pi micro-computer fitted with accelerometer and GPS sensors, naive optimism and a persistence to prove the initial hypothesis. After collecting our first dataset on the streets of New York, we set out to polish our "lump of clay".

We currently use OpenStreetCam as the primary method to collect street imagery and ride quality data. This approach allows cities and municipalities simply download an app and start collecting data.

Street QUality IDentification

Where SQUID fits in

New York City

Fall 2015

We worked with City of New York's Office of Operations and their SCOUT Team to collect 400+ miles of data from a single vehicle in just over 1 week!

Imagine, if just 15 vehicles vehicles were used to collect street imagery and ride quality data, we could achieve a complete and up-to-date street condition surveys across the entire city in mere weeks!

Pilot with the NYC's SCOUT Team ;

Syracuse, NY

Spring 2016

The City of Syracuse, NY invites us to prototype with their Public Works Department.

Between April 14 - 28, 2016, we collected an estimated 500 miles of street imagery (over 110,000 images) in just 10 days using a single vehicle with little manual intervention, demonstrating the scalability of this approach to inspect an entire city's street infrastructure.

SQUID Project manager, Varun Adibhatla w/Syracuse, NY Mayor Stephanie Miner

SQUID Bike

Summer, 2017

We worked with students from NYU's Center for Urban Science and Progress and used OpenStreetCam, an open-source mobile application purposefully designed to collect street imagery and repurpose SQUID for bike lane inspections giving birth to SQUID BIKE!

SQUID Bike explained

Team SQUID Bike!

OpenStreetCam is an open-source Android/iOS compatible mobile app to collect street imagery

SQUID Bike

Using OpenStreetCam for digital Bike Lane surveys

Next Steps

We are currently building towards a Computer Vision approach to partially automate the detection of street defects such as cracks and large potholes and street assets.

Preliminary results of our Computer Vision detecting cracks on streets!

We welcome feedback, ideas and support on how SQUID can be used to empower cities be proactive, open, and transparent around their public works.

Contact: argo@argolabs.org

Notable mentions:

Route Fifty, A City Data Collaborative for the Age of Autonomous Vehicles
New York Times, Why are the streets always under construction?
Fast Company, A new cheap way to quickly map your city's potholes.
FOX news(video), Smart Cities: The pothole problem.
Staten Island Live, A 21st century proposal for Street maintenance.
WRVO, SQUID to give Syracuse better feel for needed road repairs.
Syracuse.com, Syracuse to map every pothole with truck-mounted camera, $35 computer.
Forbes Tech Blog, The Knight Foundation Funds 20 Media Tech Projects.
Metro New York, Filling potholes faster.

Digitizing Municipal Street Inspections - 2016 Data for Good exchange

"People want an authority to tell them how to value things. But they chose this authority not based on facts or results. They chose it because it seems authoritative and familiar." - The Big Short

The pavement condition index is one such a familiar measure used by many US cities to measure street quality and justify billions of dollars spent every year on street repair. These billion-dollar decisions are based on evaluation criteria that are subjective and not representative. In this paper, we build upon our initial submission to D4GX 2015 that approaches this problem of information asymmetry in municipal decision-making.
We describe a process to identify street-defects using computer vision techniques on data collected using the Street Quality Identification Device (SQUID). A User Interface to host a large quantity of image data towards digitizing the street inspection process and enabling actionable intelligence for a core public service is also described. This approach of combining device, data and decision-making around street repair enables cities make targeted decisions about street repair and could lead to an anticipatory response which can result in significant cost savings. Lastly, we share lessons learnt from the deployment of SQUID in the city of Syracuse, NY.

SQUID-Bike to digitally measure citywide Bike Lane Infrastructure

Urban bicycle usage has gained in importance across many cities with progressive transportation policies. According to [1], as of this paper’s publication, “there are more than 450,000 daily bike trips in New York City, up from 170,000 in 2005, an increase that has outpaced population and employment growth”. About one in five bike trips is by a commuter. Biking serves as an important transportation option to many around the world and we argue that the need for effective bicycle lane maintenance should be a top concern for municipalities.
Conventionally, street maintenance is an expensive, often inaccurate, and time intensive process that either uses subjective data prone to error or uses very precise data that is very expensive to collect citywide. There exists a clear need for cities to adopt a cost-effective and data intensive maintenance practice that can scale to the entire city and be performed
frequently. These needs have been explored through the Street Quality Identification also
known as the SQUID project [2] to develop standardized methods for digital street inspection.
This work extends the SQUID project and repurposes it for citywide bike lane measurements. In this paper, we describe the development of a data and analytics framework to measure bicycle lane quality using street imagery and accelerometer data obtained from an open source smartphone application, OpenStreetCam (OSC) [3] . This framework can be used in crowdsourced or situated settings with the overall purpose being the standardized measurement of citywide bike lane quality

Code

Credits

Varun Adibhatla

1 project • 17 followers

Varun works at ARGO Labs, a civic data science org. that rapidly prototypes for cities by partnering with local gov around device, data & decision making.

Patrick Atwater

0 projects • 0 followers

Thanks to Graham Henke, Patrick Atwater, Krystof Litomisky, David Marulli, Shi Fan, and Manushi Majumdar.

SQUID: Street Quality IDentification