Varun AdibhatlaPatrick Atwater
Published © CC BY-NC-ND

SQUID: Street Quality IDentification

A low-cost approach to perform mobile, citywide street condition surveys by integrating street imagery with ride quality data.

AdvancedWork in progress4,030
SQUID: Street Quality IDentification

Things used in this project

Hardware components

Android device
Android device
×1
iPhone
Apple iPhone
×1
Raspberry Pi 2 Model B
Raspberry Pi 2 Model B
×1
SparkFun Triple Axis Accelerometer Breakout - ADXL335
SparkFun Triple Axis Accelerometer Breakout - ADXL335
×1
Adafruit Ultimate GPS Breakout
Adafruit Ultimate GPS Breakout
×1

Software apps and online services

AWS S3
Amazon Web Services AWS S3
Images and telemetry data are streamed to an S3 bucket
OpenCV
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
Zooniverse
We use the Zooniverse platform to annotate and label street imagery to improve our computer vision models
geopandas

Story

Read more

Schematics

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.

Credits

Varun Adibhatla

Varun Adibhatla

1 project • 11 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.
Contact
Patrick Atwater

Patrick Atwater

0 projects • 0 followers
Contact

Comments