Digitizing Municipal Street Inspections Using Computer Vision

TL;DR

This paper presents a computer vision-based system using the Street Quality Identification Device (SQUID) to digitize and improve municipal street inspections, enabling targeted repairs and cost savings.

Contribution

It introduces a novel process combining device, data, and decision-making to automate street defect identification and support proactive municipal infrastructure management.

Findings

Successful deployment of SQUID in Syracuse, NY.

Enhanced accuracy in street defect detection.

Potential for significant cost savings in street repairs.

Abstract

"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.