AI-Assisted Vehicle Noise Detection and Plate Reading

What it is for

Enforcement

Supports DEP staff in determining whether to issue a noise summons to vehicle owners found to be in violation of noise regulations on NYC roads.

NYC Algorithmic Tools Compliance Report

Run by: Department of Environmental Protection (DEP)
Where: No fixed location
Kept: Not stated by the NYC Office of Technology and Innovation.
Shared with: Accountable organization, Vendor
Your copy: You cannot see the data it holds about you. What you can do

What it is for

Enforcement

This system uses roadside cameras to record loud vehicle noises and automatically classifies them by type — muffler violations, honking, or other sources — while also attempting to read license plate numbers using optical character recognition. The results help NYC Department of Environmental Protection staff decide whether to issue a noise summons to a vehicle owner. A human staff member reviews all recordings before any enforcement action is taken.

What it collects and what happens to it

Data taken in

Biometric

Identifiable data

Video recordings from roadside cameras capture vehicle audio and visual imagery, including vehicle license plates which can identify specific individuals through vehicle registration records.

NYC Algorithmic Tools Compliance Report

About a measurement

Anonymized data

Noise decibel levels recorded by roadside cameras alongside video footage of the noise event.

NYC Algorithmic Tools Compliance Report

Processing

Computer Vision

Video analysis classifies the type of noise event (muffler, honking, or other) from camera recordings and applies OCR to read vehicle license plate numbers from the footage.

NYC Algorithmic Tools Compliance Report

Classification & Prediction

Classifies recorded noise events into categories: car muffler violation, honking, or other noise types. Computation type is explicitly described as classification in the register.

NYC Algorithmic Tools Compliance Report

What it does

Deciding (Analytical AI)

Human decides

Classifies recorded noise events by type (muffler, honking, or other) and reads vehicle license plates. DEP staff review all results manually before deciding whether to issue a noise summons.

NYC Algorithmic Tools Compliance Report

Sensing (Perceptive AI)

Human decides

Uses optical character recognition (OCR) to read vehicle license plates from camera footage, and audio-visual analysis to detect and classify noise events from raw video recordings.

NYC Algorithmic Tools Compliance Report

Outputs

Sensitive personal information

Identifiable data

Vehicle plate number output by the OCR component, which when matched against vehicle registration databases identifies the registered owner — a specific individual.

NYC Algorithmic Tools Compliance Report

A recommendation or prediction

Anonymized data

Noise type classification output (muffler, honking, or other) that informs — but does not determine — DEP staff decisions on whether to issue a noise summons.

NYC Algorithmic Tools Compliance Report

Run by

Department of Environmental Protection (DEP)

The NYC Department of Environmental Protection, through its Bureau of Environmental Compliance, deploys and operates this noise-monitoring system on New York City roads and uses its outputs to inform enforcement decisions.

NYC Algorithmic Tools Compliance Report

Built by

Intelligent Instruments

Intelligent Instruments provides the roadside cameras installed on New York City roads and the software platform that performs automatic analysis of the audio-visual recordings to classify noise types and read license plates.

NYC Algorithmic Tools Compliance Report

Kept for

Not stated by the NYC Office of Technology and Innovation.

Shared with

Not available to me

The register does not describe any public access mechanism for individuals to view data collected about their vehicle. No individual access or data request pathway is described.

NYC Algorithmic Tools Compliance Report

Available to the accountable organization

DEP staff access the recordings and analysis outputs to review and verify results before making enforcement decisions.

NYC Algorithmic Tools Compliance Report

Available to vendor

Intelligent Instruments operates the software platform that processes the recordings; as the platform provider, the vendor has access to data processed through their system.

NYC Algorithmic Tools Compliance Report

Stored

Not stated by the NYC Office of Technology and Innovation.

How to read the colours

Can it identify you?

Anonymized data: Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
Pseudonymous data: Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
Identifiable data: The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.

Who completes the loop?

Human decides: This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
Human executes: This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
Autonomous: This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.

Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.

What you can do

Ask about this system

Questions go to the NYC Office of Technology and Innovation, not the vendor.

Your rights

Right to Be Informed of AI UseVehicle owners who receive a noise summons are informed of the basis for that summons. The existence of this noise-monitoring program is disclosed through the NYC Algorithmic Tools Compliance Report, publicly available at https://data.cityofnewyork.us/City-Government/Algorithmic-Tools-Compliance-Report/jaw4-yuem.
Right to a Human ReviewAll recordings are manually reviewed by DEP staff before any noise summons is issued. No automated enforcement action is taken without human verification of the AI system's outputs.
Right to ContestIndividuals who receive a noise summons issued by the NYC Department of Environmental Protection may contest the summons through the standard NYC administrative adjudication process. The register does not describe a specific AI-related appeal pathway.

Risks and safeguards

Civil liberties harmAutomated license plate reading and surveillance of public roads could implicate the civil liberties of all road users, with potential for misidentification leading to erroneous enforcement.Safeguard: The system is supervised — DEP staff manually review all recordings before any summons is issued, ensuring no fully automated enforcement action occurs.
Reputational harmOCR misreads or noise-type misclassification could link a summons to the wrong vehicle owner, causing reputational or financial harm.Safeguard: Human staff verify all results manually prior to enforcement action; training data provenance is not publicly disclosed, limiting independent accuracy audits.