top of page

AI Case Study

Las Vegas speeds up rubbish and grafitti removal with machine reading of downtown images to identify issues triggering deployment of clean-up crews

Las Vegas uses security camera feeds to automatically spot changes to image suggesting that grafitti has been created or rubbish left. This triggers the deployment of clean-up crews to deal with the issue.


Public And Social Sector

Public Services

Project Overview

"Video captured from cameras already installed in the parks for security purposes streams in real-time to a cloud-based AI service in Microsoft Azure. The AI service, designed by the city, analyses the video data to make a determination, based on what the AI system has been trained to spot. If a park is judged dirty, a work order is generated to clean it....

In developing the project, Vegas city staff relied on generally available, less expensive software tools and already-installed video cameras. The cameras aren’t the most expensive high-resolution models that are equipped for facial recognition. They don’t store data directly; they send all the collected data over wireless to a server for analysis. The city hopes to patent its AI learning approach."

There have been challenges with getting city crews to switch over to this just in time approach. Whilst there is apparently opportunities for "large" savings, but (perhaps not-unconnected with the staff management challenge) these have not been released at this stage.

Reported Results

"The Las Vegas system has already worked successfully in two parks near the downtown area and may soon be adapted for other parks and city roadways."




Field Services


Dealing with street cleaning is an expensive and time-consuming business. Considerable resources are focused on regular sweeps that may or may not pick up much rubbish - meanwhile sudden build-ups of grafitti or fly-tipping may go uncleaned for often lengthy periods between sweeps.



bottom of page