Automating the Process: Collecting Traffic Sign Data in Clovis

In many one-person GIS shops across the United States, collecting and managing local assets can be a daunting task. For Steven Hewett of Clovis, New Mexico, Mapillary presented a way to streamline and automate the process of completing a city-wide traffic sign inventory.

When GIS Specialist Steven Hewett first moved to the 39,000 people city of Clovis in the US he was assigned a task. As a one-person GIS department, Steven needed to undertake a complete traffic sign inventory of the approximately 24 square mile city–something that had never been done before. City managers assumed this task could be completed fairly easily and within a month, but no-one knew how many signs were actually out there.

Steven Hewett, GIS Specialist–Clovis, New Mexico Steven Hewett, GIS Specialist–Clovis, New Mexico

When cities need to do asset data collection, the job can be painstakingly time-consuming and expensive. The mapping function is the largest portion of the GIS market today, a market that is expected to reach over $10 billion by 2023. When it comes to GIS projects, the data capture phase traditionally involves either going out yourself to every location and manually recording the data you need, or hiring a contractor to do it for you. For small cities and towns, private contractors can be far outside of their budgetary restrictions, costing upwards of $4–6 per sign. In Clovis, where there are about 4,000 traffic signs, this would quickly rack up costs to somewhere between $16,000-24,000.

In Clovis, a previous GIS technician had identified Mapillary as a potential solution to this problem. When Steven investigated further, he found that for the cost of a couple of action cameras and fuel, he could do the imagery collection himself and have the traffic signs detected automatically by Mapillary.

Steven mounts action cameras on his vehicle Steven mounts action cameras on his vehicle to capture street-level imagery

Using action cameras attached to his car, Steven collected approximately 200,000 street-level images and uploaded them to Mapillary. Even though he was the only person collecting images, and though he juggled it alongside other day-to-day tasks, the entire process took a couple of months. He believes it could have been done in just a few days—a huge time saving compared to doing the work manually. According to Steven:

“Doing all this work manually, it wouldn’t surprise me if it had taken up to a decade to walk through each and every block to get every sign that is out there. There is no telling how many changes would come through to traffic signs in that time.”

Traffic signs automatically identified by Mapillary Traffic signs automatically identified by Mapillary’s computer vision algorithms in the city of Clovis, New Mexico.

Soon after the images had been uploaded to Mapillary, Steven was able to access the automatically detected traffic sign data. Even better, with a Mapillary for Organizations subscription, the city of Clovis now has access to the freshest traffic sign data, as new imagery can be uploaded at any time by any member of their team. During their subscription period, fresh map data can be downloaded as often as it is needed.

Map data downloaded from Mapillary for Organizations is easily imported into ArcGIS, which is what Steven uses in his day-to-day operations. This traffic sign inventory will be used to make sure all signs are visible, and to check whether they are in need of repair or replacement. With a full inventory, it is also possible to see where more or fewer signs may be necessary for a particular area.

Locations of traffic signs on the Mapillary platform The Mapillary web platform, showing the location of every identified traffic sign.

Earlier this year, we released an update to our traffic sign recognition that supports 1,500 different classes of signs from over 100 countries. If you would like to learn more about how Mapillary can help your GIS organization streamline geospatial data collection, contact our sales team at

/Madelen, Customer Success Manager

Continue the conversation