Axon to integrate license-plate-reader tech as part of in-car video system next year

Donny Jackson, Editor

October 23, 2019

5 Min Read
Axon logo

Axon today announced plans to integrate automated license-plate recognition (ALPR) powered by artificial intelligence (AI) into its next generation of in-car video cameras in a manner that promises to dramatically reduce the cost of ALPR and address ethics concerns that have been raised about the technology.

Today, it common for law-enforcement agencies to use ALPR to identify the location of vehicles associated with criminal activity, but the specialized equipment—for instance, infrared-based cameras—is expensive, with a total investment of about $20,000 per vehicle to deploy ALPR, according to Axon CEO and founder Rick Smith. This cost factor has resulted in license-plate readers being deploy in a limited number of vehicles, he said.

Smith said Axon plans to take a different approach to ALPR. Instead of using infrared technology, it will leverage the wide-angle video feed and AI processing power in the Axon Fleet 3 in-car video system—expected to be in the market late next year—to identify license-plate information at a 90% reduction in cost, even when a regular ALPR subscription fee is included.

“Fundamentally, what we’ve done is we’re using AI to process video streams off of a standard, color in-car camera,” Smith said during an interview with IWCE’s Urgent Communications. “What that allows us to do is dramatically reduce the cost, because an in-car camera is around a $1,000 investment, as opposed to a $20,000 investment.

“We’re able to now do license-plate reading using the stream from these in-car cameras, where it is effectively just software running on an in-car camera, rather than having to buy a whole separate system.”

Axon will wait until the Axon Fleet 3 in-car video system is shipping next year to offer the ALPR service, because the Fleet 3 is the first Axon camera system that can support the necessary AI functions, according to Smith.

“We’re actually running the AI in the camera itself, which is why we’re holding off on deploying this for the new camera system,” he said. “With our existing cameras, you would have to push the video stream up to the cloud, and that would consume a ton of data.

“With the new camera, we’re putting a pretty beefy AI-capable processor in the camera itself, so it’s doing all of the image processing locally on the camera.”

Of course, any license-plate information gathered must be compared to a database of license-plate numbers of interest to be useful to the officers in the field. Smith identified two approaches to doing this.

“The camera will do the basic processing, and it will determine the license-plate number and state,” Smith said. “We can compare that to data that can be stored in encrypted form.

“So, you can have hot lists that can be pushed down to the camera, or you can push that data up to the cloud, but what we’re really pushing then is just text data—license-plate numbers and states—which is a very light data lift, compared to pushing a whole video stream over LTE up to the cloud for processing.”

Proponents of many existing ALPR systems contend that infrared technology is more effective reading reflective license plates that have been covered with mud, something that potentially could be a problem for a camera-based system. But Smith says the Axon technology has outperformed four existing ALPR in early tests conducted by the company, noting that infrared technologies cannot see temporary license plates made of paper and often have difficulty discerning which state issued the license plates—tasks that the camera-based ALPR handle well.

“We’re early enough that we don’t have definitive comparative data, but we believe it [the Axon ALPR service] will be comparable or more accurate, especially if you consider the cost per deployment,” Smith said. “And we’ll be able to offer much broader coverage, because of the much lower cost of the cameras.”

Smith said the impact of this potential for broader ALPR usage was studied by Axon’s AI and Policing Technology Ethics Board prior to the company deciding to announce its license-plate technology. Previously, this ethics board determined that facial-recognition technology was not yet accurate enough for Axon to utilize the technology in its solutions at this time, he said.

When the notion of ALPR was brought to the ethics board, “the initial reaction was very negative,” Smith said. Key concerns revolved around the fact that ALPR usage was being done with very little transparency when implemented, that data was being retained for extended time periods—in some cases, forever—and that some ALPR vendors claimed ownership of the license-plate data and would sell it commercially, he said.

Axon is trying to address these concerns by vowing not to resell ALPR data commercially and developing a “heat map” functionality depicting ALPR usage that can be shared with the public, Smith said. In addition, by dramatically lowering the cost of ALPR, the Axon technology could be deployed in most law-enforcement vehicles, so there is less concern that only certain segments of the community are being targeted—a concern voiced by some civil-liberties organizations, he said.

Axon Ethics Board member Barry Friedman—founder of the Policing Project at the New York University School of Law and the Jacob D. Fuchsberg Professor of Law at New York University—said that vendors should consider such impacts of technologies prior to releasing products.

“The unregulated use of ALPRs has exposed millions of people subject to surveillance by law enforcement, and the danger to our basic civil rights is only increasing as the technology is becoming more common,” Friedman said in a prepared statement.

“If government is going to continue to abdicate its responsibility to regulate this technology appropriately—and we hope it doesn’t—it is incumbent on companies like Axon to ensure that ALPRs serve the communities who are subject to ALPR usage. This includes guardrails to ensure their use does not compromise civil liberties or worsen existing racial and socioeconomic disparities in the criminal justice system.”

Axon will preview the Axon Fleet 3 system in Booth 2211 beginning Sunday at the International Association of Chief of Police (IACP) event that will be conducted in Chicago.

About the Author

Donny Jackson

Editor, Urgent Communications

Donny Jackson is director of content for Urgent Communications. Before joining UC in 2003, he covered telecommunications for four years as a freelance writer and as news editor for Telephony magazine. Prior to that, he worked for suburban newspapers in the Dallas area, serving as editor-in-chief for the Irving News and the Las Colinas Business News.

Subscribe to receive Urgent Communications Newsletters
Catch up on the latest tech, media, and telecoms news from across the critical communications community