Whether it’s using a cell phone in the car while driving or excessive noise coming from the vehicle, new cameras with AI-powered surveillance techniques are enabling authorities to improve safety and reduce the harm that can be caused by irresponsible vehicle use.

Traffic enforcement systems have evolved from detecting speeding and red light violators to detecting traffic violations. Recently, roadside technologies have also been able to detect drivers using mobile phones while driving, not wearing seat belts, or even breaking excessive noise laws.

The latest capabilities, as is the case in more and more industries, are enabled by the emergence of artificial intelligence systems that can learn and interpret patterns in the real world and perform data fusion, for example by combining audio and video feeds to accurately identify vehicles making excessive noise.

One of the pioneers of “noise camera” technology is British company Intelligent Instruments. It recently won an Intertraffic Award for its SoundVue system, which is being trialled around the world, including in New York City (NYC has passed new laws criminalising excessive noise from vehicles and providing for enforcement), London (in the UK, existing Public Space Protection Order (PSPO) legislation is used for enforcement) and Knoxville, Tennessee.

“Whether someone is modifying their exhaust pipes or revving their engine unnecessarily and driving antisocially, SoundVue captures sound levels and video,” says David Cole, co-founder of Intelligent Instruments. “Then the data is packaged and sent to the cloud where it can be reviewed and a decision can be made as to whether action needs to be taken.”

Of course, with this potential, SoundVue also has competition in this new area of ​​traffic monitoring. Brazilian company Mobilis Technologica has developed a noise detector that is ideal for ensuring quiet in critical locations such as hospitals, clinics, schools and nursing homes. “This system not only combats noise pollution, but also serves as an indicator of air pollution,” says a spokesperson for Mobilis Technologica. “Excessive noise from exhaust systems can indicate harmful gas emissions, so we support more effective environmental monitoring.”

“We have studies linking noise to physiological effects such as heart disease and sleep disorders. We have a lot of evidence quantifying the health effects of noise.”

Dr. Antonio Torija-Martinez, Associate Professor of Acoustic Engineering, University of Salford

Meanwhile, a Dutch collaboration between Sorama and Axis Communications has seen eight noise cameras installed on the streets of Eindhoven, and German company Jenoptik unveiled its own noise camera prototype at this year’s Intertraffic Amsterdam.

“Noise can actually make you sick. More and more customers are asking for such solutions,” says Tobias Deubel, the new head of Jenoptik Smart Mobility Solutions. In fact, the World Health Organization (WHO) has classified noise pollution as the second most harmful environmental cause of illness, surpassed only by fine dust in the air. In Western Europe alone, at least one million premature deaths per year are attributable to excessive, long-term environmental noise pollution.

“We have studies linking noise to physiological effects such as heart disease and sleep disorders. We have a lot of evidence quantifying the health effects of noise,” says Dr. Antonio Torija-Martinez, associate professor of acoustic engineering at the University of Salford in Manchester, UK.

To detect those causing excessive noise in vehicles, the SoundVue system uses four small microphones mounted in a dish, using subtle temporal differences in the sound to determine the location of the source. “Combined with three cameras and a microphone array, it measures sound levels very accurately,” says Rueben Peckham, co-founder of Intelligent Instruments. “If there are multiple vehicles in the video, it can identify which vehicle is causing the extra noise.”

Similarly, Jenoptik’s sound detection system features a multi-microphone Class 1 acoustic array – the same class that SoundVue uses and offers the highest precision possible outside of laboratory environments. It is designed for “vehicle classification and tracking” and “acoustic anomaly detection” that goes beyond vehicle noise and could also help with general law enforcement if it detects the sound of a gunshot, for example. Any sound can be reliably traced to its source.

Jenoptik’s noise camera can be paired with the popular Vector ALPR camera to identify traffic offenders in vehicles. As soon as a predefined decibel level is reached or a noise anomaly is registered, the authorities can be automatically alerted. “You can determine which vehicle caused the noise – and then you can punish people for driving too loudly,” says Deubel.

Both the Jenoptik system and SoundVue are being used in pilot projects. The latter has already been well received in the London borough of Kensington and Chelsea, where there are now a total of eight cameras issuing fines of £100. In the UK, tests are also underway in Bradford, Bristol, Great Yarmouth and Birmingham.

Unlike automatic speed enforcement, the system remains under human control despite issuing fines. The final decision on issuing fines is made by enforcement officers after distinguishing between anti-social driving and legitimate violations of legal limits.

One of the reasons for this is that noise can be subjective and there may be extenuating circumstances, such as when there is a car rally or an emergency. “To you, noise might be a Harley-Davidson motorcycle, but to me it’s not,” says Dr. Torija-Martinez. “Two people can be exposed to the same decibel level of noise, but there are other factors that affect perception.”

Mobile phone surveillance cameras

Another new area of ​​law enforcement is distracted driving detection. Again, a pioneer in this field is a former winner of the Intertraffic Awards – Australian company Acusensus won in Amsterdam in 2022 for its groundbreaking AI system that can accurately detect mobile phone use and seat belt violations.

“Using mobile phones while driving has been illegal for 20 years, but it is clear that more needs to be done to put an end to this potentially deadly habit.”

Edmund King OBE, Director, AA Charitable Trust. Over the past two years, the scheme and rival schemes have been tested around the world. Extensive pilots have taken place in the UK and the new scheme received AA (Automobile Association) backing in December 2023.

“Using mobile phones while driving has been illegal for 20 years, but it is clear that more needs to be done to stop this potentially deadly habit,” said Edmund King OBE, director of the AA Charitable Trust. “Sophisticated camera technology can help detect offenders… This will make our roads safer for everyone.”

In February 2024, Aecom announced that it would act as a systems integrator for Acusensus in further pilot projects in the UK in collaboration with National Highways and 10 police forces: Durham, Greater Manchester Police, Humberside, Staffordshire, West Mercia, Northamptonshire, Wiltshire, Norfolk, Thames Valley Police and Sussex.

At Intertraffic 2024 in April, Jenoptik presented its prototype for distracted driving in addition to its noise camera. It is the first monitoring system of its kind that is suitable for all vehicle classes. “We are currently testing it in initial projects,” says Deubel. “It can detect the use of mobile phones while driving as well as violations of the seat belt requirement.”

The innovation that makes Jenoptik’s system so versatile is the fact that it uses not one but two high-resolution 5K cameras with AI technology: One camera is mounted high and at a steep angle to look into the vehicle’s windshield, and is primarily tasked with detecting phone usage on laps and checking seatbelt indicators. It is complemented by a flat camera optimized for ear-held phone detection, additional seatbelt checks, and automatic license plate recognition (ALPR). “We believe that you need good systems, good cameras, and the right angle to get the best possible result,” says Deubel.

“For our solution to distraction while driving, we use an additional piece of hardware to create different viewing angles.”

Tobias Deubel, Division Manager, Jenoptik Smart Mobility Solutions

Deubel believes the distracted driving solution is a good example of how, despite the benefits of sensor fusion and AI-powered analysis that multifunctional devices can provide, dedicated setups are essential for optimal accuracy.

“For certain applications, you need certain devices and configurations – it has to be the right tool for the right job,” says Deubel. “For our solution against distracted driving, we decided to use an additional piece of hardware to create different viewing angles, which helps to overcome the various challenges in identifying traffic offenders.”

The system is designed for 24/7 surveillance and features a lighting system that enables “24/7 surveillance, day and night.” It also offers additional flexibility as the solution can be deployed stationary: mounted on existing or new infrastructure or as a mobile, self-sufficient trailer solution.

Cutting-edge technology and sensor fusion that address distracted driving and noise pollution have the potential to make our environment safer for generations to come. And with AI capabilities growing rapidly, there is real potential for new forms of enforcement that haven’t even been invented yet.

This article is an edited version of the full article that first appeared in the June 2024 issue of TTi magazine.