ABI Research reports that such cameras will enable an increasing number of low latency mission-critical machine vision applications like pedestrian detection and alerting, and real-time surveillance.
Smart AI-based cameras will help cities build resilience into their transport systems
More than 155,000 smart artificial intelligence-based (AI-based) cameras will be in use by 2025 for traffic management, up from 33,000 in 2020, according to latest research.
This marks a 36 per cent compound annual growth rate for in shipments over the next five years.
Machine vision applications
ABI Research reports that such cameras will transform traffic management by 2025, enabling an increasing number of low latency mission-critical machine vision applications like pedestrian detection and alerting, and real-time surveillance in the intelligent transportation systems (ITS) and the wider smart cities markets.
In the Edge Analytics Cloud Use Cases in Smart Cities and Intelligent Transportation research report, traffic management applications include adaptive traffic lights, vehicle prioritisation and preemption, parking access and detection, and electronic tolling.
“Camera system revenue will grow from US$46m in 2020 to US$189m in 2025,” said Dominique Bonte, vice president end markets at ABI Research. ”Advanced AI-capable processors featuring hardware acceleration for high-performance neural net software frameworks from silicon vendors like Intel, Nvidia, and Qualcomm are propelling smart cameras into the mainstream, offering more features and flexibility at lower price points compared with legacy traffic and electronic toll collection (ETC) sensors like magnetic loops and radio frequency identification (RFID).”
”Advanced AI-capable processors featuring hardware acceleration for high-performance neural net software frameworks from silicon vendors are propelling smart cameras”
The research group added the deployment of 5G and V2X connectivity allowing moving low latency analytics to the edge of telco networks – referred to as edge cloud, network cloud, multi-access edge computing (MEC) or distributed cloud – will enable a new range of application categories across larger geographical areas. These include:
- road intersection management: cooperative adaptive traffic lights and remote traffic management
- safety and security operations: crowdsourced hazard and security alerts and remotely controlled response management systems installed on light poles, buildings and other street furniture
- autonomous asset management: remote control and operation of driverless vehicles, drones and robots.
“In most cases the edge cloud will not replace the roadside edge but rather complement and enhance local safety and security systems into more aggregated, collective, cooperative, and holistic solutions including feeding urban digital twins with actionable local intelligence,” added Bonte.
ABI predicts that closing the loop in near real-time between detection, alerting and local emergency response modes will allow improving the resilience of cities. The application of flood lighting following gunshot detection via audio sensors and automatically closing off gas distribution networks via electronically controlled valves following gas leak detection via chemical sensors are just two examples of next-generation urban safety and security solutions.
These findings are from ABI Research’s Edge Analytics Cloud Use Cases in Smart Cities and Intelligent Transportation. It is part of the company’s Smart Cities and Smart Spaces research service.