A leading researcher into the use of artificial intelligence solutions in traffic is hailing a new solution which uses AI to deliver advanced signal control and safe crossing solutions.
Professor at Korea’s Advanced Institute of Science and Technology, Hwasoo Yeo, is praising Nota AI (Nota Incorporated)’s new vision analysis technique called AI Camera. This artificial intelligence solution collects traffic data from a standard CCTV camera at the intersection, processes it in real-time to calculate traffic flow, time-mean speed and occupancy similar to existing, passive sensors such as loop detectors and radar.
“The ITS industry needs a new wave and new dynamics,” said Professor Yeo. “Up to now there have not been many talents that research both AI and traffic. Nota AI is a company that focuses on research, one of the few companies whose capacity encompasses both sides. I have a high expectation that Nota AI will be the company that enables digital twin, new AI-based traffic signal control, simulation-based traffic signal control and so much more. I do think Nota AI will be the next generation.”
The Korean ITS solutions company Nota AI launched the solution focusing on intersections last year, calling them the core of urban problems. Its management system makes them more efficient and safer through edge AI techniques.
Nota AI says that due to its edge AI technology, AI Camera can reduce the cost of data communication and latency compared to the other server-based vision analysis methods. It can classify vehicles into seven types and secure over 95% accuracy in various weather conditions (daytime, night, snow, rain, etc). In addition, it also collects spatial information (such as space-mean speed) of the road using the perspective transform to improve the data applicability to the various fields.
Nota AI is an NVIDIA Inception and Metropolis partner, and Adam Scraba, Marketing lead for NVIDIA’s Metropolis Platform added, “Nota AI is bringing to market a new generation of vision AI applications that make roadways safer and more efficient. Their applications accurately detect and track vehicle types, understand traffic patterns, and provide cities the insights they need to help reduce congestion and increase safety.”
The AI Camera solution being launched has already been implemented in Daejeon City in South Korea. “Today most of our sites are implementing smart intersection systems and the ultimate goal of having these systems is to control traffic signals in real time,” explained Chang-hee Lee, works for Daejeon City and plans and executes smart traffic projects. “To enable such a system, the connection of the on-site edge device and the AI algorithms applied is the single most important requirement. Nota AI’s AI edge device can be an important way to solve these municipal traffic problems.”
The solution not only delivers data for motor vehicles, but walking and cycling as well, predicting hazardous situations through the short-term trajectory prediction by working out if two objects on different trajectories are likely to collide.
(Picture – Nota AI)