There is already a wide array of diverse sensors that function within today's traffic infrastructure - speed cameras, weight-in-motion, traffic lights, and more. They provide information and data that makes road traffic more effective and safe. Unfortunately, they're currently limited by the fact that they have been created by different manufacturers with varying approaches and standards. In other words - they aren't able to talk to each other.
An AI-based Intelligent Transportation Platform called Fits has been developed in cooperation with the company Dots. It's a system that helps solve the issue of sensors not "talking" to each other. Fits automatically collects data from across a spectrum of vendors and suppliers into a unified data store, fuses it with AI engines and enables business process specific processing for any data-driven use case - from speed enforcement to traffic optimization. It also monitors the fleet of sensors to ensure maximum data collection uptime and includes 24/7 monitoring centre services.
This system was built keeping European Transport Policy in mind, which is why this system supports both the DATEX II format, as well as all EU safety requirements. It's located at the isolated EUROPEAN data centre and is in compliance with ISO/IEC 27001/27002:2013 and the GDPR.
This project is considered graduated, and an example of the Fits system efficiency is the implemented Speed Enforcement platform in Latvia, for the Road Traffic Safety Directorate. We've created a system that makes use of a re-trained deep neural network to pre-process speeding violations, ensure statistical analysis, and enable rapid response. Both the client and industry representatives from other European countries highly appraise system and we can confidently say that it's one of the most effective in Europe. But what's more important, it has made the streets of Latvia more safe - in 2016-2018, the number of traffic accidents has dropped by 47% and serious accidents - by 45%.