AI-supported traffic analysis from Swarm Analytics gives cities and municipalities a powerful tool with permanent journey time analyses
Up-to-date and comprehensive traffic analyses with automated recognition of vehicle classes, speeds, directions of movement and much more – these are the foundations for evidence-based traffic planning in cities and municipalities. And thus indispensable tools in the search for the solution to gridlock and accelerating climate change. Swarm Analytics is now expanding its traffic analysis and planning system with the new Journey Time feature. Journey Time reveals which vehicle classes are on the road for how long and on which routes. A particularly powerful feature that has been at the top of the wish list of all traffic experts for years. Now it is available.
“Urban planners have been waiting for years for the possibility to get travel times with little effort,” says Michael Bredehorn, CEO at Swarm Analytics. From now on, this data can be collected permanently, automatically and fully DSGVO-compliant. And are available for fact-based traffic planning and control.
Basic prerequisite: Complete data protection conformity
For travel time, whether for cars, public transport or trucks, a vehicle must be clearly identifiable over spatial and temporal distances. The crux of the matter: personal information must not be recognised or stored. In other words, DSGVO-compliant.
The solution from Swarm Analytics is based on the AI-supported evaluation of video data from commercially available IP cameras. The information is converted on site, without ever being stored, into encrypted strings (so-called hashes) in compliance with data protection laws, which are then further encoded. A personal allocation is thus impossible.
Sooner or later: permanent recording of travel times is indispensable for modern transport planning
Real-time data is made available, which can be used immediately by traffic engineers and traffic information systems and used to solve current problems: Detours, breakdowns, waiting times – all important information for people on the move.
But far more important is the long-term benefit: Vehicle type, speed and route load – until now, this data simply did not exist or only existed very sporadically. With them, strategic measures are reliably simulated, thanks to the huge, dynamic database.
The integration of information such as travel times and traffic frequencies ensures that all planning is based on the latest findings and not on data that has been outdated for years. This makes it possible for the first time to use reliable, up-to-date studies as the basis for an expensive investment decision and to meaningfully shape a data-driven traffic turnaround.
Travel time captures the traffic mix
The travel time data provides the traffic distribution within the entire road network and thus the valuable insight into how traffic is distributed, broken down by vehicle class. In other words, how people perceive whether and how smoothly traffic flows – or comes to a standstill. This allows traffic to be divided into the following user groups, among others:
– Commuter traffic, which occurs recurrently at fixed times and can be optimised through appropriate prioritisation (e.g. green wave in the morning towards the city centre).
– Through traffic, which only passes through a place, but still burdens the road network. Especially in holiday and holiday regions, this can lead to a significant increase in traffic.
– Shopping traffic or short-term visiting traffic, which makes targeted trips to areas (e.g. shopping centres, industrial estates) and leaves them again after less than two to four hours.
All the above-mentioned traffic types and many more use one and the same road network and are important for sustainable traffic planning. And this is exactly where traffic analysis systems come in. Thanks to the travel time feature, now also with valuable data that simply did not exist before. As much reliable and comprehensible data as possible is the basis for any sensible traffic control and for new ideas or approaches.
Pioneer and think tank Innsbruck
The best example for the use and implementation of Journey Time in demanding traffic is Innsbruck: In close cooperation with Austria’s fifth largest city, Swarm Analytics has set up a productive test installation. On four test routes, which combine practically all challenges for automatic detection and evaluation, counting, classification and precisely the journey time has been calculated since November 2022.
A win-win situation: with the installation, Swarm Analytics proves the daily benefit with little effort and continuously optimises the system according to real requirements. The City of Innsbruck, in turn, has all the advantages of real-time data and a reliable overview of the demanding traffic hotspot urban area. Improvement measures can be sensibly planned and their success easily checked. Including “aha experiences”, such as the fact that closing roads can make traffic flow more smoothly.