Compared to traditional transportation systems, advanced highway traffic control systems rely on sensors and data analytics tools to automate various processes, allowing operators to focus on what’s more important at hand.
Compared to traditional transportation systems, advanced highway traffic management systems (HTMS) rely on sensors and data analytics tools to automate various processes, allowing operators to focus on what’s more important at hand.
It’s worth noting that traffic management systems are nothing new. The first traffic signal, one of the earliest forms of traffic management systems, came about in 1914. Over the years, traffic management systems have evolved and become quite advanced.
The differences between a traditional transportation system and a modern highway traffic management system begin with sensors, which, for the latter, are diverse and wide-ranging. “What has changed (between traditional and modern traffic management systems) is the number of sensors that have been added. With more sensors, the information is finer and therefore more accurate are the predictions and management,” said José Luis Añonuevo Navarro, Traffic Management Systems Operations Manager of Transports Division at
Indra Sistemas.
“The presence of intelligent sensors such as AID systems based on artificial intelligence, LPR and ADR systems and WIM systems enable to improve the quality of highway management in the present and the future,” said Paola Clerici, GM and VP Sales of
Sprinx Technologies.
The data generated by these sensors is analyzed with advanced analytics tools to provide actionable insights for operators, who can then concentrate on more important work at hand instead of constantly monitoring data feeds.
“While earlier-generation systems may have featured similar sources of information, that is where the similarities between a highway traffic management system and a traditional transportation system end. In a traditional analog system, most if not all decisions are driven by operators directly monitoring video feeds or other sensor data. Pre-scripted workflows can be triggered by an operator, but those scripts are very static and hard-coded. Automating interventions, analyzing video and correlating it with data of different kinds is simply impossible,” said Christian Chenard-Lemire, Team Lead for Intelligent Transport Systems at
Genetec.
The importance of data
Indeed, a major differentiator between traditional and modern traffic management systems for both road and
highway applications is data, which can not only help raise situational awareness but also predict future traffic patterns, thus allowing better planning for municipal operators.
“Modern
advanced traffic management systems (ATMS) do have analytics tools to support public agencies in two major ways: 1) improve the operational efficiencies of the system by comparing historical data with real-time data and creating new relationships between different types of data that would normally not be looked at in relationship, and 2) supporting predictions based on pattern recognition and AI-based algorithms,” said Joerg “Nu” Rosenbohm, Global Solutions Expert at
Kapsch TrafficCom.
“Traffic data enrichment is essential to plan road mobility properly. Thanks to information such as the number of vehicles in transit, the classes of vehicles, the average transit speed, the traffic density and the analysis of the trajectories, it is possible to understand the behavior of traffic in each road section by time bands and predict it for the future. A correct analysis of the actual traffic allows planning intervention areas for possible improvements,” Clerici said.
And the sharing of this data between different stakeholders in a municipality would be beneficial to the overall health and sustainability of the city. “In the increasingly complex urban environment, contextualized data will be critical to understanding events and situations as they unfold in real time, allowing decision makers to react quickly and efficiently. Cities will need to collaborate and share data. They will be able to improve operations through use of deep learning technology to manage large volumes of data and offer actionable insights that will empower agencies to not only deal with real-time issues but to get ahead of problems the system uncovers,” Chenard-Lemire said.