Tollsense is an AI-powered image processing software that can detect in real time the class of a vehicle at the toll plaza, only from a unique image feed and with the same performance as a classification expert. It relieves operators of manual verification on lane equipment classification errors, a tedious and time-consuming process for tolling operators and expensive for road managers.
By automatizing manual reprocessing of tolling classification, operators immediately gain in productivity, with great impact on operational efficiency
Tollsense registers a dramatic reduction in intercom customer calls and customer claims : toll lanes are more fluid and customers more satisfied
Tollsense has been deployed at an industrial level since 2018 on the entire VINCI Autoroutes network. It processes more than 360 millions images per year on 1200 tolling lanes
With an anonymization technology developed in-house, Tollsense is a Privacy-by-design solution that respect user confidentiality by blurring personal data visible on all processed images
Tollsense enables to meet this need for precision by bringing AI at the service of toll managers
Easy-to-use management and analysis tools for supervision, for an AI at the hand of operators
A confidence rate is associated with each Tollsense API response to guarantee high reliability
Unified API, easy to integrate into your toll systems: directly into the lane software or in your back-office, without any equipment costs
Road concession Managers
Tollsense has a very positive impact on the whole toll function : it automates a time-consuming tasks for operational teams while reducing intercom calls and customers claims. It quickly generates great savings, both time and money, for the operations.
Tolling System Integrators
Thanks to a unique Rest API, Tollsense can be easily integrated both on Cloud or On-premise architecture, in tolling back-office or directly into the lane management software, for a fast deployment at an industrial level.
Our Tollsense algorithm has reached unprecedented performance levels: trained on hundreds of millions of images, it integrates almost all specific tolling cases. It can easily be adapted according to the specific needs of each client, to reach a tremendous performance: Deep Learning enables the algorithm to self-learn and continuously improve. Thus, the more data is provided, the more accurate the model is and the more accustomed it is to recognizing complex cases such as snow, trucks, trailers, etc.
Based on leading-edge AI technologies, Tollsense truly allows to generate big savings for the tolling function. The initial investment -only on the software integration part as it does not require any additional equipment - is quickly paid back and the marginal gains are then accumulated over all the concession time, which makes it a product with a very high ROI.
After an important R&D effort, Tollsense was deployed at-scale in 2018 directly into the 1200 toll lanes of the VINCI Autoroutes network. Since then, it has overseen all the Class 2 and 5 transaction checks, directly through the operator qualification tool. The additional automatic verification of all the Class 1 (light vehicle) is currently under implementation.
The ADM Group, the leading road management company in Morocco, decided to test the Tollsense solution on a statistically representative tolling transactions database. The results have been very promising and the collaboration between the two actors is currently being pursued to test smart journey reconstitution through AI plate matching technology.
Cyclope.ai has developed a video-based algorithm to detect PRM (Person with Reduced Mobility) vehicles for ASF needs. Committed to promoting mobility access for all, Cyclope.ai is very proud to have collaborated with VINCI Autoroutes subsidiary on this innovative feature, which ensures PRM vehicles to always pay the fair price at the toll plaza.