Intelligent solution for traffic monitoring

Automatic Incident Detection and Traffic Data Collection software solution for smarter and safer mobility.

Leveraging Deep Learning (AI) and 3D Object Tracking, traffix.ai is the Sprinx solution dedicated to critical infrastructures such as roads, highways, tunnels, bridges, and viaducts, capable of analyzing video streams in real-time to classify vehicles and quickly identify anomalous situations in traffic. It combines extremely high detection capability with a drastic reduction in false alarms.

The solution also collects and analyzes statistical data on vehicle flow providing insights on the distribution and composition of traffic to operators and other stakeholders.

Sprinx as an Independent Software Vendor (ISV) is focused on developing software platforms that can be installed, both server-side and at-the-edge, on market hardware and belonging to different brands.

In the case of server-side solutions, the co.exist is entirely agnostic to the camera brand, requiring a standard Onvif-RTSP stream for analysis. The co.exist can be installed on a standard PC platform, using just the CPUs, thanks to the AI inference engine based on the Intel® OpenVINO™ toolkit, or Nvidia GPUs, according to the system requirements.

Activating professional AID algorithms directly at-the-edge standard CCTV cameras represents an interesting and cost-effective solution in distributed architectures. Sprinx, aware of the strategic importance of enriching the number of brands and camera models compatible with its at-the-edge traffix.ai application, has long since undertaken a verification activity aimed at selecting and certifying the devices that guarantee performance levels according to Sprinx standards. As a result, the list of compatible CCTV camera brands and models is constantly updated; for this reason, it is suggested to request the latest updated list in force.

The traffix.ai web user interface also displays a dashboard and an event journal for tuning and maintenance purposes. Upon detecting an event and collecting traffic flow information, alarms and data can be automatically forwarded to third-party systems using standard protocols and displayed on the Sprinx centralized management platform, dragon.

traffix.ai can quickly alert operators in case of accidents, traffic slowdowns or gatherings, sending event notifications, as well as to the centralized management platform Sprinx dragon, to third-party systems (eg VMS, SCADA or ITS platform) capable of triggering scenarios of visualization and intervention.

traffix.ai collects statistical data relating to multimodal traffic (people, bicycles, vehicles), enhancing the role of video surveillance cameras by attributing functions typically delegated to other technologies /sensors.

It is possible to use a graphical interface that allows the visualization of data analytics. Thanks to the data collected by the traffix.ai platform, it is possible to carry out sudden interventions and plan targeted activities to improve traffic and viability conditions and, consequently, the quality of our lives.

More than 15.000 cameras around the world turned into intelligent sensors by Sprinx software since 2009.

Compatible with any IP camera or video encoder that supports RTSP video streaming protocol. This scheme facilitates system maintainability while enabling limitless evolution.

Alarms are automatically forwarded to 3rd party systems, using standard protocols, to quickly alert operators and make instant decisions in case of traffic incidents

Installable directly onboard the Open Platform of video cameras from major CCTV manufacturers on the market.

It allows the construction of hybrid architectures: Server-side (Intel) and at-the-edge integration on a third-party camera.

Centralized upper-level user experience empowered by Dragon.

No more trade-off between high detection accuracy and low false alarm rate, even in challenging outdoor environments

CPU only thanks to the AI inference engine based on Intel OpenVINO. Nvidia GPU cards ideal to upgrade existing hardware to AI-based solution or drastically increase the number of channels on a single server.

Stopped vehicle

Slowdown & Queue

Wrong way

Vehicle classification

Pedestrians

Spilled cargo

Slow/fast vehicle

Lane change

Smoke/loss of visibility

Vehicle counting

• Counting of people, bicycles, and vehicles in transit
• Origin/destination matrix at intersections/roundabouts
• Classification of vehicles in transit (4 classes: motorcycle, car, van/commercial vehicle, truck/bus)
• Average speed of vehicles divided by vehicle class (km/h per class)
• Traffic density, calculated on the basis of the integration of multiple data