cyclope.ai logo

New generation AI-powered AID software

Tunnelwatch is an Automatic Incident Detection (AID) software which detection models are based on the latest Deep Learning and Computer Vision technologies. By filtering the major part of the false alarms formerly registered by the traditional system, it widely improves the accuracy of real-time reported information for tunnel operators.

illustration1
Very high precision and reliability

Based on a leading-edge expertise in Deep Learning, Tunnelwatch ensure a very with high detection rate while filtering false alarms

illustration1
Easy to set up and maintain

Thanks to an automatic lane segmentation AI model, camera masks are automatically generated, with the right area classification associated

illustration1
An open system, working with all equipment

Compatible with most cameras, Tunnelwatch has no specific equipment constraints. This scheme facilitates system maintainability while enabling limitless evolution

illustration1
Rapidly adapting to every infrastructure

Our Tunnelwatch algorithms have been already trained on millions of videos coming from different tunnels. This robust knowledge base makes it easy to adapt to every context

Higher precision for tunnel operators

As tunnel environment is subject to multiple constraints and traffic challenges, tunnel management is very sensitive and supervision can become costly, especially when orders for safety equipment add up to each other
------
Thanks to the latest AI progress, Tunnelwatch has leveraged smart video analysis to provide a robust incident detection solution that really improves decision-making within supervisory tunnel centers
carpooling
illustration1
Automated masks

Automatic lane segmentation, on the set-up phase as well as over time, that ensures a mask configuration adaptive maintenance

illustration1
Accurate data

AI can recognize object shapes, correlated situations and incident patterns, by taking into account the overall context parameters such as space, time and simultaneity

illustration1
Inter-cameras intelligence

Thanks to the tracking technology, each vehicle is uniquely identified from one camera to another, enabling a double verification of alarms and display prioritization

illustration1
Monitoring interface

Modern and easy-to-use interface at the hand of tunnel supervisors and integrators, to boost system qualification and supervision efficiency

carpooling

Tunnel Operators

Tunnelwatch provides an intuitive and user-friendly interface, very easy-to-handle. By only detecting relevant and accurate data, it constitutes a real support for decision-making under operations.

Due to an efficient filtering of false alarms, our AI-powered AID solution ensures higher safety on tunnels. In addition, the overall system integration and adaptation is facilitated, generating great savings in both time and money.

Thanks to a smart segmentation algorithm automatically generating well-fitted masks for each camera, Tunnelwatch really simplifies system installation and maintenance for the benefit of tunnel integrators.

High performance

An AI-powered performance

Thanks to a leading-edge expertise in the latest Deep Learning technologies, our detection algorithms have been trained on millions of images to be able to recognize specific shapes and situation patterns. We used AI to strengthen, clarify and synthetize incident detection thanks to an important analytical process: tracking, behavioral analytics, object detection, etc.

image _desc
New feature

Detection of Dangerous Goods

We also has developed an AI video-based solution that can detect Transport of Dangerous Goods licence plates, from a normal camera only. Based on a powerful image processing algorithm, this cutting-edge technology is able to reliably and accurately track the number of Dangerous Goods trucks circulating on the road network. This innovative plug-and-play solution enables a more effective monitoring of these specific vehicles that require special attention from the operators.

image _desc
Tunnelwatch industrial deployment in the Tunnel of Toulon

The challenge of this project was torenew all the AID system without changing the already-installed 96 cameras - to avoid tunnel closure and to leverage a camera infrastructure already paid for. In 2020, Tunnelwatch performance has been successfully evaluated by the Lombardi engineering firm.

Tunnelwatch tested on several Paris region tunnels

The Ile-de-France region road network management public authority - the Direction Interdepartemental d’Ile-de-France - conducted a large test of the Tunnelwatch camera masks segmentation functionnalities, applying it to a broad tunnels selection. In addition, it also tested the entire AID system on 10 cameras within the A6b tunnel.

Tunnelwatch tested by Transurban in Australia

Our AID solution has been successfully tested on 6 cameras within one of the Melbourne area tunnel. Very good performance rates has been reached, especially to detect stopped vehicles at the tunnel entrance and exit. The solution has shown a drastical reduction of false alarms while increasing the detection of proven incidents, usually not registered by the traditional system.

Discover our products

cyclope.ai logo

6 Place du Colonel Bourgoin
Leonard:Paris, 75012 Paris

Subscribe to our newsletter



© Cyclope.ai

welcome

Language