Citilog launches Deep Learning deployment on a 700+ camera project in Egypt!

As part of the "ITS Egypt" project, in partnership with its distributor RAET and Autostrade per l'Italia, Citilog completed a demonstration of the CT-ADL (Citilog Applied Deep Learning) product on the Cairo Motorways site, in 2020.

For the Egyptian authorities, the objective of this demonstration was to validate the incident detection functionalities (accident, debris, pedestrians, congestion, slow vehicles and wrong way).

​​​​

 

Results

The results of the demonstration proved that the system was able to detect clearly even in an outdoor inter-urban environment with very disturbed light variations as well as at night with no lighting.

The addition of the latest Deep Learning software called CT-ADL (Citilog Applied Deep Learning) has significantly reduced the number of false positives.

Official detection tests have been carried out by the government with satisfactory results for all types of vehicles (cars, trucks, buses, motorized bicycles).

Conclusions

Following the first conclusive tests that removed all doubts about the possibility of providing a reliable outdoor system in all conditions, Citilog was honoured to receive an order to supply a set of expressways with more than 700 analysis licenses installed directly in the cameras.

These licenses were scheduled to be activated between June and December 2021.

This project is one of the largest deployments of AID systems in the world in open (running) sections.
The project provides further momentum in the deployment of large-scale AID systems!

Deep Learning applied in Incident Management

The first and most simple subset of Artificial Intelligence, Machine Learning, has been integrated into Citilog’s products for a long time. The more complex and resource demanding  Deep Learning is now a reality with CT-ADL (Citilog Applied Deep Learning). The uniqueness of CT-ADL is the ability to run a specifically developed neural network targeting at eliminating  false positive detections while maintaining the increase of hardware requirement to a very limited level: 1 standard additional GPU card can cope with 100 cameras.
 

10 times less false alarms

The results, gathered from multiple sites already benefiting of CT-ADL, show that the amount of false positive detection historically due to shadows, smoke, rain patches, bad weather conditions, is divided by a factor 10 compared to traditional analytics.

This improvement, makes CT-ADL an operational Incident Management solution for tunnels, bridges, and highways even for large number of cameras.