An operator responsible for managing and developing an international airport
Product development, AI, ML, IoT
C, C++, Python


An airport operator faced a challenge regarding the safety and security of the airport’s passengers. The operator noticed a recurring issue: toddlers were frequently swept away on airport conveyor belts as they managed to sneak past ticket counters or were put on the belts as entertainment. Not only did this cause distress to passengers, but it also posed potential security risks and operational disruptions. Recognizing the need for a proactive solution, the operator turned to the ITRex anomaly detection team to address the challenge using AI-based video surveillance?

We were tasked with:
Designing and developing an anomaly detection solution capable of detecting anomalies on airport conveyor belts in the real time.
Integrating the system with the control center managing the conveyor belts in order to allow the belts to switch off automatically once an anomaly is detected.


The ITRex team designed an AI-powered solution that runs on the edge of the network on standalone surveillance cameras. The cameras are enhanced with powerful chips that allow running trained AI algorithms locally.
The solution is powered by Beta-Variational Autoencoders (Beta-VAE) and Gaussian Mixture Models (GMM). To train the algorithms, the ITRex team collected around 3,000 hours of video footage showcasing normal behavior from the airport’s security cameras. During training, the algorithms learned to detect any deviations from the normal behavior and pinpoint those in new, unseen footage.
The intelligent surveillance cameras are integrated with the conveyor belt control module via RS-485 (think: a communication protocol used for transmitting data between different devices), which allows automatically stopping a conveyor belt once an anomaly is detected.


Our cooperation with the customer continues to unfold as the ITRex team is testing out the solution on site, collecting new data and continuously updating the algorithms.
The solution successfully detects any deviations from the norm on the airport’s conveyor belt and is expected to be rolled out in production soon.

Latest projects