Meet ContextCheck: Our Open-Source Framework for LLM & RAG Testing! Check it out on Github!


Client: SITA

Luggage Tracking System and Digital Twin

Case study details


SITA is the world’s leading air transport communications and information technology specialist. It delivers solutions that cover almost every aspect of airports infrastructure and processes: operational, baggage, and passenger process.

SITA, a company providing advanced digital solutions designed for airport infrastructure, was looking for AI experts able to complement their offer. The task that needed to be handled was not easy, as it was not just about revamping the existing solution.

Addepto was responsible for building up the Image Recognition system that was supposed to replace the legacy one based on barcodes.



Challenge


SITA was constantly looking for ways to improve its offering, and computer vision technology seemed a missing piece in the whole puzzle. It was considered an “umbrella” technology able to provide an overall view of everything going on in airports, from luggage recognition through people recognition and predicting events such as prolonged queues, crowdy “kiss and ride” space, and so on.

In the “before” state, the specific processes were handled in silos. When the various elements were collected and presented independently, it wasn’t easy to see the overall picture and how all the elements interact.



Approach


Addepto team has started with data collection and aggregations from various operational systems, sensors, and cameras. The goal was to provide operational information in real-time for decision-making. Additionally, passenger and baggage tracking solutions were implemented to meet all pandemic standards.

Addepto delivered an entire platform, including real-time UI for airport operations analysis. The application is 3D based and allows users to interact with some chosen parts.



Goal


The ultimate goal of partnering SITA with Addepto was to complement the SITA’s offer in terms of airport facilities with Intelligent Tracking System dedicated to luggage tracking, and Digital Twin to grasp the overall happenings in the airports.



Outcome


Addepto delivered:

  • Intelligent Tracking System dedicated to luggage recognition
  • Digital Twin to grasp the overall happenings in the airports

Challenge

Replacement of old, legacy systems with AI solutions


SITA, a worldwide company focused on creating solutions dedicated to airport infrastructure, is constantly looking for ways to improve its offering. Computer vision technology seemed a missing piece in the whole puzzle.

Advanced computer vision solutions would facilitate various processes in airport operations, from luggage tracking through people recognition and predicting events such as prolonged queues, crowdy “kiss and ride” space, and so on.

The thing is, there was no proper infrastructure and software able to process the images acquired from cameras. The specific processes were handled in silos. Information about everything that happened at an airport was mostly available at more advanced control centers. However, because the various elements were collected and presented independently, it wasn’t easy to see the overall picture and how all the elements interact.

Computer vision technology was seen as a silver bullet able to gather all data under one umbrella, providing an overall so-called “helicopter” view of everything going on in airports.

In practice, it required to set – on the one hand – building infrastructure, which was a part that SITA was accountable for, and – on the other – building AI modules that are able to analyze the images coming from videos. The latter part is what Addepto was hired to do.



Approach

AI solutions able to provide operational information in real-time for decision-making


Addepto team has started with data collection and aggregations from various operational systems, sensors, and cameras. The goal was to provide operational information in real-time for decision-making.


During project development, our team worked on:


  • Passenger and baggage tracking solutions were implemented to meet all pandemic standards.
  • Addepto delivered an entire platform, including real-time UI for airport operations analysis. The application works as an interactive map, on which we draw all the visualization.
  • The system was based on Deep Learning modules enhanced with some classic AI algorithms to adjust to specific business SITA's requirements. Currently, it is working on a test environment, gathering data and gathering data to fine-tune the models for better accuracy of its analysis.
  • With time both systems will work only better. The more data will be trained; the better result will be delivered, and - as it is an umbrella technology - it could provide more accurate overall views not only on the current situation but also on the future events.

Goal

Provide operational information in real-time for decision-making


The ultimate goal of partnering SITA with Addepto was to complement the SITA’s offer in terms of airport facilities. In practice, the assignment was divided into two partial projects: an intelligent tracking system dedicated to luggage recognition and Digital Twin to grasp the airport’s overall happenings.

An intelligent tracking system was supposed to replace the current barcode-based system that handled tracking with lasers. It was costly and non-scaleable, so SITA was looking for something more affordable, expandable, and future-proof. Computer vision technology turned out to be it, especially since if the camera network had been set, the images from it could be re-used for many other purposes.


Intelligent Tracking System dedicated to luggage tracking


Digital Twin to grasp the overall happenings in the airports


Outcome

AI solutions for airport


Prepared AI solutions processed tons of videos in hours and with high accuracy find missed baggage and can track passengers and provide based on it operational information. It saves a lot of working hours and optimizes airport costs.

The decision-making process based on the overall picture of airport operations was significantly improved. In addition to showing what is happening now, we can also choose a moment in history and replay exactly what happened in the past. This is a very effective way to investigate how the disruption is handled and determine what can be done better next time.



Before


  • Bar-code-based laser tracking system for luggage monitoring that was costly and non-scaleable
  • Analyzing the current situation by airport employees, which was reactive and non-effective


After


  • Computer Vision-based tracking system for luggage minitoring that provides complete automation
  • Digital Twin, a virtual representation of real-life objects updated from real-time data able to recognize, detect, and – with time – predict future airports events

About Addepto


Addepto, a growing company developing innovative data-based and AI-related solutions, supports increasing efficiency with intelligent computer vision system.


We support digital transformation at companies operating in Manufacturing Aerospace, to increase the efficiency of their performance with Machine Learning methods and data processing.


About us


We are recognized as one of the best AI, BI, and Big Data consultants


We helped multiple companies achieve their goals, but - instead of making hollow marketing claims here - we encourage you to check our Clutch scoring.

Let's discuss
a solution
for you



Edwin Lisowski

will help you estimate
your project.










Required fields

For more information about how we process your personal data see our Privacy Policy





Message sent successfully!