Computer vision replaces barcodes
Cloudflight developed, validated, deployed and hosted the software systems for optical baggage tracking and identification, leveraging the vast variety of in-house experts. We adapted state of the art machine learning approaches from other identification problem domains, e.g. face recognition, to the requirements of baggage identification.
Tracking baggage by conventional means (such as bar codes etc.) is both costly and error prone, e.g. bar codes can be lost. Furthermore, a continuous tracking of baggage within large scale installations requires a large number of tracking sensors – which are expensive to purchase and maintain.
By extending existing tracking solution and camera based systems, the overall tracking accuracy is improved and new use cases can be covered.
Camera systems mounted at key locations of the baggage transport logistic process (e.g. at check in counters, before and after security checks, at aircraft loading docks, …) can both detect and track baggage and thus ensure a complete audit trail.
This can be applied in a variety of use cases:
- Security: Has the baggage being loaded into the aircraft been checked at the security checkpoint?
- Lost and found: Did the checked in baggage make it into the aircraft?
- Liability: Where was a piece of baggage lost and by whom? At the airport? By the airline?
- Theft prevention: Did a piece of baggage unloaded from an aircraft arrive at the baggage claim area? If so, how long was it there?
Instead of developing a large centralized system, Cloudflight divided the solution into two main parts:
- A small and cost effective camera and image processing services
- and a centralized identification and tracking service
With using this architecture we process images in almost real time. This means that the video doesn’t need to be streamed over the network, which contributes to low network load. Also, a central processing server is not needed (no single point of failure).
Image Processing Service
Cloudflight has created a multi stage real time image processing pipeline consisting of the following steps:
Object detection: detection, localization and classification of baggage on the video stream
- What objects are visible?
- Where are these objects located on the video?
- What type of objects are visible? Persons? Baggage? Cargo container?
Instance segmentation: which parts of the image belong to which object exactly?
- Multiple, possibly touching and overlapping pieces of baggage?
- People handling and covering baggage items?
Object Fingerprinting: finding a numerical feature and a representation of the characteristics of the detected baggage
- What are the features that most differentiate the baggage from others?
- There are millions of black trolleys, but maybe only one has a blue Cloudflight logo on it?
Identification and Tracking Service
The central server receives object fingerprints from the image processing services and stores them in a central database. By comparing these fingerprints – a quick and easy operation – the server can easily compare the current detection of baggage with the previous detection and thus creating a complete audit trail.
- Do you need to track individual items in your production plant?
- Would your business benefit from real time tracking of assets?
- Automated alerts when specific objects leave or enter virtual geo fences?