We use cookies

This website uses cookies to provide necessary website functionality, improve your experience and analyze our traffic. By using our website, you agree to our Privacy Policy and our cookies usage.

Contact us

Our friendly team would love to hear from you.




    or contact us directly at office@cognitum.eu

    This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
    ionicons-v5-e

    Thank you for your interest!

    We will contact you as soon as possible.

    Back to homepage
    Logistics solutions development
    Back to stories

    Container Code Recognition

    A computer vision solution with deep learning techniques.

    software house services

    Highlights

    Our team was tasked with developing a container code recognition solution that could be used in large ports and by logistics companies for efficient cargo management. This product was supposed to reduce personnel costs, speed up the cargo movement and provide general analytics for further use.

    Industry

    Logistics

    Warehouses

    Security

    Team

    1

    Duration

    8 months

    Country

    Turkey

    Challenge

    Some ports still use humans to read container IDs, which takes a long time and leaves room for human error. But people can read even bad, dirty and weak container ids in any weather conditions (bright sunlight, rain, snow when the camera could not work properly). Therefore, our main task was to deliver a solution that would at least not be inferior to people, but at the maximum was higher than human indicators.

    The main difficulty of the project was to build the right deep learning model and find enough quality data for it to learn from.

    Container Code Recognition Solution Engineering

    Solution

    We delivered a computer vision solution with deep learning techniques which needs two or three cameras from the client’s side for reading ID. Dahua, Hikvision, Samsung, Axis cameras are compatible with the solution so customers can use any of them. Its reading accuracy is 98% which is higher than human indicators. 

    With the new solution, it is easy to track how much cargo enters the port and how much leaves it, the location of a particular container and to monitor the process of loading or filling containers.

    System integration with the client’s ecosystem is possible (data is transmitted via TCP or REST API). Since all containers’ data is written to the database, the client can get transparent analytics and reporting.

    Technology Specification

    Cognitum Software House C#
    Cognitum Software House C++
    Cognitum Software House Python

    backend:

    C/ C++/C#, Pyton, Keras, Opencv

    Turn your ideas into projects!

    Let’s talk about your project, just click the button and we will reach you as soon as possible.

    Contact Us