Stage-/afstudeeropdracht - Computing Science, AI, Applied Physics

Our EO-systems track the position of objects over time. However occasionally objects are not visible for a while, for example a small boat can be temporarily blocked by a large container vessel. This usually results in two tracks of the same object, one before and one after the blocking occurred. Machine learning based re-identification can be used to determine if two different snapshots correspond to the same object.

In this project, you will study the various approaches to (person) re-identification that can be found in the literature and select one or multiple promising approaches for further evaluation using actual data obtained using our systems.

The solution should be suitable for real-time execution on high-end GPU's.

Optionally, you can also work on the actual implementation using C++ and CUDA that can be used in our system.

• Machine Learning
• Machine Vision
• Image Processing
• CUDA

• An interesting internship or graduation assignment within our high-tech, innovative work environment;
• A comfortable, flexible work space in a modern environment;
• An excellent internship allowance;
• Its own student association where you can participate in educational and fun activities.

In the Netherlands, where more than 2200 employees are based, we are located in four cities: Huizen, Delft, Eindhoven and Hengelo (HQ). Together with an extensive ecosystem of knowledge partners, customers and suppliers, we work on radars for naval vessels, cyber security solutions, transportation systems, communication equipment for land forces, cryogenic cooling solutions and research & development for radar tech (in collaboration with TU Delft).

The assignment is done as part of the Electro-Optical (EO) team in the System Engineering department. The EO-team is responsible for analyzing customer requirements regarding EO-systems and translate these to product requirements and functions. In addition, the team is involved with the necessary R&D activities to meet these requirements.

By clicking the application button, you will be navigated to the website of Thales. In case the link is not working anymore, the vacancy has expired and you will no longer be able to apply. We try to keep our job database as up-to-date as possible, we would very much appreciate it if you could let us know in case a link is not working? You can do this by sending an e-mail to vacatures@twente.com. 

Would you like to be kept up-to-date about other interesting jobs in Twente, then sign up here and create your own job account!