Functieomschrijving
Flanders Make

Demonstrator Development Using a Dynamic Vision Sensor for High Speed Object Counting

Flanders Make

Flanders Make is the strategic research centre for the manufacturing industry. Our mission is to strengthen the long-term international competitiveness of the Flemish manufacturing industry. That’s why we work together with SMEs and large companies on pre-competitive, industry-driven technological research, resulting in concrete product and production innovation in the vehicle industry, the manufacturing industry, and production environments.

Goal of the internship

A Dynamic Vision Sensor a.k.a Event Camera is a silicon retina with an asynchronous output that encodes brightness changes only (e.g. an example of the output of such a sensor is shown in the right figure vs. traditional camera). These past few years more research labs and companies e.g. IniLABS, PROPHESEE Metavision® ... are developing and building application based on this type of sensor.

In this internship the aim is to build/develop a demonstrator to count objects on a conveyor belt running at high speed using a dynamic vision sensor.

This internship is linked to the Visie in de maakindustrie COOCK project, in which the overall goal is to disseminate results from previous project to the Flemish industry and share knowledge with them about the latest vision technologies available in the market.

In this context, to reach the goal of this internship the student tasks defined are: study of the state of the art (both application and sensor), the realisation of the demonstrator and the development/implementation of the algorithms required to run the demo.

In addition to the use of a DVS sensor to count the object, a 2D camera will be used to do the same thing using out of the shelf solution (e.g. the object detector/counter developed in PILS and based on YOLOv4). A comparison analysis will be done by the student to show capabilities and advantages of using a DVS camera.

Profile Student

  • Bachelor degree in electrical engineering, computer science, or related field;
  • Knowledge of image processing, computer vision, machine learning is highly recommended;
  • Good programming skills in Python or C++
  • Experience in open-source deep learning frameworks such as TensorFlow or PyTorch preferred
  • Passionate by research and new technologies with focus on applications that includes machine learning, deep learning and computer vision
  • Result oriented, responsible and proactive;
  • A good communicator, able to communicate in English;
  • Eager to learn and a team player.

Only EEA or Swiss nationals can be accepted for internships due to work permit regulations.

Practical Data

Internship:

  • The assignment is an internship of min. 4 months to max. 6 months and takes place at the offices of Flanders Make located in Leuven, Belgium.
  • All software and hardware needed for the execution of the project will be provided by Flanders Make.

  • Locatie: Gaston Geenslaan 8, 3001 Leuven / Oude Diestersebaan 133, 3920 Lommel / Karel de Goedelaan 5, 8500 Kortrijk

Interesse?

Voor meer informatie:
Bel SUVI ECKERT
op het nummer: 011790590
Even geduld, uw aanvraag wordt verwerkt
Mail naar uw vrienden
Mail(s) succesvol verstuurd
Er is een fout opgetreden, gelieve contact op te nemen met uw systeem administrator
[sluiten]