Loading...
 
Share this Job
Location: 

Kortrijk, BE

Date:  Nov 22, 2021
Job ID:  4161

Internship: Data set creation and processing using computer vision / machine learning

Barco designs technology that makes everyday life a little better. Seeing beyond the image, we develop sight, sound, and sharing solutions to help you work together, share insights, and wow audiences. Our focus is on three core markets: Enterprise (from meeting and control rooms to corporate spaces), Healthcare (from the radiology department to the operating room), and Entertainment (from movie theaters to live events and attractions). With a team of over 3,300 employees, located all around the globe, we realized sales of 770.01 million euro in 2020. 

Barco designs technology that makes everyday life a little better. Seeing beyond the image, we develop sight, sound, and sharing solutions to help you work together, share insights, and wow audiences. Our focus is on three core markets: Enterprise (from meeting and control rooms to corporate spaces), Healthcare (from the radiology department to the operating room), and Entertainment (from movie theaters to live events and attractions). With a team of over 3,300 employees, located all around the globe, we realized sales of 770 million euro in 2020.

 

A group within Barco – called Barco Labs – is continuously challenging the state-of-the-art and working on technologies that could lead to completely new Barco products. One of their prototypes is showing interesting market potential, and currently we are scaling up the team to transform this exciting prototype into a real product. Keywords of this innovative technology include video analysis, machine learning and automatic camera control.

 

In this context, we are looking for a motivated internship student with background and interest in computer vision and machine learning. Main activities include:

 

  • Extending the current data set. Performing data set collection and data set cleaning (e.g., video editing and synchronization).
  • Writing scripts to automatically analyze the data set, e.g., generating a CSV file with annotations for each frame (e.g., number of people detected, pose estimation results, ID of the person talking…). For this analysis, you will mostly explore third-party off-the-shelf networks and frameworks for, e.g., pose estimation, speech recognition, action recognition… Implementing, evaluating, comparing, and fine tuning these techniques where relevant.
  • Implementing scripts to evaluate the prototype's performance relative to the data set,
  • Supporting the team in other tasks related to computer vision and machine learning,
  • Identifying opportunities for machine learning using the annotated data set, and designing and training neural networks accordingly. Evaluating and refining your approach where necessary.