MSc: Edge-based Machine Learning for Low-Resolution Thermal Cameras at RISE Research Institutes of Sweden

The Connected Intelligence Unit is part of RISE Computer Science in Kista. The current research focus is on the Internet of Things. Among the group's key technologies are the Contiki operating system, uIP stack, ContikiRPL, SICSLoWPAN, and lightweight implementation of IPsec and DTLS. The unit conducts projects together with industry and academic partners from Sweden and across the world.

Thesis Description
Low-resolution thermal cameras enable a number of privacy-preserving applications such as counting the number of people in a meeting room. Our earlier work has shown that such an application is feasible even with low-resolution thermal cameras with as few pixels as 32x24 pixels. The results have been achieved with state-of-the-art machine learning methods including transfer learning. The goal of this thesis is to take the current work forward to solve interesting outstanding issues such as larger settings.

Terms:

Start Time: As soon as possible

Scope: 30 hp

Location: RISE Computer Science, Kista, Stockholm

Who are you?
We expect you to have good programming skills in Python and (embedded) C. Basic knowledge or a strong interest in machine learning and in particular deep learning is also a prerequisite.

Welcome with your application!
If this sounds interesting and you would like to know more, please contact Joakim Eriksson, tel. 010 228 43 64 or Thiemo Voigt, tel. 010 228 43 48. Applications should include a brief personal letter, CV, and recent grades. Candidates are encouraged to send in their application as soon as possible but at the latest 1st of January 2021. Suitable applicants will be interviewed as applications are received.
Our union representatives are Ingemar Petermann, Sveriges Ingenjörer, 010-228 41 22 and Linda Ikatti, Unionen, 010-516 51 61.

Master thesis, Embedded systems, Machine Learning, Edge computing, Internet of Things, RISE, Stockholm

Attention: Often you need a pre-approval from your university or study counsellor, to be sure that projects or thesis found on ORU CareerGate can be accepted as part of your education. Please contact the right entity in due time to ensure that you're picking the right project.