|
|
Subject
Person identification is crucial in many applications such as public and smart home security and thief detection. The common approaches use camera which violates privacy and fail to function in harsh weather and intense light conditions. On the other hand, recent advances in radar technologies have turned it into a robust and privacy-friendly sensor in many civilian applications.
IMEC has recently developed advanced radar imaging algorithms capable of generating point clouds of people from afar. The idea of this topic is to develop these algorithms further to get a high-resolution point cloud in spatial domain based on which people can be identified. Accordingly, the following steps are foreseen for this position:
1. Developing appropriated radar signal processing to generate high-resolution point cloud of a person in spatial domain
2. Developing a machine-learning-based model with the features given by the algorithm developed in the previous step as input and the ID of the person as output.
Kind of work
Master Thesis internship @ IMEC (6 months)
Preceded by (optional) summer internship @ IMEC (1-3 months) (the summer internship alone is not possible)
Framework of the Thesis
In collaborationn with
Dr. André Bourdoux (IMEC) [email protected]
Dr. Seyed Hamed Javadi (IMEC) [email protected]
Expected Student Profile
Following an MSc in a field related to one or more of the following: Electrical engineering, Computer Science, or Applied Computer Science.
Experience with image processing, signal processing, and computer vision. Some knowledge of radar concepts is a plus.
Experience with machine learning and statistics.
Strong programming skills (Python).
Interest in developing state-of-the-art Machine Learning methods and conduct experiments.
Ability to write scientific reports and communicate research results at conferences in English.
|
|
