Thema
Vision Based Human-Machine Interaction
Typ Master (preferred), Bachelor
Betreuer Ioannis Agtzidis
Tel.: +49 (0)89 289-28550
E-Mail: ioannis.agtzidis@tum.de
Sachgebiet Human and Computer Vision
Beschreibung As the world moves towards more automation, humans and machines (robotic helpers,
autonomous cars, smart appliances) have to communicate by using new
strategies. Our eyes are one of the strongest explicit and implicit
communication channels in our everyday interaction with other humans. This
natural way of communication has not been completely integrated in our
interaction with machines yet.

We can utilize eye-enabled interaction by using wearable eye tracking. (Remote
RGB camera based eye tracking algorithms are so far very inaccurate +- 7
degrees.) By adding eye tracking along with a scene camera to the whole
system we can quantify the attention of the human factor in the 3D world and
increase the situational awareness of the whole system.

In this project we will start with the simplified scenario of a mapped room
with a single rigid shaped robot. The participant of the experiment will wear
eye tracking glasses with high frame rate scene camera. The student will be
responsible for the integration of a selection of well understood video based
Localization and Mapping (vSLAM), rigid robot pose estimation, eye tracking,
and attention algorithms.
Voraussetzung Knowledge of:
- C++ and/or Matlab
- Linux
Familiarity with:
- Computer vision algorithms
- Eye tracking (is a plus)
Bewerbung If you are interested in this topic, we welcome the applications via the email address above. Please set the email subject to “<Type of application> application for topic 'XYZ'”, ex. “Master’s thesis application for topic 'XYZ'”, while clearly specifying why are you interested in the topic in the text of the message. Also make sure to attach your most recent CV (if you have one) and grade report.