Thema
Smoothing of Eye Movement Type Labelling
Typ Master, Forschungspraxis, Bachelor, Ing.prax.
Betreuer Mikhail Startsev
Tel.: +49 (0)89 289-28550
E-Mail: mikhail.startsev@tum.de
Sachgebiet Human and Computer Vision
Beschreibung Human eye movements are the most frequent muscle movements in the human body. Commercial solutions to report eye movements already exist, but data processing is still challenging. Different eye movement types carry different information about the observer, they are differently linked to perception. There exists a wide variety of tools and algorithms to produce the labelling of eye movement types given a gaze position recording. Not all of the approaches explicitly take into account a certain continuity in the eye movement types, thus producing “noisy” labels.

The three basic eye movement types of interest for this project are fixations (relatively stationary), saccades (fast point of regard displacement) and smooth pursuit (also called “fixation on a moving target”, relatively continuous motion that follows the trajectory of some stimulus).

With high enough temporal resolution of the recording, it is unlikely, for instance, that the actual sequence of the eye movements has frequently alternating labels. The candidate would apply various techniques to attempt to minimize such noise, whilst evaluating the performance of the resulting system. The result of the project would be a thorough evaluation of the smoothing approaches for the case of eye movement labels, which hopefully helps improve the state-of-the-art recognition system, smooth pursuit classifiers in particular.
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.