Modelling eye movements during Multiple Object Tracking
|Thesis title in Czech:||Modelling eye movements during Multiple Object Tracking|
|Thesis title in English:||Modelling eye movements during Multiple Object Tracking|
|Key words:||modely, oční pohyby, sledování více objektů, neuronové sítě|
|English key words:||models, eye movements, multiple object tracking, neural networks|
|Academic year of topic announcement:||2011/2012|
|Type of assignment:||diploma thesis|
|Department:||Department of Software and Computer Science Education (32-KSVI)|
|Supervisor:||doc. Mgr. Jiří Lukavský, Ph.D.|
|Author:||hidden - assigned and confirmed by the Study Dept.|
|Date of registration:||31.10.2011|
|Date of assignment:||04.11.2011|
|Confirmed by Study dept. on:||12.12.2011|
|Date and time of defence:||03.09.2012 10:00|
|Date of electronic submission:||05.07.2012|
|Date of submission of printed version:||30.07.2012|
|Date of proceeded defence:||03.09.2012|
|Reviewers:||Mgr. Peter Gabriel Toth|
|People tend to move their eyes towards the objects of their interest. However, when they are asked to pay attention to several objects at once, it is not clear how they are optimizing their eye movements with respect to the positions of the objects and the distances to the other objects within the scene (distractors).
In a typical Multiple Object Tracking experiment a person watches a screen with 8 identical dots. Four dots are highlighted for 2 seconds, and then they turn gray and all dots start to move for 10 seconds. Finally, the motion stops and the person is asked to identify the previously highlighted dots. The task has been used for many experiments on spatial attention in psychology, but in combination with computer-based eye tracking it provides also an interesting challenge for computer scientists. Only few studies so far attempted to model eye movements in this dynamic task, while there are several models designed for static attentional tasks (e.g. visual search).
Goal of the project is to design one or several models of eye movements during Multiple Object Tracking, based on the empirical data and literature. For this purpose it will be necessary to design, implement and evaluate an eye tracking experiment. The eye movement predictions of the proposed model/s will be evaluated in a subsequent experiment, and the performance will be compared with other models.
|Mitchell, T.M. (1997). Machine Learning; MIT Press.
Russell, S.J., Norvig, P. (1995). Artificial Intelligence: A Modern Approach; Prentice Hall.
Pylyshyn, Z. W., & Storm, R. W. (1988). Tracking multiple independent targets: evidence for a parallel tracking mechanism. Spatial Vision, 3(3), 179–197.
Cavanagh, P., & Alvarez, G. A. (2005). Tracking multiple targets with multifocal attention. Trends in Cognitive Sciences, 9(7), 349–354.
Colas, F., Flacher, F., Tanner, T., Bessière, P., & Girard, B. (2009). Bayesian models of eye movement selection with retinotopic maps. Biological Cybernetics, 100(3), 203–214.