|
Application of pupillometry during measurement of the defocused curve
Musilová, Kateřina ; Harabiš, Vratislav (referee) ; Kolář, Radim (advisor)
The aim of this work is to design algorithm that will detect pupil from video. The theoretical knowledge necessary for proper pupil detection is also described in this master’s thesis. Detection is done on 24 videos that are converted to single images. The complete result the dependence of the pupil diameter on the used dioptre. The overall success rate of the algorithm is 88,13 %. The overall error is 11,87 %. For 17 out of 24 patients, it is confirmed that the greater the dioptre, the larger the pupil.
|
|
Eye gaze tracking
Bastl, Petr ; Číp, Pavel (referee) ; Richter, Miloslav (advisor)
This thesis deals with the eye gaze tracking and determining the direction and the place of the view. The overview of methods for determining the view direction is provided here. The direct 3D gaze estimation technique is proposed and implemented. The eye gaze can be estimated by using a single camera and under nature head movement. This paper describes the algorithms for the image processing and the image description. The center of the pupil is determined by the genetic algorithm for the ellipse detection. The procedures of the instrumentation calibration are proposed here as well. The work also addresses the issue of the determining the eye location. Finally, the comparison of the accuracy with similar projects is mentioned in my thesis.
|
| |
|
Design and implementation of eye tracking system
Špaček, Michal ; Janoušek, Oto (referee) ; Kolář, Radim (advisor)
Cieľom tejto práce je design a implementácia systému na sledovanie očí. Sledovanie očí je technológia, ktorá umožňuje meranie a analýzu pohybov očí a správania pohľadu, poskytujúc informácie o pozornosti, vnímaní a kognitívnych procesoch. V práci je diskutovaná potrebná teória k sledovaniu očí, konrétne prehľad anatómie a fyziológie ľudského oka a potom už samotné sledovanie očí, jej delenie, metológia, využite a ďalšie. Pre praktickú časť tejto práce bol vytvorený návrh riešenia, podľa ktorého sa ďalej implementovali obe časti praktickej práce, teda hardwarová a softwarová časť. Bol nameraný dataset, ktorý obsahoval videá zobrazujúce snímky očí a ich hýbanie. Následne bol dataset analyzovaný pomocou softwarového riešenia a diskutovali sa dosiahnuté výsledky z individuálnych častí analýzy.
|
|
Application of pupillometry during measurement of the defocused curve
Musilová, Kateřina ; Harabiš, Vratislav (referee) ; Kolář, Radim (advisor)
The aim of this work is to design algorithm that will detect pupil from video. The theoretical knowledge necessary for proper pupil detection is also described in this master’s thesis. Detection is done on 24 videos that are converted to single images. The complete result the dependence of the pupil diameter on the used dioptre. The overall success rate of the algorithm is 88,13 %. The overall error is 11,87 %. For 17 out of 24 patients, it is confirmed that the greater the dioptre, the larger the pupil.
|
| |
|
Eye gaze tracking
Bastl, Petr ; Číp, Pavel (referee) ; Richter, Miloslav (advisor)
This thesis deals with the eye gaze tracking and determining the direction and the place of the view. The overview of methods for determining the view direction is provided here. The direct 3D gaze estimation technique is proposed and implemented. The eye gaze can be estimated by using a single camera and under nature head movement. This paper describes the algorithms for the image processing and the image description. The center of the pupil is determined by the genetic algorithm for the ellipse detection. The procedures of the instrumentation calibration are proposed here as well. The work also addresses the issue of the determining the eye location. Finally, the comparison of the accuracy with similar projects is mentioned in my thesis.
|