Measuring torsional eye movements by tracking stable iris features.
Bottom Line: In this method, we track iris features that have been identified as Maximally Stable Volumes.These features, which are stable over time, are dark regions with bright borders that are steep in intensity.The advantage of Maximally Stable Volumes is that they are robust to nonuniform illumination and to large changes in eye and camera position.
Affiliation: Institute of Medical Device Engineering, FH OO Forschungs & Entwicklungs GmbH, Upper Austria University of Applied Sciences, Garnisonstr 21, 4020 Linz, Austria. firstname.lastname@example.orgShow MeSH
Related in: MedlinePlus
Mentions: In our application of the Maximally Stable Volumes detector, we choose the third dimension to be time, not space, which means that we can identify two-dimensional features that persist in time. The resulting features are maximally stable in space (2-D) and time (1-D), which means that they are 3-D intensity troughs with steep edges. Our implementation is based on the VLFeat library written by Vedaldi and Fulkerson (2008). However, the method of Maximally Stable Volumes is rather memory intensive, meaning that it can only be used for a small number of frames (in our case, 130 frames) at a time. Thus, we divide up the original movie into shorter overlapping movie segments for the purpose of finding features. We use an overlap of four frames, since the features become unreliable at the ends of each submovie. We set the parameters of the Maximally Stable Volumes detector such that we find almost all possible features. Of these features, we only use those that are near to the detected pupil centre (up to 6 mm away) and small (smaller than roughly 1% of the iris region). We remove features that are large in angular extent (the pupil and the edges of the eyelids), as well as features that are further from the pupil than the edges of the eyelids (eyelashes). We also remove features on the borders of the polar transformed images because these change size as they shift across the border, thus causing them to provide incorrect estimates of the torsional status of the eye. Fig. 2b shows the remaining features found in the image in Fig. 2a.
Affiliation: Institute of Medical Device Engineering, FH OO Forschungs & Entwicklungs GmbH, Upper Austria University of Applied Sciences, Garnisonstr 21, 4020 Linz, Austria. email@example.com