Abstract | ||
---|---|---|
A way to improve gaze tracking by spectral imaging is presented. Spectral still and video cameras enabled a collection of a novel database consisting of 180 multispectral eye movement videos and 30 spectral images of the eyes of 30 voluntary human subjects. Unfavorable conditions, such as eyewear reflections, extreme angles and make-up were incorporated. Unlike conventional RGB and gray scale eye tracking a seven-channel spectral video capture over the wavelength range of 380-1000 nm, in addition with spectral still images in the range of 450-950 nm, provided a detailed acquisition of spectral signatures of the eye and its surroundings. These signatures can be exploited to create new methodologies for imaging, training, analysis and interpretation of eye tracking data in harsh conditions.
|
Year | DOI | Venue |
---|---|---|
2016 | 10.1145/2968219.2968335 | UbiComp '16: The 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing
Heidelberg
Germany
September, 2016 |
Keywords | Field | DocType |
Multispectral video, Hyperspectral Image, Eye Tracking, Spectral database | Eyewear,Computer vision,Spectral imaging,Video capture,Computer science,Multispectral image,Eye movement,Eye tracking,Artificial intelligence,RGB color model,Spectral signature,Database | Conference |
ISBN | Citations | PageRank |
978-1-4503-4462-3 | 2 | 0.41 |
References | Authors | |
3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
ana gebejes | 1 | 3 | 1.15 |
Pauli Fält | 2 | 12 | 3.63 |
Roman Bednarik | 3 | 561 | 48.77 |
Markku Hauta-Kasari | 4 | 72 | 18.97 |