Low-cost Remote Eyetracking for 19" Display
Loading...
14,551
Loading...
Uploader Comments (piechulla1966)
see all
All Comments (13)
-
On-line documentation now available. See "About This Video". Merry X-mas!
-
This could be very misleading. I use an unconventional approach. Have to find out why it works so well (testing on a range of subjects and cameras).
Loading...
Have you tried using a bullseye sticker on the forehead to inform the computer about the angle and distance of the head so that it can compensate for it?
fatmeteor 1 year ago
@fatmeteor
No, I didn't. But Ralph Schulz tried this at Dresden University of Technology. He wanted to improve the accuracy of a SmartEye system. As far as I can remember, he ended up with dozens of markers in the subjects' faces. In my demonstration, I ONLY rely on the cornea reflex method, i.e. THERE IS NO such thing as an active appearance model. This method can do without.
piechulla1966 1 year ago
Hi YouTubers, please don't use the "Send Message" feature to ask me questions. It's too buggy (internal server errors most of the time). Instead, please use the email address in the documentation. Thanks!
piechulla1966 4 years ago
it doesnt work for me. every time i press calibrate it stops responding. idk what to do.
mikeman999 4 years ago
Sorry mikeman999. This must be frustrating. I use data from both eyes (consensus approach). So, my questions are: Does it find both eye centers (green crosses)? Does it find a cornea reflex (red crosses) in both eyes? Thank you very much for testing!
piechulla1966 4 years ago
The download is on-line (ftr_by_wlp_08.zip). See documentation in "About This Video". Merry X-mas and a happy new Year!
piechulla1966 4 years ago