tried out eviacam. definitely will see my neck getting sore.

Because I really want multi-monitor, glasses-based solutions look like the best options. There are a few projects out there that use IR

Eye tracking seems like the ‘right option’. eyes don’t have much mechanically going on, they move a lot and repetitively anyway


really interesting work at york. essentially parity with mouse is found when “The Eye+SPACE Key (ESK) technique allowed participants to “point” with the eye and “select” by pressing the SPACE key upon fixation.”.

However, eye fatigue was a concern (3.5). Participants complained that staring at so many targets made their eyes dry and uncomfortable. Eye fatigue scored lowest among all the questions. Participants gave eye tracking a modest favorable response overall of 4.5, just slightly higher than the mid-point. Discussions following the experiment revealed that participants liked to use eye tracking and believed it could perform similar to the mouse. Of the three eye tracking techniques, participants expressed a preference for the Eye+SPACE Key technique. Concerns were voiced, however, on the likely expense of eye tracking system, the troublesome calibration procedure, and the uncomfortable requirement of maintaining a fixed head position.


Tried building one of these eye trackers based on babcock 2004. Rather than a wratten 87C, used a plastic garbage bag. bag was not transparent enough to get a good image. Apparently 3.5" floppy disks are great IR filters. in any case, I have one coming in from ebay.

Tried an ebay edmunds optics IR filter. IR filter is not ideal - lets a lot of red light through.

The LTE-4206 940 nm 3mm IR led I’m using for this test is fairly bright.

Safety limits:

(0.06 amps * 1.7 V) / (pi * (2.5 mm^2)) in mW / cm^2 - but the LED is not 100% efficient.

(7.67 mW / (pi * ( 5 mm)^2)) in mW/cm^2

got a cheap gray ms lifecam.

filter is a filter optcast ir 1 dia 43948 po 057040 SM2, edmunds

heated lens with heatgun and removed IR filter glass. night-and-day difference . very bright with this setup now.

framerate is only 12 fps at 640x480, not sure I’ll be satisfied. going to try the ELP camera with a smaller fixed lens with the IR filter removed, just to get a bit better framerate. needed direct 160 C heatgun to remove glue on ir filter. that’s the ticket. works very well.

tried a usb endoscope. connection is unreliable and the filter is too big to mount, and it’s very dim and slow framerate.


While testing with the 3 mm LED mentioned above, I swore I could feel pain from my eye. Indeed:

Sudden temperature elevations of the anterior of the eye due to high-level infrared exposure are readily sensed, causing pain to motivate the eye to move or blink in order to restrict the duration of exposure. Nevertheless, IR-A light initiates a very low visual stimulus and, for this reason, the aversion response that typically shields the eye from excessive continuous irradiation of 0.25 sec or more is not activated.

The norm regarding thermal
lesions for cornea and lens states that the ocular exposure should not exceed 10 mWcm-2
for lengthy exposures (>1000 sec)

Same value as in the paper.

EyeRecToo open-source gaze tracking software!

50 nm wide: