The "move the ball around with your eyes" demo doesn't work at all for me in Safari on a MacBook. I can only move the ball with the mouse. The other demo works okay, but very low accuracy (like 50%). Firefox on the same computer is unusably slow, generates a new "data point" (the visible dot) only every few seconds. Accuracy was about 10%.
Webgazer.js webcam eye tracking on the browser
41–50 of 56 posts
Re: Webgazer.js webcam eye tracking on the browser
#42Earlier quoted context omitted.
In your estimation, how far away are we from eye-tracking software being able to detect the start of a microsaccade, estimate where the gaze is moving toward, and draw new contents on the screen there before the gaze even reaches that point? I would think that by "hacking" into human brain "vulnerabilities" like saccadic masking and chronostasis, such software could potentially yield seriously trippy and mind-alterin…
There’s two parts to that implementation of such a system, and they’re both interesting! The first part is detection of a micro saccade which is already available in research systems I have personally worked on. You can basically crank up the camera frame rate until you’re around the micro saccade range and do some clustering analysis on the positional data to decouple the hardware moving vs the face. The second part…
That's fascinating, but I'm wondering what is the practical value of detecting microsaccades? Aren't they just involuntary twitching?
Re: Webgazer.js webcam eye tracking on the browser
#43Disclaimer, I am the primary engineer of a commercial eye tracking system. Tools like these popup every now and then are a nice tool for rough estimation of gaze. Fixation tracking is a large complicated issue that usually requires some sort of calibration to get more precise results. By sidestepping the calibration problem, much higher subject compliance can be achieved since you don't have a grad student barking co…
In your estimation, how far away are we from eye-tracking software being able to detect the start of a microsaccade, estimate where the gaze is moving toward, and draw new contents on the screen there before the gaze even reaches that point? I would think that by "hacking" into human brain "vulnerabilities" like saccadic masking and chronostasis, such software could potentially yield seriously trippy and mind-alterin…
I believe this might be available in less than 5 years, potentially less than 2, provided both http://www.adhawkmicrosystems.com/ and https://www.kura.tech/ ship and partner with each other. If either one of those companies dies or their technology doesn't work out like I hope, then it might be a while longer.
Re: Webgazer.js webcam eye tracking on the browser
#44Earlier quoted context omitted.
There’s two parts to that implementation of such a system, and they’re both interesting! The first part is detection of a micro saccade which is already available in research systems I have personally worked on. You can basically crank up the camera frame rate until you’re around the micro saccade range and do some clustering analysis on the positional data to decouple the hardware moving vs the face. The second part…
That's fascinating, but I'm wondering what is the practical value of detecting microsaccades? Aren't they just involuntary twitching?
They’re looking to be increasingly more interesting as a biomarker for MS among other things [0]. There’s a lot we still don’t know about our visual systems and the advent of lower cost hardware is allowing huge amount of interesting questions to be hypothesized and tested. It’s a great time to be in the science behind all of this, like the authors at Brown on this paper!
[0] https://iovs.arvojournals.org/article.aspx?articleid=2670267
Re: Webgazer.js webcam eye tracking on the browser
#45Earlier quoted context omitted.
I'm starting to develop RSI in my wrists and hands, and have been looking at eye tracking systems as a potential way to help reduce the amount of clicking that I need to do. I was thinking maybe I could put webgazer.js into a chrome extension and use it to navigate through pages for me, but I don't think it has a click mechanism. fwiw - I'm a huge vimium extension user as keyboarding is less of a strain than mouse mo…
Have you looked at https://eviacam.crea-si.com/ ? Supports Windows, GNU/Linux, and Android, works globally, and runs separately from the browser. (Technically not eye tracking, but close enough)
Wow! I had not, but that looks like it might do the trick. Thanks!
Re: Webgazer.js webcam eye tracking on the browser
#46Sadly my eyes are too small to actually track the pupils. I remember when I got my ID, the lady taking the picture said "Sir, please open your eyes". I looked at her and asked "They are open... you don't see that?" She laughed and asked if I had been smoking. :/
Re: Webgazer.js webcam eye tracking on the browser
#47Can't wait until this makes its way to adtech. You can have sites that hold their "premium" content hostage until you allow camera access and proved (via eye tracking) that you looked at their ad.
“Please drink verification can”
Re: Webgazer.js webcam eye tracking on the browser
#48Whoa. I have a strange mix of reactions to this. It's impressive, and interesting, and worthwhile, slightly creepy, and potentially hugely useful for a11y, democratizing cutting-edge HCI, AR, gaming, etc etc. Surprised it's not getting more attention!
One good thing about webcam access on the web is that browsers require explicit access by the user and browser tabs clearly indicate when a tab is recording with either the mic or camera.
Yes! Hence the "slightly" modifier. :)
Re: Webgazer.js webcam eye tracking on the browser
#49Disclaimer, I am the primary engineer of a commercial eye tracking system. Tools like these popup every now and then are a nice tool for rough estimation of gaze. Fixation tracking is a large complicated issue that usually requires some sort of calibration to get more precise results. By sidestepping the calibration problem, much higher subject compliance can be achieved since you don't have a grad student barking co…
What are your thoughts on newer ML based approaches like MITs "Eye Tracking for Everyone"?
Re: Webgazer.js webcam eye tracking on the browser
#50This seems really cool but it doesn't seem to let me choose which webcam to use- it seems to default to a virtual device I use for streaming that isn't set up right now so I can't really try it out.
I've had this issue with Chrome on OSX where it won't allow camera selection. Firefox (and I think Safari) both do.
It's unclear why Chrome does this - it has a preference for which camera but it seems ignored and takes the most recently installed one.