Oliver Jenkins

Just trying to clean up the site, I deleted the wrong datbase by mistake. Luckilly I don’t update too often and had a backup from several a couple of posts ago. The last two posts we’re carefully liften from Googles cache (site:oliverjenkins.com).

One of the upshots is that the Javascript bits I’ve put up have been mangled in the process. Will try to fix when I take a review of the site.

I kind of lost interest with the eye-tracking project. Although the videos of my eye I made did end up being projected on massive screens curtesy of my mate Dirty Henry (V.J), including Big Chill.

Been playing around with a bit more computer vision and image processing techniques. Found this paper that would offer the solution to cluster analysis in the eye tracking project.

Trying to tie alot of skills together at the moment with a little side project. Trying to build up the funds for the hardware and tools needed. I don’t want to disclose too much until things start to move on a bit.

Grabs and tests of identifying the location of the pupil using a IR web cam. This is work in progress, I

I am using a custom filter based on the following tutorial http://www.codeproject.com/cs/media/Motion_Detection.asp

Since the motion tracking methods produces too many errors - reflection off the eye itself causes the library to detect motion across the eye, I am attempting to location the pupil on a frame by frame basis. Also the pupil can move faster than the software can pick up.

I think I need to add a IR Led to have a constant light source, at the moment the camera is using ambient levels of IR and thus the success is dependant on time of day, weather etc

The approach I am working on will requires an analysis of the points detected to find the area with the highest/density or even circular in shape.

Headset

A couple of weekends ago I felt like hacking some hardware. I had seen a series of tutorials online about converting a regular web cam to work with the Infra-Red spectrum and thought I’d give it ago. If you haven’t seen the guides they can easily be found through your favourite search engine.

The nature of the hack is quite simple. The CMOS (image sensor) within the web cam is sensitive to a wide frequency of colours and the manufactures of web cams use a simple filter to block infra-red light and allow through the visible (coloured) spectrum of light. By replacing the filter with one that blocks visible light and lets through Infra-Red we have converted the Web-Cam to one that captures Infra-Red. It appears that most web-cams lent themselves to this trick - so just grab one at random and give it a go. Read the rest of this entry »