Todo List!

THIS is the real Todo List:

  1. Do maths to work out gaze direction!!!
  2. work out wether to use COM or local min to improve eeye estimate
  3. Make the eye template stick to the face
  4. Track eyes better within the eye template
  5. Use eye movement to track graze location
  6. Use template location to get head location and find gaze location

Real Todo:

  1. make a few bitmap/videos and try tracking eye movement, just use simple no head movement first.
  2. make find maxima etc to I can properly test all the methods.


  1. Finish working out how to find maxima…
  2. WordPress about maxima finding attempts->need to find them first
  3. Test if Gauss func should be a circle or an oval “base”. – perhaps call it a cross section??
  4. Investigate Joelet size… if I ever get round to it :p
  5. Learn some fuzzy logic?? Could replace Gaussian blur? Or help to weight estimates?
  6. Install FFTW.
  7. Read through latest papers and add to literature review… need Alex to check my current first.
  8. read more c++ book 😀

Mostly done:

  1. Work out curvature of paper1… sqrt(Ixx^2 + 2Ixy^2 + Iyy^2) – this is just larger for smaller circles, smaller for larger circles. so smaller circles would have more effect. wordpress about this.
  2. Make/check Gauss func has as constant area underneath it, make A(sigx, sigy) or something. – might be impossible, or need a creative solution. or not relevant, as the image is then just drawn as its fraction from 1-255, so only seems darker, as all points are near the same value, apart from perhaps one or two. maybe should invert image when using high values??
  3. OpenCV muthaaaa