Eye tracking model work

    Last week he continued to work on computer modeling eye traking : he optimized the algorithm, now he processes the 1350x768 picture on vaio tz laptop not in 8 minutes, as before, but in 2. There are a couple more ideas on how to speed up the work. Purpose: processing a picture of seconds in 30.

    Well, a video of selecting fixation points after saccades:

    This picture was taken: “velobike: original” And the processing result provided that the distance to the monitor is ~ 40 centimeters, a 20 ”monitor with a resolution of 1680x1050 “ velobike: processing result ” The video above shows how the points of fixation of the eyes are calculated by the algorithm. The duration of fixation (reflected in the heatmap) is calculated as the density of lines over the area. PS For the sake of curiosity, how do other people model the distribution of attention? Here is a video of the simulation found in YouTube:

    velobike: original

    velobike: processing result

    It can be seen that it models somehow differently :) Judging by the comments on this and other videos , a specially trained neural network is used. But my algorithm has the ability to predict saccades :)

    Also popular now: