Head and eye tracking

Abstract

Embodiments of the invention relate to a method of extracting eye velocity information from a video footage having a plurality of frames, comprising detecting at least part of an eye in at least two frames of the video footage, applying an optical flow algorithm to the at least two frames of the video footage to extract pixel velocity information, and determining a statistical measure from the pixel velocity information within the detected at least part of the eye. Other embodiments of the invention relate to a method of extracting head image trajectory information from a video footage having a plurality of frames, comprising detecting at least part of a facial region of the head image in at least two frames of the video footage, determining a measure of the movement of the at least part of a facial region between the at least two frames, and determining a transformation map from the measure of the movement.

1 . A method of evaluating visual performance or visual health to detect vision problems, comprising:
 providing a visual stimulus in front of eye(s) of a subject, the stimulus effective to elicit optokinetic nystagmus,   obtaining video footage of the subject watching the stimulus,   applying an algorithm to the video footage to detect at least part of an eyeball of the subject and linear movement of the eyeball within the video footage, while also detecting movement of a head of the subject from movement of a facial feature other than an eyeball within the video footage, and compensating for the head movement within the video footage, to determine a presence of optokinetic nystagmus in response to the stimulus,   evaluating visual performance or visual health from the presence or absence or strength of optokinetic nystagmus to identify whether the stimulus gained the subject's attention indicating the subject was able to see the stimulus, and   outputting an indicator of visual performance or visual health based on whether the subject was able to see the stimulus.   
     
     
         2 . The method as claimed in  claim 1  including compensating for the head movement within the video footage by moving or cropping frames in the video footage such that a facial region within the frames is held constant between frames. 
     
     
         3 . The method as claimed in  claim 1  comprising detecting at least part of an eyeball of the subject and linear movement of the eyeball within the video footage by extracting from the video footage pixel velocity information relating to linear movement of at least part of the eyeball in response to the stimulus. 
     
     
         4 . The method as claimed in  claim 1  wherein the at least part of the eyeball is a region of contrast discontinuity of the eyeball. 
     
     
         5 . The method as claimed in  claim 1  wherein the at least part of the eyeball is a limbus portion of the eyeball. 
     
     
         6 . An eye tracking system for evaluating visual performance or visual health to detect vision problems comprising:
 a visual stimulus arrangeable in front of the eye(s) of a subject, the stimulus operable to elicit optokinetic nystagmus,   a camera arranged to capture footage of an eye or eyes of the subject watching the visual stimulus, and   a controller configured to receive the footage of the eye and perform steps of:
 detecting at least part of an eyeball of the subject and linear movement of the eyeball within the video footage, while also detecting movement of a head of the subject from movement of a facial feature other than an eyeball within the video footage, and compensating for the head movement within the video footage, to determine a presence of optokinetic nystagmus in response to the stimulus, 
 evaluating visual performance or visual health from the presence or absence or strength of optokinetic nystagmus to identify whether the stimulus gained the subject's attention indicating the subject was able to see the stimulus, and 
 outputting an indicator of visual performance or visual health based on whether the subject was able to see the stimulus. 
   
     
     
         7 . The eye tracking system as claimed in  claim 6  wherein the controller is configured to compensate for the head movement within video footage by moving or cropping frames in the video footage such that a facial region within the frames is held constant between frames. 
     
     
         8 . The eye tracking system as claimed in  claim 6  wherein the controller is configured to detect at least part of an eyeball of the subject and linear movement of the eyeball within the video footage by extracting from the video footage pixel velocity information relating to linear movement of at least part of the eyeball in response to the stimulus. 
     
     
         9 . The eye tracking system as claimed in  claim 6  wherein the at least part of the eyeball is a region of contrast discontinuity of the eyeball. 
     
     
         10 . The eye tracking system as claimed in  claim 6  wherein the at least part of the eyeball is a limbus portion of the eyeball.