Eye tracking method and apparatus for anterior segment octa, device, and storage medium

1 . An eye tracking method for anterior segment optical coherence tomography angiography (OCTA), comprising:

acquiring two consecutive frames of pupil images;

separately performing contour extraction on the two frames of pupil images to obtain two corresponding pupil contours;

determining whether the two pupil contours are similar to a reference contour; and

in response to the two pupil contours being similar to the reference contour, calculating a central position offset of one of the two pupil contours with respect to the other pupil contour.

2 . The method according to claim 1 , wherein performing contour extraction on a frame of the two frames of pupil images comprises:

performing polar coordinate transform on the frame of pupil image to obtain a transformed pupil image;

extracting, based on a shortest path algorithm, a boundary of a pupil in the transformed pupil image; and

performing inverse polar coordinate transform on the boundary to obtain a corresponding pupil contour.

3 . The method according to claim 1 , wherein determining whether a pupil contour of the two pupil contours is similar to the reference contour comprises:

calculating a distance between the pupil contour and the reference contour; and

determining, according to a preset distance range and the distance, whether the pupil contour is similar to the reference contour.

4 . The method according to claim 1 , wherein the calculating a central position offset of one of the two pupil contours with respect to the other pupil contour comprises:

acquiring, according to each of the two pupil contours, a center of mass of each of the two pupil contours; and

calculating, according to two centers of mass, the central position offset.

5 . The method according to claim 1 , further comprising:

in response to the two pupil contours being dissimilar to the reference contour, re-acquiring another two consecutive frames of pupil images, separately performing the contour extraction on the two re-acquired consecutive frames of pupil images to obtain two pupil contours corresponding to the two re-acquired consecutive frames of pupil images, and determining whether the two pupil contours corresponding to the two re-acquired consecutive frames of pupil images are similar to the reference contour;

wherein the two re-acquired frames of pupil images are images adjacent to the two consecutive frames of pupil images.

6 . The method according to claim 1 , wherein the reference contour is acquired through the following operations:

acquiring a pupil reference image, wherein the pupil reference image is a reference image captured when a pupil is not obscured;

performing polar coordinate transform on the pupil reference image to obtain a transformed pupil reference image;

extracting, based on a shortest path algorithm, a boundary of the pupil in the transformed pupil reference image; and

performing inverse polar coordinate transform on the boundary to obtain a reference contour of the pupil.

7 . An electronic device, comprising a memory and a processor, wherein the memory is configured to store a computer program, and the processor is configured to, when executing the computer program, implement the following steps:

acquiring two consecutive frames of pupil images;

separately performing contour extraction on the two frames of pupil images to obtain two corresponding pupil contours;

determining whether the two pupil contours are similar to a reference contour; and

in response to the two pupil contours being similar to the reference contour, calculating a central position offset of one of the two pupil contours with respect to the other pupil contour.

8 . A non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, causes the processor to implement the following steps:

acquiring two consecutive frames of pupil images;

separately performing contour extraction on the two frames of pupil images to obtain two corresponding pupil contours;

determining whether the two pupil contours are similar to a reference contour; and

in response to the two pupil contours being similar to the reference contour, calculating a central position offset of one of the two pupil contours with respect to the other pupil contour.

9 . The device according to claim 7 , wherein performing contour extraction on a frame of the two frames of pupil images comprises:

performing polar coordinate transform on the frame of pupil image to obtain a transformed pupil image;

extracting, based on a shortest path algorithm, a boundary of a pupil in the transformed pupil image; and

performing inverse polar coordinate transform on the boundary to obtain a corresponding pupil contour.

10 . The device according to claim 7 , wherein determining whether a pupil contour of the two pupil contours is similar to the reference contour comprises:

calculating a distance between the pupil contour and the reference contour; and

determining, according to a preset distance range and the distance, whether the pupil contour is similar to the reference contour.

11 . The device according to claim 7 , wherein the calculating a central position offset of one of the two pupil contours with respect to the other pupil contour comprises:

acquiring, according to each of the two pupil contours, a center of mass of each of the two pupil contours; and

calculating, according to two centers of mass, the central position offset.

12 . The device according to claim 7 , wherein the processor is further configured to, when executing the computer program, implement the following steps:

in response to the two pupil contours being dissimilar to the reference contour, re-acquiring another two consecutive frames of pupil images, separately performing the contour extraction on the two re-acquired consecutive frames of pupil images to obtain two pupil contours corresponding to the two re-acquired consecutive frames of pupil images, and determining whether the two pupil contours corresponding to the two re-acquired consecutive frames of pupil images are similar to the reference contour;

wherein the two re-acquired frames of pupil images are images adjacent to the two consecutive frames of pupil images.

13 . The device according to claim 7 , wherein the reference contour is acquired through the following operations:

acquiring a pupil reference image, wherein the pupil reference image is a reference image captured when a pupil is not obscured;

performing polar coordinate transform on the pupil reference image to obtain a transformed pupil reference image;

extracting, based on a shortest path algorithm, a boundary of the pupil in the transformed pupil reference image; and

performing inverse polar coordinate transform on the boundary to obtain a reference contour of the pupil.

14 . The storage medium according to claim 8 , wherein performing contour extraction on a frame of the two frames of pupil images comprises:

performing polar coordinate transform on the frame of pupil image to obtain a transformed pupil image;

extracting, based on a shortest path algorithm, a boundary of a pupil in the transformed pupil image; and

performing inverse polar coordinate transform on the boundary to obtain a corresponding pupil contour.

15 . The storage medium according to claim 8 , wherein determining whether a pupil contour of the two pupil contours is similar to the reference contour comprises:

calculating a distance between the pupil contour and the reference contour; and

determining, according to a preset distance range and the distance, whether the pupil contour is similar to the reference contour.

16 . The storage medium according to claim 8 , wherein the calculating a central position offset of one of the two pupil contours with respect to the other pupil contour comprises:

acquiring, according to each of the two pupil contours, a center of mass of each of the two pupil contours; and

calculating, according to two centers of mass, the central position offset.

17 . The storage medium according to claim 8 , wherein the computer program, when executed by the processor, further causes the processor to implement the following steps:

in response to the two pupil contours being dissimilar to the reference contour, re-acquiring another two consecutive frames of pupil images, separately performing the contour extraction on the two re-acquired consecutive frames of pupil images to obtain two pupil contours corresponding to the two re-acquired consecutive frames of pupil images, and determining whether the two pupil contours corresponding to the two re-acquired consecutive frames of pupil images are similar to the reference contour;

wherein the two re-acquired frames of pupil images are images adjacent to the two consecutive frames of pupil images.

18 . The storage medium according to claim 8 , wherein the reference contour is acquired through the following operations:

acquiring a pupil reference image, wherein the pupil reference image is a reference image captured when a pupil is not obscured;

performing polar coordinate transform on the pupil reference image to obtain a transformed pupil reference image;

extracting, based on a shortest path algorithm, a boundary of the pupil in the transformed pupil reference image; and

performing inverse polar coordinate transform on the boundary to obtain a reference contour of the pupil.