Trajectory tracking method and apparatus, computer device, and storage medium

1. A trajectory tracking method for a computer device, comprising:

performing motion tracking on head images in a plurality of video frames, to obtain motion trajectories corresponding to the head images;

acquiring face images corresponding to the head images in the video frames, to obtain face image sets corresponding to the head images;

determining from the face image sets corresponding to the head images, at least two face image sets having same face images; and

combining motion trajectories corresponding to the at least two face image sets having same face images, to obtain a final motion trajectory of trajectory tracking.

2. The trajectory tracking method according to claim 1 , wherein:

before the performing motion tracking on head images in a plurality of video frames, the method further comprises:

performing head detection and face detection on the plurality of video frames, to determine head images and face images in the video frames; and

determining head images and face images that are in the video frames and belong to a same person, and establishing correspondences between the head images and the face images that belong to a same person; and

the acquiring face images corresponding to the head images in the video frames comprises:

acquiring according to the established correspondences, the face images corresponding to the head images in the video frames.

3. The trajectory tracking method according to claim 2 , wherein the determining head images and face images that are in the video frames and belong to a same person comprises:

obtaining the area overlap ratios between the head images and the face images that are determined from the video frames; and

determining according to the area overlap ratios obtained from the video frames, head images and face images that are in the video frames and belong to a same person.

4. The trajectory tracking method according to claim 3 , wherein the determining according to the area overlap ratios obtained from the video frames, head images and face images that are in the video frames and belong to a same person comprises:

performing bipartite graph optimal matching on the head images and the face images in the video frames according to the area overlap ratios obtained from the video frames; and

determining that head images and face images that are in the video frames and match each other belong to a same person.

5. The trajectory tracking method according to claim 1 , wherein the determining from the face image sets corresponding to the head images, at least two face image sets having the same face images comprises:

selecting two face image sets from the face image sets corresponding to the head images;

obtaining similarities among face images in the two face image sets, to obtain a plurality of similarities; and

determining, in a case that a similarity reaching a first preset similarity exists in the plurality of similarities, that the two face image sets have same face images.

6. The trajectory tracking method according to claim 5 , wherein before the determining that the two face image sets have same face images, the method further comprises:

obtaining an average similarity of the plurality of similarities in a case that none of the plurality of similarities reaches the first preset similarity; and

determining, in a case that the average similarity reaches a second preset similarity, that the two face image sets have same face images, the second preset similarity being less than the first preset similarity.

7. The trajectory tracking method according to claim 5 , wherein the obtaining similarities among face images in the two face image sets comprises:

separately selecting one face image from the two face image sets, to obtain two face images;

separately obtaining multidimensional image features of the two face images, to obtain a first image feature set and a second image feature set; and

obtaining a distance between the first image feature set and the second image feature set, and using the obtained distance as a similarity between the two face images.

8. A computer device, comprising:

a memory storing computer-readable instructions; and

a processor coupled to the memory and, when executing the computer-readable instructions, configured to perform:

performing motion tracking on head images in a plurality of video frames, to obtain motion trajectories corresponding to the head images;

acquiring face images corresponding to the head images in the video frames, to obtain face image sets corresponding to the head images;

determining from the face image sets corresponding to the head images, at least two face image sets having same face images; and

combining motion trajectories corresponding to the at least two face image sets having same face images, to obtain a final motion trajectory of trajectory tracking.

9. The computer device according to claim 8 , wherein:

before the performing motion tracking on head images in a plurality of video frames, the processor is further configured to perform:

performing head detection and face detection on the plurality of video frames, to determine head images and face images in the video frames; and

determining head images and face images that are in the video frames and belong to a same person, and establishing correspondences between the head images and the face images that belong to a same person; and

the acquiring face images corresponding to the head images in the video frames comprises:

acquiring according to the established correspondences, the face images corresponding to the head images in the video frames.

10. The computer device according to claim 9 , wherein the determining head images and face images that are in the video frames and belong to a same person comprises:

obtaining the area overlap ratios between the head images and the face images that are determined from the video frames; and

determining according to the area overlap ratios obtained from the video frames, head images and face images that are in the video frames and belong to a same person.

11. The computer device according to claim 10 , wherein the determining according to the area overlap ratios obtained from the video frames, head images and face images that are in the video frames and belong to a same person comprises:

performing bipartite graph optimal matching on the head images and the face images in the video frames according to the area overlap ratios obtained from the video frames; and

determining that head images and face images that are in the video frames and match each other belong to a same person.

12. The computer device according to claim 8 , wherein the determining from the face image sets corresponding to the head images, at least two face image sets having the same face images comprises:

selecting two face image sets from the face image sets corresponding to the head images;

obtaining similarities among face images in the two face image sets, to obtain a plurality of similarities; and

determining, in a case that a similarity reaching a first preset similarity exists in the plurality of similarities, that the two face image sets have same face images.

13. The computer device according to claim 12 , wherein before the determining that the two face image sets have same face images, the processor is further configured to perform:

obtaining an average similarity of the plurality of similarities in a case that none of the plurality of similarities reaches the first preset similarity; and

determining, in a case that the average similarity reaches a second preset similarity, that the two face image sets have same face images, the second preset similarity being less than the first preset similarity.

14. The computer device according to claim 12 , wherein the obtaining similarities among face images in the two face image sets comprises:

separately selecting one face image from the two face image sets, to obtain two face images;

separately obtaining multidimensional image features of the two face images, to obtain a first image feature set and a second image feature set; and

obtaining a distance between the first image feature set and the second image feature set, and using the obtained distance as a similarity between the two face images.

15. A non-transitory computer-readable storage medium storing computer program instructions executable by at least one processor to perform:

performing motion tracking on head images in a plurality of video frames, to obtain motion trajectories corresponding to the head images;

acquiring face images corresponding to the head images in the video frames, to obtain face image sets corresponding to the head images;

determining from the face image sets corresponding to the head images, at least two face image sets having same face images; and

combining motion trajectories corresponding to the at least two face image sets having same face images, to obtain a final motion trajectory of trajectory tracking.

16. The non-transitory computer-readable storage medium according to claim 15 , wherein:

before the performing motion tracking on head images in a plurality of video frames, the processor is further to perform:

performing head detection and face detection on the plurality of video frames, to determine head images and face images in the video frames; and

determining head images and face images that are in the video frames and belong to a same person, and establishing correspondences between the head images and the face images that belong to a same person; and

the acquiring face images corresponding to the head images in the video frames comprises:

acquiring according to the established correspondences, the face images corresponding to the head images in the video frames.

17. The non-transitory computer-readable storage medium according to claim 16 , wherein the determining head images and face images that are in the video frames and belong to a same person comprises:

obtaining the area overlap ratios between the head images and the face images that are determined from the video frames; and

determining according to the area overlap ratios obtained from the video frames, head images and face images that are in the video frames and belong to a same person.

18. The non-transitory computer-readable storage medium according to claim 17 , wherein the determining according to the area overlap ratios obtained from the video frames, head images and face images that are in the video frames and belong to a same person comprises:

performing bipartite graph optimal matching on the head images and the face images in the video frames according to the area overlap ratios obtained from the video frames; and

determining that head images and face images that are in the video frames and match each other belong to a same person.

19. The non-transitory computer-readable storage medium according to claim 15 , wherein the determining from the face image sets corresponding to the head images, at least two face image sets having the same face images comprises:

selecting two face image sets from the face image sets corresponding to the head images;

obtaining similarities among face images in the two face image sets, to obtain a plurality of similarities; and

determining, in a case that a similarity reaching a first preset similarity exists in the plurality of similarities, that the two face image sets have same face images.

20. The non-transitory computer-readable storage medium according to claim 19 , wherein before the determining that the two face image sets have same face images, the method further comprises:

obtaining an average similarity of the plurality of similarities in a case that none of the plurality of similarities reaches the first preset similarity; and

determining, in a case that the average similarity reaches a second preset similarity, that the two face image sets have same face images, the second preset similarity being less than the first preset similarity.