Multiple mesh encoding using motion tracking data of objects

1. An apparatus for three-dimensional (3D) geometric data compression, comprising:

a memory configured to store a first 3D geometric mesh having a first data size, wherein

the first 3D geometric mesh is associated with a video that includes a plurality of objects in a 3D space, and

the first 3D geometric mesh includes a 3D representation of the plurality of objects in the 3D space; and

circuitry configured to:

receive motion tracking data of each of the plurality of objects, wherein

the received motion tracking data indicates motion of each of the plurality of objects, from a first position to a second position, in the 3D space; retrieve, from the memory, the first 3D geometric mesh;

compute a centroid of each of a plurality of faces of the first 3D geometric mesh based on an average of vertices of the first 3D geometric mesh;

compute a first distance between adjacent faces of the plurality of faces based on the centroid of each of the plurality of faces;

divide the first 3D geometric mesh into a plurality of vertical clusters based on the computed first distance between the adjacent faces, wherein the plurality of vertical clusters corresponds to the plurality of objects;

segment the first 3D geometric mesh into a plurality of 3D geometric meshes, based on the plurality of vertical clusters and the received motion tracking data of each of the plurality of objects, wherein each 3D geometric mesh of the plurality of 3D geometric meshes corresponds to a respective object of the plurality of objects;

compute a second distance between the centroid of each of the plurality of vertical clusters;

compare the computed second distance with a threshold distance;

segment adjacent faces of the plurality of 3D geometric meshes into a third geometric mesh based on a result of the comparison of the computed second distance with the threshold distance;

identify a set of frames of the video based on the received motion tracking data of each of the plurality of objects; and

encode the plurality of 3D geometric meshes based on

a frame of the identified set of frames of the video,

the segmentation of the first 3D geometric mesh, and

the received motion tracking data of each of the plurality of objects,

wherein a combination of the encoded plurality of 3D geometric meshes has a second data size that is less than the first data size.

2. The apparatus of claim 1 , wherein

the received motion tracking data of the plurality of objects is associated with a plurality of devices, and

the plurality of devices is associated with the plurality of objects.

3. The apparatus of claim 1 , wherein the circuitry is further configured to identify each of the plurality of objects in the 3D space based on the received motion tracking data.

4. The apparatus of claim 1 , wherein the circuitry is further configured to:

distinctly encode each of the plurality of 3D geometric meshes based on a 3D objects encoding technique; and

merge the encoded plurality of 3D geometric meshes into a second 3D geometric mesh having the second data size, based on encoding information of each of the plurality of 3D geometric meshes.

5. The apparatus of claim 4 , wherein the circuitry is further configured to transmit the second 3D geometric mesh as 3D interactive video content to an external device.

6. The apparatus of claim 1 , wherein the circuitry is further configured to:

receive binary images corresponding to the video, wherein the video is captured from a plurality of cameras;

receive camera parameters of the plurality of cameras corresponding to the video;

generate the first 3D geometric mesh having the first data size, based on the received binary images and the received camera parameters; and

store, in the memory, the generated first 3D geometric mesh.

7. The apparatus of claim 6 , wherein the camera parameters include at least one of a position of each of the plurality of cameras in the 3D space, an angle of each of the plurality of cameras, or device setting information of each of the plurality of cameras.

8. The apparatus of claim 1 , wherein the circuitry is further configured to track each of the plurality of 3D geometric meshes based on the received motion tracking data of each of the plurality of objects.

9. The apparatus of claim 8 , wherein each of the plurality of 3D geometric meshes is tracked for a number of frames of the video.

10. The apparatus of claim 8 , wherein the circuitry is further configured to:

merge the tracked plurality of 3D geometric meshes into a second 3D geometric mesh; and

encode the second 3D geometric mesh after the merge, based on a 3D objects encoding technique, wherein the encoded second 3D geometric mesh exhibits the second data size.

11. The apparatus of claim 8 , wherein the circuitry is further configured to:

distinctly encode each of the tracked plurality of 3D geometric meshes, based on information of the first position of each of the plurality of objects, wherein

an image frame that includes the information of the first position of each of the plurality of objects corresponds to a reference frame,

each of the tracked plurality of 3D geometric meshes is encoded based on the reference frame, and

the image frame is associated with the video that includes the plurality of objects in the 3D space; and

merge the encoded plurality of 3D geometric meshes into a second 3D geometric mesh having the second data size, based on the received motion tracking data and encoding information of each of the plurality of 3D geometric meshes.

12. The apparatus of claim 11 , wherein the circuitry is further configured to:

receive direction information of each of the plurality of objects in the 3D space, from a plurality of devices, wherein each device of the plurality of devices is attached to each of the plurality of objects; and

determine at least one motion model associated with the second 3D geometric mesh, based on the received direction information and the received motion tracking data, wherein the at least one motion model indicates at least one cumulative motion paths of at least one group of objects from the plurality of objects in the 3D space.

13. The apparatus of claim 12 , wherein the circuitry is further configured to:

divide the second 3D geometric mesh into a plurality of 3D geometric portions, based on the determined at least one motion model; and

distinctly encode the plurality of 3D geometric portions of the second 3D geometric mesh, based on the determined at least one motion model.

14. A method for three-dimensional (3D) geometric data compression, comprising:

in an apparatus:

storing a first 3D geometric mesh having a first data size, wherein

the first 3D geometric mesh is associated with a video that includes a plurality of objects in a 3D space, and

the first 3D geometric mesh includes a 3D representation of the plurality of objects in the 3D space;

receiving motion tracking data of each of the plurality of objects, wherein

the received motion tracking data indicates motion of each of the plurality of objects, from a first position to a second position, in the 3D space;

retrieving the first 3D geometric mesh;

computing a centroid of each of a plurality of faces of the first 3D geometric mesh based on an average of vertices of the first 3D geometric mesh;

computing a first distance between adjacent faces of the plurality of faces based on the centroid of each of the plurality of faces;

dividing the first 3D geometric mesh into a plurality of vertical clusters based on the computed first distance between the adjacent faces, wherein the plurality of vertical clusters corresponds to the plurality of objects;

segmenting the first 3D geometric mesh into a plurality of 3D geometric meshes, based on the plurality of vertical clusters and the received motion tracking data of each of the plurality of objects, wherein each 3D geometric mesh of the plurality of 3D geometric meshes corresponds to a respective object of the plurality of objects;

computing a second distance between the centroid of each of the plurality of vertical clusters;

comparing the computed second distance with a threshold distance;

segmenting adjacent faces of the plurality of 3D geometric meshes into a third geometric mesh based on a result of the comparison of the computed second dista nce with the threshold distance;

identifying a set of frames of the video based on the received motion tracking data of each of the plurality of objects; and

encoding the plurality of 3D geometric meshes based on

a frame of the identified set of frames of the video,

the segmentation of the first 3D geometric mesh, and

the received motion tracking data of each of the plurality of objects, wherein a combination of the encoded plurality of 3D geometric meshes has a second data size that is less than the first data size.

15. The method of claim 14 , wherein

the received motion tracking data of the plurality of objects is associated with a plurality of devices, and

the plurality of devices is associated with the plurality of objects.

16. The method of claim 14 , further comprising identifying each of the plurality of objects in the 3D space based on the received motion tracking data.

17. The method of claim 14 , further comprising:

distinctly encoding each of the plurality of 3D geometric meshes based on a 3D objects encoding technique; and

merging the encoded plurality of 3D geometric meshes into a second 3D geometric mesh having the second data size, based on encoding information of each of the plurality of 3D geometric meshes.

18. The method of claim 17 , further comprising transmitting the second 3D geometric mesh as 3D interactive video content to an external device.

19. The method of claim 14 , further comprising:

receiving binary images of the video, wherein the video is captured from a plurality of cameras;

receiving camera parameters of the plurality of cameras corresponding to the video;

generating the first 3D geometric mesh having the first data size, based on the received binary images and the received camera parameters; and

storing the generated first 3D geometric mesh.

20. The method of claim 19 , wherein the camera parameters include at least one of a position of each of the plurality of cameras in the 3D space, an angle of each of the plurality of cameras, or device setting information of each of the plurality of cameras.