Technology to automatically locate ball-holding players in multi-camera video feeds
Methods, systems and apparatuses may provide for technology that selects a player from a plurality of players based on an automated analysis of two-dimensional (2D) video data associated with a plurality of cameras, wherein the selected player is nearest to a projectile depicted in the 2D video data. The technology may also track a location of the selected player over a subsequent plurality of frames in the 2D video data and estimate a location of the projectile based on the location of the selected player over the subsequent plurality of frames.
1. A performance-enhanced computing system comprising:
a plurality of cameras to generate two-dimensional (2D) video data;
a processor coupled to the plurality of cameras; and
a memory coupled to the processor, the memory including a set of instructions, which when executed by the processor, cause the computing system to:
conduct, in response to a height of a projectile being less than a height threshold, an automated analysis of the two-dimensional (2D) video data,
select a player from a plurality of players based on the automated analysis of the 2D video data, wherein the selected player is to be nearest to the projectile depicted in the 2D video data, track a location of the selected player over a subsequent plurality of frames in the 2D video data, and
estimate a location of the projectile based on the location of the selected player over the subsequent plurality of frames.
2. The computing system of claim 1 , wherein the projectile is to be occluded from view in one or more of the subsequent plurality of frames.
3. The computing system of claim 1 , wherein the instructions, when executed, further cause the computing system to conduct the automated analysis over a buffered initial plurality of frames occurring before the subsequent plurality of frames in the 2D video data.
4. The computing system of claim 1 , wherein instructions, when executed, further cause the computing system to conduct the automated analysis in response to a distance between the projectile and one or more of the plurality of players being less than a distance threshold.
5. The computing system of claim 1 , wherein the instructions, when executed, further cause the computing system to estimate, via an artificial neural network, the location of the projectile and locations of a plurality of body parts in a bounding box associated with the location of the selected player.
6. A semiconductor apparatus comprising:
one or more substrates; and
logic coupled to the one or more substrates, wherein the logic is implemented at least partly in one or more of configurable logic or fixed-functionality hardware logic, the logic coupled to the one or more substrates to:
conduct, in response to a height of a projectile being less than a height threshold, an automated analysis of two-dimensional (2D) video data associated with a plurality of cameras;
select a player from a plurality of players based on the automated analysis of the two-dimensional (2D) video data associated with the plurality of cameras, wherein the selected player is to be nearest to a projectile depicted in the 2D video data,
track a location of the selected player over a subsequent plurality of frames in the 2D video data, and
estimate a location of the projectile based on the location of the selected player over the subsequent plurality of frames.
7. The semiconductor apparatus of claim 6 , wherein the projectile is to be occluded from view in one or more of the subsequent plurality of frames.
8. The semiconductor apparatus of claim 6 , wherein the logic coupled to the one or more substrates is to conduct the automated analysis over a buffered initial plurality of frames occurring before the subsequent plurality of frames in the 2D video data.
9. The semiconductor apparatus of claim 6 , wherein the logic coupled to the one or more substrates is to conduct the automated analysis in response to a distance between the projectile and one or more of the plurality of players being less than a distance threshold.
10. The semiconductor apparatus of claim 6 , wherein the logic coupled to the one or more substrates is to estimate, via an artificial neural network, the location of the projectile and locations of a plurality of body parts in a bounding box associated with the location of the selected player.
11. At least one computer readable storage medium comprising a set of instructions, which when executed by a computing system, cause the computing system to:
conduct, in response to a height of a projectile being less than a height threshold, an automated analysis of two-dimensional (2D) video data associated with a plurality of cameras;
select a player from a plurality of players based on the automated analysis of the two-dimensional (2D) video data associated with a-the plurality of cameras, wherein the selected player is to be nearest to a projectile depicted in the 2D video data;
track a location of the selected player over a subsequent plurality of frames in the 2D video data; and
estimate a location of the projectile based on the location of the selected player over the subsequent plurality of frames.
12. The at least one computer readable storage medium of claim 11 , wherein the projectile is to be occluded from view in one or more of the subsequent plurality of frames.
13. The at least one computer readable storage medium of claim 11 , wherein the instructions, when executed, further cause the computing system to conduct the automated analysis over a buffered initial plurality of frames occurring before the subsequent plurality of frames in the 2D video data.
14. The at least one computer readable storage medium of claim 11 , wherein instructions, when executed, further cause the computing system to conduct the automated analysis in response to a distance between the projectile and one or more of the plurality of players being less than a distance threshold.
15. The at least one computer readable storage medium of claim 11 , wherein the instructions, when executed, further cause the computing system to estimate, via an artificial neural network, the location of the projectile and locations of a plurality of body parts in a bounding box associated with the location of the selected player.
16. A method of operating a performance-enhanced computing system, comprising:
conducting, in response to a height of a projectile being less than a height threshold, an automated analysis of two-dimensional (2D) video data associated with a plurality of cameras;
selecting a player from a plurality of players based on the automated analysis of the two-dimensional (2D) video data associated with the plurality of cameras, wherein the selected player is nearest to a projectile depicted in the 2D video data;
tracking a location of the selected player over a subsequent plurality of frames in the 2D video data; and
estimating a location of the projectile based on the location of the selected player over the subsequent plurality of frames.
17. The method of claim 16 , wherein the projectile is occluded from view in one or more of the subsequent plurality of frames.
18. The method of claim 16 , further including conducting the automated analysis over a buffered initial plurality of frames occurring before the subsequent plurality of frames in the 2D video data.
19. The method of claim 16 , further including conducting the automated analysis in response to a distance between the projectile and one or more of the plurality of players being less than a distance threshold.
20. The method of claim 16 , further including estimating, via an artificial neural network, the location of the projectile and locations of a plurality of body parts in a bounding box associated with the location of the selected player.