Systems and methods for virtual camera highlight creation

Patent metadata

Field	Value
Publication number	US-12462563-B2
Application number	US-202017924580-A
Country	US
Kind code	B2
Filing date	Jun 12, 2020
Priority date	Jun 12, 2020
Publication date	Nov 4, 2025
Grant date	Nov 4, 2025

Abstract

A system ( 600 ) includes multiple cameras ( 104 ) disposed about an area ( 102 ), a processor ( 606 ), and a memory ( 608 ) communicatively coupled to the processor. The memory stores instructions that cause the processor to receive a set of video data ( 602 ) associated with the cameras. In an embodiment, the set of video data includes a set of image frames associated with a set of ball tracking data ( 618, 622 ). In an embodiment, the operations include selecting a first image frame ( 626 ) associated with a first change in acceleration and a second image frame ( 628 ) associated with a second change in acceleration. In an embodiment, the operations include generating a set of virtual camera actions ( 630 ) based on the first image frame and the second image frame.

First claim

What is claimed is:

1 . A system, comprising:
a plurality of cameras disposed about an area; at least one processor; and at least one non-transitory, computer-readable media communicatively coupled to the at least one processor, wherein the at least one non-transitory, computer-readable media is configured to store instructions which, when executed, cause the processor to perform operations comprising: receiving a set of video data from the plurality of cameras, the set of video data comprising a set of image frames associated with a set of ball tracking data for a ball; determining, based on the set of image frames and the set of ball tracking data, a peak acceleration of the ball; selecting, based on the set of image frames and the set of ball tracking data, a first image frame associated with a first change in acceleration for the ball and a second image frame associated with a second change in acceleration for the ball, wherein the first change in acceleration for the ball corresponds to the peak acceleration and the second change in acceleration corresponds to a change in direction of the ball; and generating a set of virtual camera actions based on the first image frame and the second image frame.

2 . The system of claim 1 , wherein the instructions, when executed, cause the processor to perform the operations, wherein the operations comprise:
generating a set of virtual image frames associated with the virtual camera actions; and generating a virtual ball model based on the set of ball tracking data.

3 . The system of claim 2 , wherein the set of virtual image frames comprises a first virtual image frame associated with a first time and a second virtual image frame associated with a second time.

4 . The system of claim 2 , wherein the instructions, when executed, cause the processor to perform the operations comprising generating a set of player tracking data for a set of players based on the set of image frames.

5 . The system of claim 4 , wherein the instructions, when executed, cause the processor to perform the operations, wherein the operations comprise generating a set of virtual player models based on the set of player tracking data.

6 . The system of claim 4 , wherein the set of player tracking data comprises a velocity of at least one player or an acceleration of the at least one player.

7 . The system of claim 1 , wherein the set of virtual camera actions comprises a pan, a zoom, a focus, a tilt, or any combination thereof.

8 . The system of claim 1 , wherein the first image frame is a starting image frame of a highlight.

9 . The system of claim 1 , wherein the set of ball tracking data comprises a location of the ball, a velocity of the ball, an acceleration of the ball, or any combination thereof.

10 . A method, comprising:
receiving a set of video data from a plurality of cameras, the set of video data comprising a set of image frames; generating, based on the set of video data, a set of ball tracking data for a ball and a set of player tracking data for a set of players; selecting, based on the set of image frames and the set of ball tracking data, a first image frame associated with a change in acceleration of the ball, wherein the change in acceleration comprises a maximum change in acceleration associated with the set of ball tracking data; and generating a set of virtual image frames based on the set of video data, the set of virtual image frames comprising a first virtual image frame associated with the first image frame.

11 . The method of claim 10 , comprising determining that the change in acceleration of the ball exceeds a threshold change in acceleration.

12 . The method of claim 10 , comprising determining a location of the ball associated with the set of ball tracking data is within an area.

13 . The method of claim 12 , comprising selecting, based on the location of the ball being within the area, a second image frame associated with the location.

14 . The method of claim 13 , comprising displaying the set of virtual image frames, the set of virtual image frames comprising a second virtual image frame associated with the second image frame.

15 . A non-transitory, computer-readable medium comprising instructions that, when executed, are configured to cause a processor to perform operations comprising:
receiving a set of video data from a plurality of cameras, the set of video data comprising a set of image frames; generating, based on the set of video data, a set of ball tracking data for a ball, the set of ball tracking data comprising a trajectory of the ball, wherein the trajectory of the ball comprises a change in acceleration of the ball; determining, based on the set of ball tracking data, a peak acceleration of the ball; determining, based on the trajectory of the ball being within a goal area, a first image frame of the set of image frames associated with the trajectory of the ball, wherein the first image frame corresponds to the peak acceleration of the ball; and generating a set of virtual image frames based on the set of video data, the set of virtual image frames comprising a virtual ball model associated with the set of ball tracking data and a set of virtual player models associated with a set of player tracking data.

16 . The non-transitory, computer-readable medium of claim 15 , wherein the instructions, when executed, cause the processor to perform the operations, wherein the operations comprise selecting a second image frame of the set of image frames based on a change in the trajectory of the ball.

17 . The non-transitory, computer-readable medium of claim 15 , wherein the set of ball tracking data comprises a location of the ball, an acceleration of the ball, or a combination thereof.

18 . The non-transitory, computer-readable medium of claim 15 , wherein the instructions, when executed, cause the processor to perform the operations, wherein the operations comprise selecting a second image frame of the set of image frames based on a location of the ball being within an area, the second image frame associated with the location of the ball.

19 . The method of claim 10 , comprising:
selecting, based on the set of image frames and the set of ball tracking data, a second image frame spaced a first threshold time before the first image frame; and selecting, based on the set of image frames and the set of ball tracking data, a third image frame spaced a second threshold time after the first image frame, wherein the set of virtual camera frames comprises:
a second virtual image frame associated with the second image frame; and
a third virtual image frame associated with the third image frame.

20 . The non-transitory, computer-readable medium of claim 15 , wherein the operations comprise determining that the ball is within a threshold proximity of the goal area.

Assignees

• Intel Corp

Inventors

• Li Wenlong
• Wang Yumeng
• Ling Chen
• Tong Xiaofeng
• Li Qiang

Classifications

• G06T2207/30241

  Trajectory · CPC title

• G06T2207/30224

  Ball; Puck · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• H04N23/64

  Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image · CPC title

• H04N23/90

  Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums · CPC title