Identifying And Extracting Video Game Highlights Based On Audio Analysis

• US 20170065889A1
• Filed: 12/30/2015
• Published: 03/09/2017
• Est. Priority Date: 09/04/2015
• Status: Abandoned Application

• Current Assignee: SRI International, Inc.
• Original Assignee: SRI International, Inc.
• Inventors: Cheng, Hui
• Application Number:
  US14/985,039
• Publication Number:
  US 20170065889A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A63F 13/497 Partially or entirely replaying previous game actions
• CPC Class Codes: A63F 2300/634 for replaying partially or entirely the game actions since the beginning of the game

Abstract

The present invention extends to methods, systems, and computer program products for identifying and extracting game video highlights. Game highlights are identified and extracted from game video recorded or streamed from video games. Game highlights are created by identifying low-level sounds in a game video. Then, game concepts are detected based on identified low-level sounds. A game concept space is created for different types of game concepts. One or more highlights are generated using the concept space based on game knowledge and/or user preference. Multiple highlights can be fused together into a compilation of highlights.

Claims

1. A method for generating highlights from a game video of a video game, the method comprising:

identifying low-level sound features present in the game video by applying audio analysis for detecting multiple sound types, wherein the sound types include at least one sound types defined in the video game sound track;

detecting game concepts based on the low-level sound features and knowledge of audio characteristics of the video game, each of the one or more audio characteristics selected from among;

a relationship, a feature, or a concept of the video game, each of the one or more audio characteristics selected from among;

a spatial characteristic, a temporal characteristic, or a semantic characteristic of the video game;

creating a game concept space by establishing concept types of game concepts of high interest; and

generating one or more highlights based on concepts detected in the video game and user preference.

2. The method of claim 1, wherein detecting game concepts is further based on machine learning that has established relationships between one or more of:

(a) low-level sounds and game concepts and (b) game concepts and game highlights.

3. The method of claim 1, further comprising fusing highlights from one or more concepts appropriately relevant to the game type to form a game highlight.

4. The method of claim 1, wherein the low-level sound features include at least one of character sounds, weapon sounds, object sounds, music and complex sounds.

5. The method of claim 1, wherein audio analysis for detecting multiple sounds includes frequency detection algorithms.

6. The method of claim 1, wherein low-level sound features are tagged based on a library of a game video sound track.

7. The method of claim 6, wherein low-level sound features include tags generated by machine-learning.

8. The method of claim 1, wherein generating one or more highlights based on concept types and user preference comprises referring to a user profile for a user that requested video highlights.

9. The method of claim 1, wherein generating one or more highlights comprises generating one or more highlights based on metadata provided by the manufacturer of the video game.

10. A system for generating highlights from a game video of a video game, the system comprising:

one or more processors;

system memory; and

a game highlight generation engine, using the one or more processors, configured to;

identify low-level sound features present in the game video by applying sound detection algorithms for detecting multiple sound types;

detect game concepts based on the low-level sound features and knowledge of audio relationships of the video game;

create a game concept space by establishing concept types of game concepts of high interest; and

generate one or more highlights based on concept types and user preference.

11. The system of claim 10, wherein the low-level sound features include at least one sound defined by a sound track of the video game.

12. The system of claim 10, wherein detecting is further based on machine learning that has established relationships between low-level sound features and game concepts.

13. The system of claim 10, wherein concepts are tagged with a sound-specific vocabulary.

14. The system of claim 10, wherein portions of the sound-specific vocabulary are machine-learned.

15. The system of claim 10, wherein the game highlight generation engine, using the one or more processors, configured to generate one or more highlights comprises the game highlight generation engine, using the one or more processors, configured to generate one or more highlights based on metadata provided by the manufacturer of the video game.

16. A method for generating highlights from a game video of a video game, the method comprising:

identifying low-level video features present in the game video by applying feature detection algorithms to sections of the game video identified by a sound based highlight detector for detecting multiple sound types;

detecting game concepts based on the low-level video features and knowledge of audio relationships of the video game;

creating a game concept space by establishing concept types of game concepts of high interest; and

generating one or more highlights based on concept types and user preference.