18094879. EVENT PROGRESS DETECTION IN MEDIA ITEMS simplified abstract (GOOGLE LLC)

From WikiPatents
Jump to navigation Jump to search

EVENT PROGRESS DETECTION IN MEDIA ITEMS

Organization Name

GOOGLE LLC

Inventor(s)

Jue Wang of San Jose CA (US)

EVENT PROGRESS DETECTION IN MEDIA ITEMS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18094879 titled 'EVENT PROGRESS DETECTION IN MEDIA ITEMS

Simplified Explanation

The patent application describes a method for analyzing frames from a media item to identify and divide an event into different time periods. Here are the key points:

  • Frames from a media item are sampled and analyzed to identify potential event periods.
  • Each frame is checked to determine if a candidate event period meets certain conditions.
  • If a candidate event period satisfies the conditions, it is identified as an actual event period.
  • Mapping data is generated to associate each actual event period with a timestamp from the respective frame.

Potential applications of this technology:

  • Video editing software could use this method to automatically divide recorded events into different time periods for easier editing.
  • Sports analysis tools could utilize this method to identify and analyze specific moments or periods within a game or match.
  • Content recommendation systems could use this method to identify and categorize different segments within a video for more accurate recommendations.

Problems solved by this technology:

  • Manual identification and division of event periods in media items can be time-consuming and subjective. This method automates the process, saving time and ensuring consistency.
  • It can be challenging to accurately identify specific moments or periods within a video. This method provides a systematic approach to identify and categorize event periods.

Benefits of this technology:

  • Increased efficiency in video editing and analysis processes by automating the identification and division of event periods.
  • Improved accuracy in identifying and categorizing specific moments or periods within a video.
  • Consistency in the identification and division of event periods, reducing subjective interpretation.


Original Abstract Submitted

One or more frames sampled from a first media item of an event are analyzed to identify one or more candidate event periods within the one or more frames. For each of the one or more frames, whether a candidate event period of the one or more candidate event periods satisfies one or more conditions is determined. Responsive to determining that the candidate event period of the one or more candidate event periods satisfies the one or more conditions, the candidate event period is identified as an actual event period used to divide a time the event. Mapping data that maps the actual event period to a timestamp associated with a respective frame of the one or more frames of the first media item is generated.