Frame by Frame Time and Space-Based Object Mapping in Multimedia

Patent metadata

Field	Value
Publication number	US-2025218077-A1
Application number	US-202418402228-A
Country	US
Kind code	A1
Filing date	Jan 2, 2024
Priority date	Jan 2, 2024
Publication date	Jul 3, 2025
Grant date	—

Abstract

A computer implemented method processes a video. A processor set identifies frames in the video. The processor set recognizes objects in a frame in the frames. The processor set modifies each of the objects in the frame that do not fit the geospatial model for the frames to form a revised frame for the video.

First claim

What is claimed is:

1 . A computer implemented method for processing a video, the computer implemented method comprising:
identifying, by a processor set, frames in the video; recognizing, by the processor set, objects in a frame in the frames; and modifying, by the processor set, each of the objects in the frame that do not fit a geospatial model for the video to form a revised frame for the video.

2 . The computer implemented method of claim 1 further comprising:
determining, by the processor set, geospatial information for the objects in the frame; and
tagging, by the processor set, the objects in the frame with the geospatial information.

3 . The computer implemented method of claim 2 further comprising:
determining, by the processor set, whether the objects in the frame fit the geospatial model using the geospatial information tagged to the objects.

4 . The computer implemented method of claim 3 , wherein determining, by the processor set, whether the objects in the frame fit the geospatial model comprises:
identifying, by the processor set, a model time context for the frame using the geospatial model; identifying, by the processor set, an object time context for the objects in the frame; and comparing, by the processor set, the object time context identified for the objects to the model time context for the frame.

5 . The computer implemented method of claim 3 , wherein determining, by the processor set, whether the objects in the frame fit the geospatial model comprises:
identifying, by the processor set, a model geographic location for the frame using the geospatial model; identifying, by the processor set, an object geographic location for the objects in the frame; and comparing, by the processor set, the object geographic location for the objects to model geographic location for the frame.

6 . The computer implemented method of claim 3 , wherein determining, by the processor set, whether the objects in the frame fit the geospatial model comprises:
identifying, by the processor set, a model time context and a model geographic location for the frame using the geospatial model; identifying, by the processor set, an object time context and an object geographic location for the objects in the frame; and comparing, by the processor set, the object time context to the model time context for the frame and the object geographic location to model geographic location for the frame.

7 . The computer implemented method of claim 1 , wherein modifying, by the processor set, each of the objects comprises:
removing, by the processor set, an object in the objects from the frame in response to the object not fitting the geospatial model.

8 . The computer implemented method of claim 1 , wherein modifying, by the processor set, each of the objects comprises:
augmenting, by the processor set, an object in the objects in the frame to fit the geospatial model in response to the object not fitting the geospatial model.

9 . The computer implemented method of claim 1 further comprising:
recognizing, by the processor set, the objects in other frames in the frames; and
modifying, by the processor set, each of the objects in the other frames that do not fit the geospatial model.

10 . A computer system comprising:
a processor set; a set of one or more computer-readable storage media; and program instructions, collectively stored in the set of one or more storage media, for causing the processor set to perform the following computer operations:
identify frames in a video;
recognize objects in a frame in the frames; and
modify each of the objects in the frame that do not fit a geospatial model for the video to form a revised frame for the video.

11 . The computer system of claim 10 , wherein the program instructions, collectively stored in the set of one or more storage media, further causes the processor set to perform the following computer operations:
determine geospatial information for the objects in the frame; and tag the objects in the frame with the geospatial information.

12 . The computer system of claim 11 , wherein the program instructions, collectively stored in the set of one or more storage media, further causes the processor set to perform the following computer operation:
determine whether the objects in the frame fit the geospatial model using the geospatial information tagged to the objects, wherein the geospatial model defines a model time context and a model geographic location for the frames.

13 . The computer system of claim 12 , wherein as part of determining whether the objects in the frame fit the geospatial model, the program instructions, collectively stored in the set of one or more storage media, further causes the processor set to perform the following computer operations:
identify the model time context for the frame using the geospatial model; identify an object time context for the objects in the frame; and compare the object time context to the model time context for the frame.

14 . The computer system of claim 12 , wherein as part of determining whether the objects in the frame fit the geospatial model, the program instructions, collectively stored in the set of one or more storage media, further causes the processor set to perform the following computer operations:
identify the model geographic location for the frame using the geospatial model; identify an object geographic location for the objects in the frame; and compare the object geographic location to model geographic location for the frame.

15 . The computer system of claim 12 , wherein as part of determining whether the objects in the frame fit the geospatial model, the program instructions, collectively stored in the set of one or more storage media, further causes the processor set to perform the following computer operations:
identify the model time context and the model geographic location for the frame using the geospatial model; identify an object time context and an object geographic location for the objects in the frame; and compare the object time context to the model time context for the frame and the object geographic location to model geographic location for the frame.

16 . The computer system of claim 10 , wherein as part of determining whether the objects in the frame fit the geospatial model, the program instructions, collectively stored in the set of one or more storage media, further causes the processor set to perform the following computer operation:
remove an object in the objects from the frame in response to the object not fitting the geospatial model.

17 . The computer system of claim 10 , wherein as part of modifying each of the objects, the program instructions, collectively stored in the set of one or more storage media, further causes the processor set to perform the following computer operation:
augment an object in the objects in the frame to fit the geospatial model in response to the object not fitting the geospatial model.

18 . The computer system of claim 10 , wherein the program instructions, collectively stored in the set of one or more storage media, further causes the processor set to perform the following computer operations:
recognize the objects in other frames in the frames; and modify each of the objects in the other frames that do not fit the geospatial model.

19 . A computer program product for processing a video the computer program product comprising:
a set of one or more computer-readable storage media; p

Assignees

• IBM

Inventors

• Pandey Diwesh
• Bose Tathagato

Classifications

• G06T7/74

  involving reference images or patches · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• G06V20/41

  Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49) · CPC title