Visual experience modulation based on stroboscopic effect

Patent metadata

Field	Value
Publication number	US-2023147659-A1
Application number	US-202117524088-A
Country	US
Kind code	A1
Filing date	Nov 11, 2021
Priority date	Nov 11, 2021
Publication date	May 11, 2023
Grant date	—

Abstract

An approach for modifying in real-time by removing or reinforcing stroboscopic effect from images associated with a viewing experience is disclosed. The approach includes identifying video clips, detecting environmental parameters and calculating display setting. The approach also analyzes display setting using recommendation from GAN, output displaying setting on an AR display and receiving feedback from user.

First claim

What is claimed is:

1 . A computer-implemented method for modifying in real-time stroboscopic effect, by leveraging machine learning, from images, the computer-method comprising:
identifying one or more video clips by the user; determining optical data; determining stroboscopic effect setting; executing stroboscopic effecting setting on the one or more video clips; outputting the video clips based on the updated the stroboscopic effecting setting; and receiving feedback from user.

2 . The computer-implemented method of claim 1 , wherein determining optical data further comprising:
collecting the optical data, wherein optical data includes environmental data and user data; and encoding optical data into latent space.

3 . The computer-implemented method of claim 1 , wherein determining stroboscopic effect setting is based on factors comprising environmental condition, user medical profile, lighting condition, frequency of light, rotating speed of the object, spatio-temporal object visibility score.

4 . The computer-implemented method of claim 1 , wherein stroboscopic effect setting further comprises, enabling/disabling stroboscopic effect, enhancing stereoscopic effect and negating stereoscopic effect.

5 . The computer-implemented method of claim 1 , wherein executing stroboscopic effecting setting on the one or more video clips further comprises:
generating an augmented video by learning discriminator and generators using various loss functions.

6 . The computer-implemented method of claim 1 , wherein outputting the video clips based on the updated the stroboscopic effecting setting further comprises:
superimposing a GAN generated video as an additional layer with an (AR) augmented reality system.

7 . The computer-implemented method of claim 1 , wherein receiving feedback from user further comprises:
updating model parameters; and fine-tuning the model parameters based on the reward score provided by the user using reinforcement learning.

8 . A computer program product for modifying in real-time stroboscopic effect from images, the computer program product comprising:
one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to identify one or more video clips by the user;
program instructions to determine optical data;
program instructions to determine stroboscopic effect setting;
program instructions to execute stroboscopic effecting setting on the one or more video clips;
program instructions to output the video clips based on the updated the stroboscopic effecting setting; and
program instructions to receive feedback from user.

9 . The computer program product of claim 8 , wherein program instructions to determine optical data further comprising:
program instructions to collect the optical data, wherein optical data includes environmental data and user data; and program instructions to encode optical data into latent space.

10 . The computer program product of claim 8 , wherein program instructions to determine stroboscopic effect setting is based on factors comprising environmental condition, user medical profile, lighting condition, frequency of light, rotating speed of the object, spatio-temporal object visibility score.

11 . The computer program product of claim 8 , wherein stroboscopic effect setting further comprises, enabling/disabling stroboscopic effect, enhancing stereoscopic effect and negating stereoscopic effect.

12 . The computer program product of claim 8 , wherein program instructions to execute stroboscopic effecting setting on the one or more video clips further comprises:
program instructions to generate an augmented video by learning discriminator and generators using various loss functions.

13 . The computer program product of claim 8 , wherein program instructions to output the video clips based on the updated the stroboscopic effecting setting further comprises:
program instructions to superimpose a GAN generated video as an additional layer with an (AR) augmented reality system.

14 . The computer program product of claim 8 , wherein program instructions to receiving feedback from user further comprises:
program instructions to update model parameters; and program instructions to fine-tune the model parameters based on the reward score provided by the user using reinforcement learning.

15 . A computer system for modifying in real-time stroboscopic effect from images, the computer system comprising:
one or more computer processors; one or more computer readable storage media; and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:
program instructions to identify one or more video clips by the user;
program instructions to determine optical data;
program instructions to determine stroboscopic effect setting;
program instructions to execute stroboscopic effecting setting on the one or more video clips;
program instructions to output the video clips based on the updated the stroboscopic effecting setting; and
program instructions to receive feedback from user.

16 . The computer system of claim 15 , wherein program instructions to determine optical data further comprising:
program instructions to collect the optical data, wherein optical data includes environmental data and user data; and program instructions to encode optical data into latent space.

17 . The computer system of claim 15 , wherein program instructions to determine stroboscopic effect setting is based on factors comprising environmental condition, user medical profile, lighting condition, frequency of light, rotating speed of the object, spatio-temporal object visibility score.

18 . The computer system of claim 15 , wherein stroboscopic effect setting further comprises, enabling/disabling stroboscopic effect, enhancing stereoscopic effect and negating stereoscopic effect.

19 . The computer system of claim 15 , wherein program instructions to execute stroboscopic effecting setting on the one or more video clips further comprises:
program instructions to generate an augmented video by learning discriminator and generators using various loss functions.

20 . The computer system of claim 15 , wherein program instructions to output the video clips based on the updated the stroboscopic effecting setting further comprises:
program instructions to superimpose a GAN generated video as an additional layer with an (AR) augmented reality system.

Assignees

• IBM

Inventors

• Pandey Diwesh
• Bose Tathagato
• MARVANIYA Smitkumar Narotambhai
• Joseph Arun
• Rakshit Sarbajit K

Classifications

• G06N3/092

  Reinforcement learning · CPC title

• G06N3/094

  Adversarial learning · CPC title

• G06N3/0475

  Generative networks · CPC title

• H04N5/76

  Television signal recording · CPC title

• G11B27/031 Primary

  Electronic editing of digitised analogue information signals, e.g. audio or video signals · CPC title