Spherical Video Copyright Detection via Modified Projection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods struggle to detect copyrighted video content embedded within spherical video content, particularly when it is superimposed or stitched at non-default viewing locations or distorted, making it difficult for fingerprinting techniques to identify matches.

Innovation Solution

The method involves projecting spherical video content onto a two-dimensional region using a modified equirectangular projection, dividing the frame into tiles, and analyzing each tile for likelihood of containing copyrighted content using video and audio fingerprinting techniques, with a coordinate system based on latitude and longitude, to identify matches with reference content items.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If spherical video content is projected to a two-dimensional region using a modified equirectangular projection, then the detection accuracy of copyrighted content is improved, but the complexity of the processing system increases

Engineering Contradiction:
Improvedetection accuracyVSAvoidprocessing system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The spherical video content is divided into multiple tiles after projection, where each tile represents a specific region of the sphere. This segmentation allows the system to process and analyze smaller portions independently, improving detection accuracy while managing computational complexity through divide-and-conquer processing

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The modified equirectangular projection serves as an intermediary transformation that converts three-dimensional spherical content into a two-dimensional format suitable for standard video fingerprinting techniques. This intermediate representation enables accurate content detection while maintaining compatibility with existing processing pipelines

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If video fingerprinting techniques are applied to detect copyrighted content in spherical video, then the reliability of copyright detection is improved, but the difficulty of detecting and measuring increases due to distortion and non-default viewing locations

Engineering Contradiction:
Improvecopyright detection reliabilityVSAvoidcontent detection difficulty
Core Design Contradiction:
ReliabilityVSDifficulty of detecting and measuring

Solution Approach 1:

The system performs preliminary projection of the spherical video content to a two-dimensional region before applying fingerprinting techniques. This preliminary transformation ensures that copyrighted content, regardless of its location or orientation on the sphere, is properly positioned and undistorted in the 2D space, enabling reliable detection

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent modifies the projection parameters by using a customized equirectangular projection that maps spherical coordinates to 2D Cartesian coordinates with specific scaling and positioning. This parameter change optimizes the representation of copyrighted content for fingerprinting, making detection more reliable despite variations in viewing locations

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3752956B1Methods, systems, and media for detecting two-dimensional videos placed on a sphere in abusive spherical video content
Publication Date: 2023.12.13 GOOGLE LLC
  • EP3752956B1 patent drawingFigure 1A
  • EP3752956B1 patent drawingFigure 1B
  • EP3752956B1 patent drawingFigure 1C~1D

AI summary

Methods, systems, and media for analyzing spherical video content are provided. More particularly, methods, systems, and media for detecting two-dimensional videos placed on a sphere in abusive spherical video content are provided. In some embodiments, the method comprises: receiving an identifier of a spherical video content item, wherein the spherical video content item has a plurality of views; selecting a first frame of the spherical video content item; projecting the first frame of the spherical video content item to a two-dimensional region using a projection defined by a mapping according to which neighboring points of the first frame are mapped to respective neighboring points of the region, and one or more contiguous portions of the frame are each mapped to a corresponding plurality of contiguous portions of the region; identifying an area within the region which meets a criterion indicative of the region having a likelihood above a threshold of including a particular type of content; in response to identifying the area within the region which meets the criterion, analyzing the identified area of the region using a video fingerprinting technique; and, in response to determining that content associated with the identified area of the region matches a reference content item of a plurality of reference content items using the video fingerprinting technique, generating an indication of the match in association with the identifier of the spherical video content item.