Stereoscopic Content Detection via Image Correlation Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing multimedia content delivery systems face challenges in automatically detecting stereoscopic content within video/image data without embedded supplemental information, making it difficult for users to identify eye priority and manage metadata effectively.

Innovation Solution

A method and system that calculate the correlation between two portions of an image/video frame on either side of a reference portion using a processor to determine whether the content is stereoscopic or non-stereoscopic, employing correlation analysis and edge detection to identify stereoscopic content even in the absence of metadata.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If supplemental information is stored in an external dedicated server, then stereoscopic content detection capability is improved, but data management complexity and communication difficulty increase

Engineering Contradiction:
Improvestereoscopic content detection capabilityVSAvoiddata management complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts the essential detection functionality from external servers and implements it locally within the computing device. The processor directly analyzes video/image data to detect stereoscopic content and determine eye priority, eliminating the need for complex external data management systems while maintaining detection capability.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The computing device performs self-detection of stereoscopic content using its own processor and algorithms. The system analyzes correlation between image portions locally, determines eye priority independently, and renders content without requiring external supplemental information, making the system self-sufficient.

Inventive Principle:
Principle #25Self-service

2Extent of automation

If correlation analysis is performed between two portions of an image on either side of a reference portion, then automatic detection of stereoscopic content is improved, but computational complexity increases

Engineering Contradiction:
Improveautomatic detection capabilityVSAvoidcomputational complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The patent divides the image into distinct portions: a reference portion and two portions on either side. The processor calculates correlation specifically between these segmented portions, which simplifies the computational approach compared to analyzing the entire image, while still achieving automatic stereoscopic content detection.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS9092658B2Automatic detection of stereoscopic content in video/image data
Publication Date: 2015.07.28 NVIDIA CORP
  • US9092658B2 patent drawing
  • US9092658B2 patent drawing
  • US9092658B2 patent drawing

AI summary

A method includes calculating, through a processor of a computing device communicatively coupled to a memory, correlation between two portions of an image and/or a video frame on either side of a reference portion thereof. The method also includes determining, through the processor, whether content of the image and/or the video frame is stereoscopic or non-stereoscopic based on the determined correlation.