3D Image Disparity Adjustment via Visual Attention Mapping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

3D displays cause increased visual fatigue due to differing image information for left and right fields of view, leading to a desire for methods to decrease this fatigue while maintaining the 3D effect.

Innovation Solution

An image processing apparatus and method that generates a visual attention map based on user attention characteristics, adjusting disparity information in 3D images to minimize visual fatigue by repositioning high-attention regions closer to the viewer, using a ROI configuration unit and disparity adjustment unit.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Object-affected harmful factors

If disparity information is uniformly adjusted to decrease visual fatigue, then visual fatigue is reduced, but the 3D effect and perceived depth are degraded

Engineering Contradiction:
Improvevisual fatigueVSAvoidperceived depth accuracy
Core Design Contradiction:
Object-affected harmful factorsVSManufacturing precision

Solution Approach 1:

The patent applies local quality by adjusting disparity information differently for different regions of the 3D image based on visual attention levels. High-attention regions (such as faces, eyes, and important objects) receive different disparity adjustment than low-attention regions, allowing visual fatigue reduction in critical areas while maintaining 3D effect in other areas. This is achieved through the visual attention map that identifies and prioritizes specific regions for differential processing.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent segments the 3D image into multiple regions with different visual attention levels using the visual attention map. This segmentation allows the system to apply different disparity adjustment strategies to different segments, rather than uniformly adjusting the entire image. The region of interest extraction unit divides the image based on attention levels, enabling selective processing that balances fatigue reduction with 3D effect preservation.

Inventive Principle:
Principle #1Segmentation

2Manufacturing precision

If disparity information is adjusted to maintain 3D effect, then perceived depth is maintained, but visual fatigue increases

Engineering Contradiction:
Improveperceived depthVSAvoidvisual fatigue
Core Design Contradiction:
Manufacturing precisionVSObject-affected harmful factors

Solution Approach 1:

The patent changes the disparity parameter selectively based on visual attention levels. By modifying the disparity parameter only in regions with high visual attention (where it contributes most to fatigue), and maintaining or minimally adjusting it in other regions, the system achieves a balance between maintaining 3D effect and reducing fatigue. The visual attention map guides which parameter changes are applied where.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If visual attention map is generated using multiple calculation methods, then accuracy of region identification is improved, but processing complexity increases

Engineering Contradiction:
Improveregion identification accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements partial action by focusing computational resources on calculating visual attention for only the most critical regions rather than uniformly processing the entire image with maximum detail. The system identifies key regions (faces, eyes, important objects) and applies more sophisticated attention calculation methods to these areas, while using simpler methods for less critical regions, thus balancing accuracy with processing complexity.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP2590416B1Image processing apparatus and method
Publication Date: 2017.08.02 SAMSUNG ELECTRONICS CO LTD
  • EP2590416B1 patent drawingFigure 1
  • EP2590416B1 patent drawingFigure 2
  • EP2590416B1 patent drawingFigure 3

AI summary

An image processing apparatus including a region of interest (ROI) configuration unit may generate a visual attention map according to visual characteristics of a human in relation to an input three dimensional (3D) image. A disparity adjustment unit may adjust disparity information, included in the input 3D image, using the visual attention map. Using the disparity information adjusted result, a 3D image may be generated and displayed which reduces a level of visual fatigue a user may experience in viewing the 3D image.