Content Segment Selection for Video Quality

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Mobile terminals often capture content with poor brightness, shake, and blur due to limited camera sensors and unfavorable recording conditions, making it difficult to improve image quality without increasing noise and removing shake and blur effectively.

Innovation Solution

A method and apparatus that select content segments based on contextual similarity levels, brightness levels, blur levels, and shake levels to produce a resultant video with improved brightness and reduced shake and blur, while maintaining a desired field of view.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Illumination intensity

If post-processing techniques are used to improve brightness, then brightness levels can be enhanced, but random noise increases

Engineering Contradiction:
ImprovebrightnessVSAvoidrandom noise
Core Design Contradiction:
Illumination intensityVSObject-generated harmful factors

Solution Approach 1:

The system performs preliminary selection of content segments based on brightness levels, blur levels, and shake levels before final video assembly. By pre-filtering segments with adequate brightness and low noise in the selection criteria, the system avoids the need for aggressive post-processing that would amplify noise, thus resolving the contradiction between brightness enhancement and noise increase.

Inventive Principle:
Principle #10Preliminary action

2Manufacturing precision

If multiple content segments are selected and combined, then video quality improves, but device complexity increases

Engineering Contradiction:
Improvevideo qualityVSAvoidsystem complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system divides the video content into discrete segments and evaluates each segment independently based on brightness, blur, and shake characteristics. This segmentation approach allows for quality improvement by selecting only the best segments while maintaining manageable system complexity through automated segment-level analysis and selection algorithms.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system changes the evaluation parameters from a single quality metric to multiple parameters (brightness level, blur level, shake level) that are measured and compared across segments. By establishing threshold values for these parameters, the system automates the selection process, improving video quality without proportionally increasing complexity.

Inventive Principle:
Principle #35Parameter changes

3Area of stationary object

If content segments with different fields of view are selected, then more content coverage is achieved, but contextual consistency decreases

Engineering Contradiction:
Improvecontent coverageVSAvoidcontextual consistency
Core Design Contradiction:
Area of stationary objectVSStability of the object's composition

Solution Approach 1:

The system applies different selection criteria to different segments based on their contextual characteristics. By evaluating brightness, blur, and shake levels locally for each segment and comparing contextual characteristics to determine similarity levels, the system maintains contextual consistency within each segment while allowing overall content coverage to expand through selective inclusion of diverse segments.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP2638526B1Method and apparatus for selecting content segments
Publication Date: 2020.04.29 PROVENANCE ASSET GROUP LLC
  • EP2638526B1 patent drawingFigure 1
  • EP2638526B1 patent drawingFigure 2
  • EP2638526B1 patent drawingFigure 3

AI summary

A method, apparatus and computer program product select content segments based at least in part on a contextual similarity level between the content segments and at least one of brightness levels, blur levels, and shake levels of the content segments. As such, a resultant video may be produced that comprises selected content segments. Accordingly, brightness levels of the content may be improved and shake and blur levels reduced while maintaining a desired field of view.