Electronic Device Image Processing Non-Stationary Object Removal

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image processing technologies fail to effectively remove non-stationary objects from a sequence of images captured at different times, limiting the ability to create composite images without unwanted moving subjects.

Innovation Solution

An electronic device and method that detects non-stationary objects in a sequence of images, allows users to select a frame region containing these objects, and replaces the image data in that region with data from another image with low similarity, thereby removing the objects from the final composite image.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If image data from consecutively captured images is used to create composite images, then the ability to capture moments on notice is improved, but non-stationary objects cannot be effectively removed from the composite image

Engineering Contradiction:
Improveimage capture efficiencyVSAvoidimage content accuracy
Core Design Contradiction:
ProductivityVSManufacturing precision

Solution Approach 1:

The image is divided into multiple regions, with stationary regions being composite-ed from multiple frames and non-stationary regions being excluded. The processor identifies region types based on temporal consistency and selectively processes different regions differently, allowing efficient composite image creation while maintaining content accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Different processing strategies are applied to different regions of the image. Stationary regions undergo composite editing to capture momentous events, while non-stationary regions are identified and excluded from compositing. This localized approach ensures that each region is processed according to its characteristics, resolving the contradiction between efficiency and accuracy.

Inventive Principle:
Principle #3Local quality

2Adaptability or versatility

If automated detection of non-stationary objects is implemented, then image processing capability is improved, but device complexity increases

Engineering Contradiction:
Improveimage processing capabilityVSAvoidprocessing system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system dynamically adjusts processing based on detected motion characteristics. Rather than using a fixed complex algorithm for all images, the processor adapts its behavior based on the presence and characteristics of non-stationary objects in each specific image sequence, achieving high adaptability with manageable complexity.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The image processing system automatically detects and handles non-stationary objects without requiring manual intervention or complex external processing systems. The device performs self-analysis of image sequences, automatically identifying region types and applying appropriate processing, thereby enhancing capability while keeping the system relatively simple.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP2779632B1Electronic device and method of operating the same
Publication Date: 2018.10.24 SAMSUNG ELECTRONICS CO LTD
  • EP2779632B1 patent drawingFigure 1
  • EP2779632B1 patent drawingFigure 2
  • EP2779632B1 patent drawingFigure 3

AI summary

A method and apparatus for image processing includes receiving images, detecting non-stationary objects in the images, displaying a first image that includes a non-stationary object, selecting a frame region including the non-stationary object in the first image, selecting a second image based on a low similarity with the first image, and replacing image data in the frame region of the first image with image data represented in the frame region of the second image.