Marker-Based AR Content Generation for Precise Background Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing video stabilization and segmentation technologies struggle to accurately identify static backgrounds in dynamic videos with moving foreground objects, leading to over-segmentation and misidentification of background portions.

Innovation Solution

A system and method for generating augmented reality content using markers placed in a physical environment, where markers can be passive or active, providing data for content generation, server connections, or two-way communication with head-mounted devices (HMDs) to enhance AR experiences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If existing video stabilization and segmentation technologies are used to identify static backgrounds in dynamic videos, then the processing can be performed automatically, but the background identification accuracy deteriorates leading to over-segmentation and misidentification

Engineering Contradiction:
Improveautomatic background identificationVSAvoidbackground identification accuracy
Core Design Contradiction:
Extent of automationVSMeasurement precision

Solution Approach 1:

The patent introduces markers as intermediary objects placed in the physical environment to mediate between the video processing system and the static background identification. These markers serve as reference points that the system can reliably detect and use to distinguish static background portions from moving foreground objects, thereby improving identification accuracy while maintaining automation.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Manufacturing precision

If markers are placed in the physical environment for AR content generation, then the precision of background identification and content generation improves, but the device complexity increases due to additional marker detection and processing requirements

Engineering Contradiction:
ImproveAR content generation precisionVSAvoidmarker detection system complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent makes the marker detection system multi-functional by enabling it to serve multiple purposes: identifying static backgrounds for video stabilization, providing reference frames for segmentation, and generating AR content. This universal approach justifies the added complexity by delivering multiple benefits from a single detection infrastructure.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Adaptability or versatility

If dynamic content generation based on marker detection is implemented, then the AR experience becomes more engaging and interactive, but the processing time and computational resources increase

Engineering Contradiction:
ImproveAR experience interactivityVSAvoidcontent generation time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-detecting and storing marker information and background reference data during video capture. This preprocessing allows the AR content generation to proceed more efficiently during playback or interaction phases, reducing real-time computational burden and delivery time while maintaining high interactivity.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3750138B1Marker-based augmented reality system and method
Publication Date: 2025.07.16 SAMSUNG ELECTRONICS CO LTD
  • EP3750138B1 patent drawingFigure 1
  • EP3750138B1 patent drawingFigure 2
  • EP3750138B1 patent drawingFigure 3~4A

AI summary

The present disclosure describes a system and method for a marker-based augmented reality system. The method includes acquiring image data including image related to real-world environment from a camera of the electronic device, identifying at least one marker from the acquired imaged data, identifying information represented by the at least one marker, the information represented by the at least one marker including at least one of content data, metadata, or server data, generating content based on the at least one of the content data, the metadata, or the server data, and displaying, on a display of the electronic device, the content overlaying the image related to the real-world environment, wherein the content is displayed on at least one portion corresponding to at least one first location in which the at least one marker is located in the image of the real-world environment or at least one second location indicated by the at least one marker.