AR Object Tracking via Predefined Geometry and Perspective Adaptation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current augmented reality devices cannot effectively display predefined objects in a physical scene from different perspectives, as alterations made to a single image do not translate to subsequent captured images, limiting the immersive experience.

Innovation Solution

The method involves capturing images of a physical scene using camera devices, determining the region and configuration of a physical object, and rendering a sequence of frames with animations and augmentations based on predefined geometric information, allowing for dynamic and interactive virtual enhancements of the object.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If alterations are applied to a single captured image, then the image can be enhanced or modified, but subsequent captured images from different perspectives do not incorporate these alterations

Engineering Contradiction:

Improveconsistency of virtual alterations across multiple perspectivesVSAvoidloss of virtual alterations when changing perspectives

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system performs preliminary actions by tracking the physical object across multiple frames and pre-calculating the transformation matrices needed to maintain virtual object consistency. The virtual alterations are applied in advance to all expected perspectives rather than reacting to each new image separately, ensuring continuity across different viewing angles.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from continuous object tracking to adjust and maintain the position and orientation of virtual alterations. By monitoring the physical object's movement across frames and using this feedback to update transformation parameters, the system ensures that virtual alterations remain consistent and properly aligned from different perspectives.

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If virtual objects are inserted into captured images, then the augmented reality experience is enhanced, but the virtual objects do not adapt to different perspectives of the same physical object

Engineering Contradiction:

Improveperspective adaptability of virtual objectsVSAvoidcomplexity of tracking and rendering system

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system implements dynamics by making virtual objects adaptive to changing perspectives through real-time transformation matrix calculations. As the physical object moves or changes orientation, the virtual objects dynamically adjust their position, scale, and rotation based on updated tracking data, creating a responsive augmented reality experience that adapts to different viewing angles.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system transitions from 2D image-based tracking to 3D spatial understanding by calculating transformation matrices that account for depth, orientation, and perspective. This dimensional enhancement allows virtual objects to be properly positioned and scaled in three-dimensional space, enabling them to adapt naturally to different perspectives of the physical object.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Productivity

If predefined geometric information is used to generate virtual objects, then rendering efficiency is improved, but the ability to handle complex or irregular physical objects is reduced

Engineering Contradiction:

Improverendering speedVSAvoidhandling of complex object shapes

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system uses copying by creating virtual representations of physical objects based on predefined geometric templates. Instead of performing complex real-time 3D modeling, the system selects appropriate pre-defined geometric models that match the detected object type and applies transformation matrices to position and orient these copies correctly, achieving fast rendering while maintaining reasonable accuracy for recognized object categories.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS10217289B2Augmented reality device with predefined object data

Publication Date: 2019.02.26 ADEIA MEDIA HOLDINGS INC

AI summary

Embodiments capture one or more images of a visual scene that includes a first physical object. A first region of the first physical object to apply one or more augmentations to is determined. Embodiments determine which configuration the first physical object is currently in. The first physical object is configured to be physically manipulatable into each of a plurality of configurations. A sequence of frames is rendered for display in which the first region of the first physical object is animated in a predefined manner depicting a virtual light source within the first physical object, based on the determined configuration of the first physical object, by applying the one or more augmentations to a first virtual object generated based on predefined geometric information corresponding to a determined object type of the first physical object. The rendered sequence of frames is output for display using one or more display devices.