Augmented Reality Surface Recognition for Realistic Virtual Object Placement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current portable terminals fail to enhance augmented reality by not separating the solidity of real-world objects, resulting in a deteriorated viewing experience due to the lack of optimal viewer perspective when combining virtual objects with real-world images.
Innovation Solution
A method and terminal configuration that recognize surfaces in a preview image to arrange virtual objects, using criteria such as color, edges, and shadows, to provide a more realistic augmented reality experience by displaying virtual objects on recognized surfaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If virtual objects are simply combined with real-world images without surface recognition, then the augmented reality can be provided with basic functionality, but the viewing experience deteriorates due to lack of optimal viewer perspective and realism
Solution Approach 1:
The patent segments the real-world image into multiple surfaces by detecting edges, contours, and depth information. This segmentation allows virtual objects to be selectively placed on specific surfaces rather than simply overlaying the entire image, thereby improving augmented reality quality and viewer perspective.
Solution Approach 2:
The patent applies local quality by recognizing different surfaces (e.g., ground, walls, objects) with distinct properties and placing virtual objects appropriately on each surface based on its characteristics. This ensures that virtual objects are positioned with optimal viewer perspective relative to their intended surface, enhancing both realism and viewing experience.
2Reliability
If surface recognition algorithms are implemented to improve augmented reality realism, then the viewing experience is enhanced, but the device complexity increases
Solution Approach 1:
The patent performs preliminary surface recognition and segmentation on the real-world image before combining it with virtual objects. By pre-identifying surfaces, their orientations, and positions, the system reduces the computational complexity during the actual augmented reality rendering phase, as the placement decisions are already determined.
Solution Approach 2:
The patent introduces an intermediary processing layer that extracts surface information (edges, contours, depth) from the real-world image. This intermediary representation serves as a bridge between the raw image and the final augmented reality composition, simplifying the overall processing by working with extracted features rather than raw pixels throughout the pipeline.
Data Source
AI summary
A method of providing augmented reality and a terminal supporting the same are provided. The terminal for supporting augmented reality includes: a display unit displaying a specific image during a preview image mode; and a controller recognizing at least one surface from the specific image according to a predetermined criteria, combining an image of a virtual object with the specific image so that the image of a virtual object is displayed on the recognized at least one surface, and controlling the display unit to output the combined image.