Augmented Reality Outlines from Geographic 3D Reconstruction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality systems struggle to provide accurate and resource-efficient virtual outlines of objects that are not within the camera's field of view, especially in low-light conditions, relying on edge detection which is inefficient and resource-intensive.
Innovation Solution
A method and system that utilize geographic data to generate three-dimensional reconstructions of a scene, creating virtual outlines of objects based on their edges, vertices, or contours, which are then overlaid on real-world objects, using shaders for illumination and ambient light sensing to enhance visibility.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If edge detection is used to create virtual outlines in real-time, then the augmented reality system can provide object outlines, but it consumes excessive computing resources and is inefficient
Solution Approach 1:
The system performs 3D reconstruction of the scene in advance, creating a detailed geometric model of the environment and all objects within it. This pre-computed 3D model is then used to generate virtual outlines by simply extracting edges from the pre-existing geometry, rather than performing computationally intensive edge detection on captured images in real-time. The preliminary 3D reconstruction enables efficient outline generation while maintaining accuracy.
2Adaptability or versatility
If virtual outlines are generated for objects beyond the camera's field of view, then navigation awareness is improved, but the complexity of the system increases
Solution Approach 1:
The system transitions from 2D image-based edge detection to 3D geometric modeling for generating virtual outlines. By reconstructing the scene in three dimensions and extracting edges from the 3D model, the system can generate outlines for objects that are not currently visible in the camera view, as the 3D model contains geometric information about the entire scene regardless of camera orientation. This dimensional transition enables broader coverage without proportionally increasing complexity.
3Reliability
If real-time edge detection is performed on captured images, then virtual outlines can be generated, but the process is resource-intensive and inefficient
Solution Approach 1:
Instead of performing edge detection on captured images, the system creates a 3D copy or reconstruction of the entire scene including all objects. Virtual outlines are then generated by extracting edges from this 3D copy, which is a computationally simpler operation compared to image-based edge detection. This copying approach maintains outline accuracy while significantly improving processing efficiency, as the 3D model can be reused for multiple outline generation tasks without reprocessing the original images.
Data Source
AI summary
A method for providing an augmented reality view includes obtaining, based on a location of a computing device, a three-dimensional (3D) reconstruction of a scene associated with the location, the 3D reconstruction of the scene including one or more objects, processing the 3D reconstruction of the scene by generating one or more virtual objects which respectively correspond to the one or more objects, each virtual object being in a form of a virtual outline of a corresponding object among the one or more objects and, providing, for presentation on a display device of the computing device, an augmented reality view of the scene by overlaying at least one virtual outline onto a corresponding real-world object presented on the display device such that the at least one virtual outline at least partially frames the corresponding real-world object.