3D Building Reconstruction Using AR World Maps and Reference Poses
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 3-D reconstruction methods for building structures face challenges with large image inputs requiring costly computing resources and sparse data failing to capture accurate information, while augmented reality (AR) devices suffer from sensor drift and noise, leading to location inaccuracies and lack of integration with other image data for realistic rendering.
Innovation Solution
A method leveraging augmented reality frameworks to capture sparse images and utilize AR maps with world coordinates, combined with computer vision techniques and sensor data, to generate accurate 3-D models by identifying reference poses, selecting candidate poses, and applying a scaling factor based on geometric transformations and illumination data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If video input or large image inputs are used for 3-D reconstruction, then comprehensive building information is captured, but costly computing cycles and resources are required
Solution Approach 1:
The patent applies partial action by using only 6-8 strategically selected sparse images instead of comprehensive video input, capturing sufficient building information while significantly reducing computing resource requirements. This selective sampling approach achieves the necessary information capture without the excessive computational burden of processing continuous video streams.
2Use of energy by moving object
If image sets with sparse data are used, then computing resources are reduced, but adequate information for realistic rendering or accurate measurements is not captured
Solution Approach 1:
The patent introduces AR map data as an intermediary that bridges sparse images and complete building information. The AR framework provides supplementary data including building geometry, textures, and metadata that compensates for the sparsity of input images, enabling accurate measurements and realistic rendering without requiring extensive image sets.
Solution Approach 2:
The patent transforms the problem by changing from direct 3-D reconstruction parameters to AR map parameters including world coordinate systems, scaling factors, and illumination data. These parameter transformations allow sparse images to be integrated with pre-existing AR frameworks, achieving accurate building representations with reduced computational input.
3Ease of operation
If AR devices are used for capturing building data, then ease of operation is improved, but sensor drift and noise cause location inaccuracies
Solution Approach 1:
The patent implements feedback by using the captured sparse images to validate and correct AR framework data. The system continuously compares AR-generated building representations with actual image content, detecting and correcting drift or inaccuracies in camera positioning and building measurements, thereby maintaining precision despite sensor limitations.
Solution Approach 2:
The patent applies preliminary action by pre-processing AR map data and establishing reference coordinate systems before final 3-D reconstruction. This preparatory step allows the system to anticipate and correct potential drift issues by anchoring the reconstruction to stable reference points identified in the sparse images, improving location accuracy before the actual measurement process.
Data Source
Figure 1A
Figure 1B
Figure 1C~1D
AI summary
System and method are provided for scaling a 3-D representation of a building structure. The method includes obtaining images of the building structure, including non-camera anchors. The method also includes identifying reference poses for images based on the non- camera anchors. The method also includes obtaining world map data including real-world poses for the images. The method also includes selecting candidate poses from the real-world poses based on corresponding reference poses. The method also includes calculating a scaling factor for a 3-D representation of the building structure based on correlating the reference poses with the selected candidate poses. Some implementations use structure from motion techniques or LiDAR, in addition to augmented reality frameworks, for scaling the 3-D representations of the building structure. In some implementations, the world map data includes environmental data, such as illumination data, and the method includes generating or displaying the 3-D representation.