3D Space Dimensioning From Fisheye Camera Triangulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing 360-degree cameras cannot determine the real-world dimensions of a reconstructed 3D space, leading to measurements in arbitrary scales that complicate comparisons and embeddings of multiple reconstructions.
Innovation Solution
A method involving multiple fisheye lenses of a camera to capture images, followed by image undistortion, key point identification, alignment of images in the same rotational space, and triangulation to calculate real-world distances, allowing for the determination of absolute dimensions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple shots of 360 camera are used to estimate scene geometry, then the 3D reconstruction of the space can be generated, but the dimensions of the reconstructed 3D space are measured in arbitrary scale and cannot determine real-world dimensions
Solution Approach 1:
The patent introduces an intermediary element (a known reference object or feature with predetermined real-world dimensions) into the scene being captured. This reference object serves as a mediator between the camera system and the unknown dimensions, allowing the system to calculate real-world scale by comparing the reference object's known dimensions against its representation in the 3D reconstruction. This resolves the contradiction by enabling accurate dimension measurement without requiring complex depth sensors or multiple cameras.
2Adaptability or versatility
If 360-degree cameras are used to capture multiple shots, then 3D reconstruction can be achieved, but comparisons and embeddings of multiple separate reconstructions become complicated due to arbitrary scaling
Solution Approach 1:
The patent changes the scaling parameter of the 3D reconstruction by introducing a reference object with known real-world dimensions. By detecting this reference object in the captured images and using its known dimensions, the system can compute a scale factor that transforms the arbitrary-scale reconstruction into an absolute-scale model. This enables direct comparison and embedding of multiple reconstructions since they all share a common real-world scale reference.
Data Source
AI summary
A method (1000) of determining a dimension value indicating a physical dimension of a three-dimensional (3D) space is provided. The method (1000) comprises obtaining (s1002) a first image, wherein the first image is generated using a first lens of a camera, identifying (s!004) a first set of one or more key points included in the first image, and obtaining (s1006) a second image, wherein the second image is generated using a second lens of the camera. The method (1000) further comprises identifying (s1008) a second set of one or more key points included in the second image and determining (S1010) a set of one or more 3D points associated with the first set of key points and the second set of key points, wherein the set of one or more 3D points includes a first 3D point. The method (1000) further comprises calculating (s1012) a first distance value indicating a distance between the camera and a real-world point corresponding to the first 3D point and based at least on the calculated first distance value, determining (s1014) the dimension value.