Photogrammetric 3D Wireframe Generation for As-Built Dimensioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for obtaining as-built dimensions of structures, such as manual measuring and surveying, are either inaccurate or require trained technicians and hazardous environments, posing safety risks and inefficiencies.
Innovation Solution
A networked system using calibrated imaging devices to capture images of structures, which are then processed to generate three-dimensional wireframes, allowing for accurate dimension determination and material estimation, and enabling the generation of fabrication data for structure components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual measuring is used to obtain as-built dimensions, then the process is simple and requires no special equipment, but the measurements are inaccurate and workers are exposed to dangerous environments
Solution Approach 1:
The patent creates a digital 3D model (copy) of the physical structure through photogrammetry. Multiple photographs are processed to generate point clouds and 3D wireframe models that accurately represent the as-built conditions without requiring physical contact or worker presence on hazardous structures
Solution Approach 2:
The patent replaces manual mechanical measuring tools (tapes, levels, transit) with an optical-digital system. Cameras capture images that are processed through computer vision algorithms to automatically extract dimensional information, eliminating the need for workers to physically measure structures in dangerous environments
2Measurement precision
If surveying techniques are used to obtain accurate measurements, then dimensional precision is improved, but the process requires trained technicians and stable platforms
Solution Approach 1:
The system performs self-calibration and automatic feature extraction without requiring trained surveyors. The photogrammetry software automatically identifies control points, matches features across images, and computes 3D coordinates through algorithmic processing, eliminating the need for human expertise in traditional surveying techniques
Solution Approach 2:
The patent transforms the measurement process from requiring stable tripod-mounted instruments to using handheld or mobile camera systems. By changing the operational parameters (from static to dynamic capture) and using computational photogrammetry to compensate for motion, the system achieves survey-grade accuracy without traditional surveying equipment constraints
3Productivity
If conventional measuring methods are used, then no special equipment is needed, but the process is time-consuming and inefficient
Solution Approach 1:
The patent enables continuous data capture by taking multiple overlapping photographs while moving through the structure. Rather than stopping to measure each point individually, the system continuously records spatial information that is later processed en masse, dramatically reducing on-site measurement time while maintaining accuracy
Solution Approach 2:
The system performs preliminary documentation by capturing comprehensive photographic coverage of the structure before any measurement or analysis is needed. These images serve as a permanent record that can be processed repeatedly to extract various dimensional information without requiring additional site visits or remeasuring
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This method provides accurate, safe, and efficient means to obtain structure dimensions and material estimates, facilitating precise fabrication while minimizing risks to workers.
Implementation Method 1
a first image of the structure in the scene is obtained from a first imaging device and a second image of the structure in the scene is obtained from a second imaging device
Data Source
AI summary
According to various embodiments, a stream of image frames depicting a structure in a scene are obtained. The stream of image frames may comprise first image frames from a first imaging device and second image frames from a second imaging device. Using the first image frames and the second image frames, a wireframe of at least a portion of the structure is generated. From the wireframe, as-built dimensions may be identified, materials estimates may be determined, and/or data for a fabrication device may be generated, for example.