3D Scan Registration via Tangent Plane Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Determining if different three-dimensional scans represent the same object or if a known object has changed between scans is difficult due to discrepancies in the captured shape information.

Innovation Solution

A method using a computer to determine congruence between physical objects by identifying tangency points, registering models to a common coordinate system, and measuring discrepancies between them to declare objects as the same if the discrepancy is within a predefined magnitude, or by matching n-tangents and tritangent planes to assess surface similarity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If three-dimensional scans are performed to capture shape information of objects, then the ability to analyze and compare objects is improved, but determining whether different scans represent the same object becomes difficult due to discrepancies in captured information

Engineering Contradiction:
Improveshape information capture accuracyVSAvoidobject identity determination difficulty
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent segments the three-dimensional object into multiple surfaces (first surface, second surface, third surface) and identifies specific feature points (apex, base points) on each surface. By dividing the object into manageable geometric components, the system can independently analyze each surface's characteristics and transform them into comparable two-dimensional representations, thereby resolving the difficulty of determining object identity from complex 3D scan data

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary transformation process that converts three-dimensional surface information into two-dimensional representations. By projecting 3D surfaces onto 2D planes and extracting key geometric features (apex positions, base coordinates, contour shapes), the system creates an intermediate representation that bridges the gap between different 3D scans, enabling reliable object identity determination despite variations in scanning conditions

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of information

If multiple three-dimensional models are registered to a common coordinate system, then the ability to fuse and mosaic model information is improved, but the complexity of the registration and comparison process increases

Engineering Contradiction:
Improvemodel information fusion capabilityVSAvoidregistration process complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent divides the complex registration task into smaller sub-tasks by identifying and processing each surface independently. For each surface, it locates specific feature points (apex, base points) and extracts geometric parameters. This segmentation allows the system to register multiple models by matching corresponding feature points and surfaces individually, reducing the overall complexity compared to attempting to register entire 3D models as single entities

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts essential geometric information from complex three-dimensional surfaces by identifying key feature points (apex, base points) and deriving simplified two-dimensional representations. By taking out only the critical geometric characteristics needed for registration and comparison, the system reduces the complexity of the registration process while preserving the essential information needed to determine object identity and fuse model data

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS9904870B2Registration and comparison of three-dimensional objects
Publication Date: 2018.02.27 COGNITECH
  • US9904870B2 patent drawing
  • US9904870B2 patent drawing
  • US9904870B2 patent drawing

AI summary

Information of different scans of physical objects may require comparison, for example to determine if the scans are of the same object or if an object has changed, or better information for a three dimensional model may be desired. Different scans of physical objects may be compared by determining lines or planes tangent to a surface at a discrete number of points, registering three dimensional information provided by the scans using the tangent lines or planes, and determining a measure of discrepancy between the surfaces. Three dimensional information of different scans of the same object may also be merged after determining lines or planes tangent to a surface at a discrete number of points and performing registration and merging.