3D Navigation Using Descriptor Vector Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Processing large amounts of three-dimensional data from vision-based navigation systems is computationally challenging and time-consuming, making it difficult to determine movement and position accurately.

Innovation Solution

A method for identifying corresponding segments in different 3D data frames using descriptor vectors, which involves pre-processing, segmentation, and feature description to compare and match segments across frames, allowing for efficient calculation of navigation solutions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If three-dimensional scan data is processed to determine navigation position and movement, then navigation accuracy is improved, but processing time increases significantly

Engineering Contradiction:
Improvenavigation position accuracyVSAvoiddata processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent divides the three-dimensional scan data into multiple two-dimensional projection images representing different viewing angles. This segmentation allows the system to process smaller 2D images instead of one large 3D dataset, significantly reducing computational complexity and processing time while maintaining navigation accuracy through multi-view geometry reconstruction.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts key geometric features and depth information from the three-dimensional scan data to create simplified two-dimensional projections. By extracting only the essential spatial relationships and projection characteristics rather than processing all raw 3D points, the system achieves fast processing while preserving the navigation-relevant geometric information.

Inventive Principle:
Principle #2Taking out (Extraction)

2Reliability

If complete three-dimensional environment data is captured, then navigation reliability is improved, but data quantity and processing complexity increase

Engineering Contradiction:
Improvenavigation reliabilityVSAvoiddata quantity
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The patent segments the complete three-dimensional environment data into multiple two-dimensional projection images from different angles. This segmentation reduces the overall data quantity by representing 3D information through multiple 2D views, while the combined information from all projections maintains the reliability needed for accurate navigation determination.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates two-dimensional projection copies of the three-dimensional environment from various viewing angles. These 2D projection images serve as simplified representations that reduce data storage requirements and processing complexity while preserving the essential spatial information needed for reliable navigation through geometric reconstruction.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP2757529B1Systems and methods for 3D data based navigation using descriptor vectors
Publication Date: 2018.09.05 HONEYWELL INTERNATIONAL INC
  • EP2757529B1 patent drawingFigure 1
  • EP2757529B1 patent drawingFigure 2
  • EP2757529B1 patent drawingFigure 3~4

AI summary

Systems and methods for 3D data based navigation using descriptor vectors are provided. In at least one embodiment, a method for identifying corresponding segments in different frames of data comprises identifying a first segment set in a first frame in multiple frames acquired by at least one sensor, and identifying a second segment set in a second frame in the multiple frames. The method also comprises calculating a first and second set of descriptor vectors, wherein the first and second sets of descriptor vectors comprise a descriptor vector for each segment in the respective first and second segment set, wherein a descriptor vector describes an indexed plurality of characteristics; and identifying corresponding segments by comparing the first set of descriptor vectors against the second set of descriptor vectors, wherein the corresponding segments describe characteristics of the same feature in the environment.