Convex Hull Feature Extraction for Dynamic Spatial Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional localization and object recognition technologies are inadequate for dynamic environments, as they assume a static environment, making it difficult to separate and recognize structures, objects, and dynamics in indoor spaces where these elements are mixed.

Innovation Solution

A method for extracting outer space feature information from spatial geometric data using three-dimensional point cloud data, employing a convex hull method to distinguish and separate static and dynamic elements, allowing conventional technologies to be applied in dynamic environments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional localization and object recognition technologies are used in dynamic environments, then the technologies can be applied in real-world scenarios, but the assumption of static environment causes inaccurate feature extraction and recognition

Engineering Contradiction:
Improveapplicability to dynamic environmentVSAvoidfeature extraction accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent segments spatial geometric data into multiple sampling planes and processes each plane independently using convex hull algorithms. This segmentation allows the system to handle dynamic environments by treating different spatial regions separately, maintaining measurement precision while adapting to real-world complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transforms three-dimensional point cloud data into two-dimensional sampling planes for processing. By projecting 3D spatial geometric data onto 2D planes and applying convex hull methods in this reduced dimensionality, the system achieves efficient feature extraction that works accurately in dynamic environments while reducing computational complexity.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Loss of information

If all spatial geometric data including structures, objects, and dynamics are processed together, then complete environmental information is obtained, but calculation load increases and processing efficiency decreases

Engineering Contradiction:
Improvecompleteness of environmental informationVSAvoidprocessing efficiency
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The patent extracts only the essential outer boundary features of structures using convex hull algorithms on sampling planes. By taking out and processing only the critical geometric boundaries rather than all detailed spatial data, the system maintains complete structural information while significantly reducing calculation load and improving processing efficiency.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies different processing approaches to different spatial regions by creating multiple sampling planes with local orientations. Each sampling plane processes local geometric features with appropriate algorithms, ensuring that important structural information is preserved while reducing overall computational requirements through localized processing.

Inventive Principle:
Principle #3Local quality

3Device complexity

If conventional methods process spatial data without separating static and dynamic elements, then implementation is simpler, but the ability to distinguish structures from moving objects deteriorates

Engineering Contradiction:
Improveimplementation complexityVSAvoidseparation of static and dynamic elements
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent performs preliminary processing by organizing spatial geometric data into multiple sampling planes before applying convex hull algorithms. This preliminary structuring of data into manageable planes simplifies the subsequent processing steps while enabling accurate distinction between static structures and dynamic elements through systematic geometric analysis.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent creates simplified two-dimensional representations (copies) of three-dimensional spatial data through sampling planes. These 2D copies preserve the essential geometric characteristics needed for distinguishing static from dynamic elements while being computationally simpler to process, thus reducing implementation complexity without sacrificing measurement precision.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3091506B1Method for extracting outer space feature information from spatial geometric data
Publication Date: 2019.01.09 TEELABS CO LTD
  • EP3091506B1 patent drawingFigure 1A
  • EP3091506B1 patent drawingFigure 1B~1C
  • EP3091506B1 patent drawingFigure 1D

AI summary

The present invention provides a method for extracting outer space feature information from spatial geometric data, the method comprising: an input step S10 of inputting spatial geometric data for a target region; a sampling step S20 of determining a sample by selecting an arbitrary area for the spatial geometric data input in the input step using a preset selection method; a feature extraction step S30 of acquiring feature information for a corresponding sampling plane using a convex hull method based on sampling information including sampling plane information of the spatial geometric data for a sampling plane selected in the sampling step. The sampling step and the feature extraction step are repeatedly performed in a preset manner.