Non-Parametric 3D City Modeling Using Point Cloud Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current 3D city modeling methods face challenges with extreme computational demand and scalability issues due to their reliance on parametric approaches and predefined shapes, making them inefficient for generating detailed and accurate models of diverse urban areas.

Innovation Solution

A non-parametric and non-iterative method using a k-dimensional (kd)-tree to assess the proximity and nature of neighboring 3D points, allowing for efficient generation of detailed 3D geographical models by removing vertical structures, segmenting rooftops, and connecting points to a base for accurate representation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If parametric approaches with predefined shapes are used for 3D city modeling, then the modeling process can be standardized, but extreme computational demand and scalability issues occur

Engineering Contradiction:
Improvestandardization of modeling processVSAvoidcomputational efficiency
Core Design Contradiction:
Ease of manufactureVSProductivity

Solution Approach 1:

The patent replaces traditional parametric modeling approaches with a point-cloud-based direct modeling system. Instead of using predefined shapes and iterative optimization algorithms, the system directly processes 3D sensor data points to generate city models, eliminating the computational burden of parameter optimization while maintaining modeling capability

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the fundamental parameters of the modeling approach by transitioning from shape-based parametric models to point-cloud-based geometric models. This parameter change allows the system to work with raw sensor data directly without requiring predefined shape parameters, thereby reducing computational demand

Inventive Principle:
Principle #35Parameter changes

2Ease of manufacture

If parametric approaches with predefined shapes are used for 3D city modeling, then the modeling process can be standardized, but scalability across different architectural environments deteriorates

Engineering Contradiction:
Improvestandardization of modeling processVSAvoidscalability across different architectures
Core Design Contradiction:
Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The patent segments the city modeling process into independent processing stages: point cloud acquisition, processing, and model generation. This segmentation allows the system to handle different architectural types independently without requiring global parameter adjustments, thereby improving scalability across diverse urban environments

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates a universal point-cloud-based modeling framework that can process various architectural types using the same core algorithms. The system's ability to work with raw 3D data points makes it adaptable to different building styles, heights, and configurations without requiring architecture-specific predefined shapes

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Extent of automation

If automatic methods are used for 3D city modeling, then time and effort of specialized personnel are reduced, but computational complexity increases

Engineering Contradiction:
Improvereduction of manual effortVSAvoidcomputational complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The patent extracts the essential geometric information directly from 3D sensor point clouds without requiring complex intermediate processing steps. By taking out only the necessary data elements needed for modeling and processing them through simplified algorithms, the system maintains high automation while reducing computational complexity

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP2849117B1Methods, apparatuses and computer program products for automatic, non-parametric, non-iterative three dimensional geographic modeling
Publication Date: 2020.02.19 HERE GLOBAL BV
  • EP2849117B1 patent drawingFigure 1
  • EP2849117B1 patent drawingFigure 2
  • EP2849117B1 patent drawingFigure 3

AI summary

An apparatus for generating 3D geographical models includes a processor and memory storing executable computer program code causing the apparatus to at least perform operations including removing 3D points of a cloud depicting vertical structures in a geographic area responsive to analyzing a set of 3D points of the cloud. The points include data indicating geocoordinates of the geographic area. The computer program code further causes the apparatus to segment rooftops of vertical structures responsive to analyzing the set. The computer program code further causes the apparatus to delineate points of segmented rooftops responsive to extracting a boundary and a portion of rooftops. The computer program code further causes the apparatus to generate 3D geographic models depicting the geographic area based on connecting delineating points to a base including a height lower than heights of delineating points. Corresponding methods and computer program products are also provided.