Building Outline Approximation from Point Cloud Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for extracting building outlines from point cloud data obtained by laser scanners are labor-intensive, error-prone, and struggle with capturing low-reflectance, specular, and transparent surfaces, leading to incomplete and noisy data that complicates boundary determination.

Innovation Solution

A method involving flood filling to extract boundary cells, followed by filtering potential boundary points using a modified convex hull, extracting line segments, and refining them under parallel and perpendicular constraints to generate a regularized polygon, effectively handling the challenges of non-uniform point density and surface types.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If interactive methods are used to create BIMs from point cloud data, then measurement precision can be achieved, but labor intensity increases and error rates increase

Engineering Contradiction:
ImproveBIM modeling precisionVSAvoidLabor intensity
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system automatically extracts building outlines and generates BIM models without requiring manual intervention. The automated boundary extraction algorithm processes point cloud data independently, eliminating the need for human operators to manually trace or measure building boundaries, thus reducing labor intensity while maintaining precision

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces manual interactive methods with automated computational algorithms. The boundary extraction process uses mathematical computations and image processing techniques instead of human operators physically measuring or tracing building boundaries, thereby reducing labor requirements while maintaining or improving precision

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

2Measurement precision

If laser scanners capture building surfaces, then measurement precision is improved, but detection difficulty increases for low-reflectance, specular, and transparent surfaces

Engineering Contradiction:
ImproveSurface capture precisionVSAvoidSurface detection difficulty
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The system uses an intermediary processing layer that combines multiple data sources and processing techniques. Instead of relying solely on direct laser scanning, the system integrates point cloud data with boundary cell analysis and convex hull computations to infer building outlines, thereby overcoming the detection difficulties of specific surface types

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the approach from direct surface reflection-based detection to geometric shape-based inference. By analyzing the overall geometry and boundary cells rather than relying on surface reflectance properties, the system can accurately capture building outlines regardless of whether surfaces are low-reflectance, specular, or transparent

Inventive Principle:
Principle #35Parameter changes

3Quantity of substance

If multiple laser scans are combined to capture whole building, then completeness is improved, but data complexity and noise increase

Engineering Contradiction:
ImprovePoint cloud completenessVSAvoidData processing complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The system extracts only the essential boundary information from the comprehensive point cloud data. By identifying and processing only the boundary cells and extracting line segments from boundary points, the system filters out unnecessary interior details and reduces complex multi-scan data to simplified boundary representations, thereby reducing processing complexity while maintaining completeness

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the building boundary into discrete boundary cells and line segments. This segmentation allows the system to process the complex point cloud data in manageable portions, organizing the information into structured representations that are easier to process and less noisy, while still capturing the complete building outline from multiple scans

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS9189862B2Outline approximation for point cloud of building
Publication Date: 2015.11.17 AUTODESK INC
  • US9189862B2 patent drawing
  • US9189862B2 patent drawing
  • US9189862B2 patent drawing

AI summary

A method, apparatus, system, and computer program product provide the ability to model a polyline boundary from point cloud data. Point cloud data is obtained and boundary cells are extracted. Potential boundary points are filtered from the boundary cells. Line segments are extracted from the potential boundary points and refined. A regularized polygon is obtained by intersecting the refined line segments.