Georeferenced Floorplan Modeling From Blueprint Images

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing blueprints are cumbersome to quickly parse for layout information, especially in emergency scenarios, and lack coordinate information for building features, hindering rapid understanding and location tracking of first responders.

Innovation Solution

A system that analyzes scanned blueprint images using machine learning models to identify floor and elevation sheets, extracts contours, and georeferences them to a three-dimensional map, enabling accurate location determination of building features.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If blueprints are used to understand building layout, then building layout information is available, but it is cumbersome to quickly parse and lacks coordinate information

Engineering Contradiction:
Improvecoordinate informationVSAvoidtime to parse blueprint
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent creates a digital three-dimensional model that replicates the building layout from two-dimensional blueprints. This digital copy includes embedded coordinate information and can be rapidly queried, eliminating the need to manually parse physical or scanned blueprints while preserving all layout details.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent transforms two-dimensional blueprint data into a three-dimensional digital model with geospatial coordinates. This dimensional transformation adds location information (latitude, longitude, elevation) to the building layout data, enabling rapid spatial queries and visualization without losing any original blueprint information.

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

2Measurement precision

If manual parsing of blueprints is used, then building layout information can be extracted, but it is time-consuming and lacks precision for location tracking

Engineering Contradiction:
Improvelocation accuracyVSAvoidtime for manual parsing
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical parsing of blueprints with automated image processing and machine learning algorithms. The system automatically extracts building features, generates three-dimensional models, and assigns precise geospatial coordinates, eliminating human effort while achieving sub-meter location accuracy.

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

Solution Approach 2:

The patent introduces a digital three-dimensional model as an intermediary between the blueprint and the end user. This model serves as a processed representation that contains both layout information and precise coordinate data, allowing rapid queries without requiring direct manual analysis of the original blueprint.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Ease of operation

If blueprints lack coordinate information, then building layout is depicted, but location tracking of first responders is hindered

Engineering Contradiction:
Improvelocation trackingVSAvoidcoordinate data
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The patent creates a three-dimensional digital model that serves multiple functions simultaneously: it preserves building layout information from blueprints, adds geospatial coordinate data, and enables location tracking applications. This single digital representation replaces multiple separate systems (blueprint storage, coordinate databases, and tracking software).

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

Data Source

PatentUS12469278B2Georeferencing a generated floorplan and generating structural models
Publication Date: 2025.11.11 CARRINGTON CHARLES C
  • US12469278B2 patent drawing
  • US12469278B2 patent drawing
  • US12469278B2 patent drawing

AI summary

Methods and systems for improved generation and georeferencing of floor plans are presented. In one embodiment, a method is presented that includes receiving images that depict sheets of a blueprint of a structure. Subsets of the images depicting floor sheets and elevation sheets may be identified. Exterior contours may be extracted from the images depicting floor sheets and elevation contours may be extracted from the images depicting elevation sheets. A corresponding structure within a three-dimensional map may be identified based on the exterior contours and the elevation contours. A three-dimensional contour of the exterior of the structure may be extracted from the three-dimensional map.