Floorplan Georeferencing From Blueprint Contours and 3D Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing blueprints, particularly those in raster image format, are difficult to quickly parse for layout information due to the inclusion of various types of sheets and lack of coordinate data, hindering emergency responders' ability to determine building layouts and locations within the building.
Innovation Solution
A system utilizing machine learning models to identify and extract exterior and interior contours from floor and elevation sheets, aligning them with a georeferenced three-dimensional map to determine corresponding building coordinates and generate a three-dimensional representation of the structure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If blueprints are provided in raster image format with multiple sheet types, then comprehensive building information is preserved, but parsing speed and ease of extracting layout information deteriorates
Solution Approach 1:
The system segments the complex blueprint document into distinct components by identifying and separating floor sheets from elevation sheets using machine learning classification. This segmentation allows targeted processing of different sheet types, improving parsing efficiency while preserving all necessary building layout information from both floor plans and elevations.
Solution Approach 2:
The system extracts only the relevant exterior contour information from the floor sheets and elevation sheets, separating this key data from the rest of the blueprint content. This extraction focuses computational resources on the essential layout information needed for emergency response, significantly improving parsing speed while maintaining information quality.
2Measurement precision
If traditional blueprint parsing methods are used, then all blueprint details are captured, but time required to determine building layout and location increases
Solution Approach 1:
The system performs preliminary classification of blueprint sheets into floor sheets and elevation sheets before detailed contour extraction. This preliminary action using machine learning models prepares the data structure in advance, enabling faster subsequent processing and reducing the overall time required to determine building layout and location while maintaining precise coordinate extraction.
Solution Approach 2:
The system creates simplified contour representations (copies) of the building layout from the detailed blueprints. These contour copies capture the essential geometric information needed for location determination and emergency response planning, reducing processing time while preserving the necessary spatial accuracy through coordinate extraction from three-dimensional maps.
3Reliability
If manual analysis of blueprints is performed, then accurate interpretation is achieved, but response time for emergency situations deteriorates
Solution Approach 1:
The system replaces manual mechanical analysis of blueprints with automated machine learning models that classify sheet types and extract contours. This substitution maintains reliable interpretation accuracy through trained algorithms while dramatically reducing response time, enabling rapid building layout determination for emergency situations without human intervention in the critical extraction phases.
Solution Approach 2:
The system changes the processing parameters from manual visual inspection to automated computational analysis using machine learning. This parameter change enables the system to process blueprint images rapidly while maintaining accurate interpretation through trained models, achieving both speed and reliability required for emergency response applications.
Data Source
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.