CAD Drawing Conversion to Indoor Maps With Automated Room Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Creating indoor maps from architectural CAD drawings is a cumbersome process due to the lack of universal standards and requires significant human interaction, as existing automated tools are not fully automated.
Innovation Solution
A computer-implemented method that preprocesses CAD drawings to create a text database, applies machine-learning algorithms for floor, furniture, and room detection, and generates indoor maps with minimal human intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated tools are used to create indoor maps from CAD drawings, then productivity is improved, but the extent of automation is insufficient and requires significant human interaction
Solution Approach 1:
The system automatically performs preprocessing of CAD drawings, floor detection, furniture detection, and room detection without requiring human intervention at each stage. The machine-learning algorithms self-correct and refine results through automated iterations, allowing the system to serve itself rather than requiring constant human oversight
Solution Approach 2:
A text database is introduced as an intermediary component that stores and manages extracted information from CAD drawings. This intermediary structure enables automated cross-referencing and validation between different drawing elements, reducing the need for manual verification while maintaining accuracy
2Measurement precision
If manual processing is used to create indoor maps from CAD drawings, then accuracy can be maintained through human review, but productivity is reduced due to the cumbersome process
Solution Approach 1:
The system implements automated feedback loops where machine-learning algorithms continuously refine their output based on detected patterns and validation results. Each detection stage (floor, furniture, room) provides feedback to subsequent stages, enabling automated quality assurance that maintains accuracy while increasing productivity
Solution Approach 2:
The system performs preliminary preprocessing of CAD drawings to extract and organize text and graphical data before main detection processes. This preliminary organization of information in the text database enables more accurate and efficient subsequent processing, maintaining precision while reducing overall processing time
3Manufacturing precision
If multiple detection stages are implemented for floors, furniture, and rooms, then manufacturing precision is improved, but device complexity increases
Solution Approach 1:
The detection process is segmented into distinct sequential stages: floor detection, furniture detection, and room detection. Each stage uses specialized machine-learning algorithms optimized for its specific task, allowing high precision for each detection type while managing complexity through modular organization of the overall system
4Loss of time
If CAD drawings are processed without preprocessing, then loss of time is reduced, but measurement precision deteriorates due to lack of data organization
Solution Approach 1:
Preprocessing is performed as a preliminary action that extracts and organizes text data with location information before main detection processes. This preliminary organization creates a structured text database that enables faster and more accurate subsequent processing, reducing overall time loss while improving precision
Data Source
AI summary
Automating conversion of drawings to indoor maps and plans. One example is a computer-implemented method comprising: preprocessing a CAD drawing to create a text database containing text from the CAD drawing and associations of the text with locations within the CAD drawing; determining a floor depicted in the CAD drawing, the determining results in a floor-level outline; identifying a plurality of room-level outlines within the floor-level outline, the plurality of room-level outlines corresponds to a respective plurality of rooms; selecting a name of a first room from the plurality of rooms, the selecting based on text within the text database; and creating an indoor map including the name of the first room, the name of the first room associated with a location of the first room within the floor-level outline.