Automated Building Floor Plan Generation Without Depth Measurements
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to effectively capture, represent, and utilize building interior information, such as floor plans, without physical travel, due to difficulties in construction, scaling, and maintaining accuracy and visual representation.
Innovation Solution
Automated techniques generate mapping information from photos of a building's interior using perspective photos and optional supplemental data, determining relative positions and structural shapes without depth measurements, and create visualizations for navigation and display.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional floor plan construction methods are used, then building layout information can be represented, but the process is difficult and time-consuming to construct and maintain
Solution Approach 1:
The patent replaces manual mechanical floor plan construction with automated computer vision analysis. The system uses image processing algorithms to automatically extract building layout information from photographs, eliminating the need for manual measurement and drawing while maintaining accuracy of layout representation.
Solution Approach 2:
The patent creates digital copies of building interiors through photograph analysis. Instead of physically measuring and reconstructing floor plans, the system generates digital representations by analyzing visual data from multiple photographs, enabling rapid replication and updating of building layout information.
2Loss of information
If floor plans are manually constructed to represent building interiors, then layout information is provided, but they are difficult to scale and populate with room interior information
Solution Approach 1:
The patent creates a universal system that handles multiple tasks simultaneously. The same image analysis framework that extracts layout information also identifies room boundaries, detects interior objects, and generates scaled measurements, eliminating the need for separate processes to populate different floor plan elements.
Solution Approach 2:
The patent performs preliminary scaling and measurement during the initial image analysis phase. By calculating scale factors and room dimensions from the photographs before generating the floor plan, the system ensures all subsequent room interior information is automatically populated with correct measurements without requiring later adjustments.
3Measurement precision
If multiple photos are analyzed to generate mapping information, then building layout accuracy is improved, but computing power and time requirements increase
Solution Approach 1:
The patent divides the image analysis process into segmented stages. The system first identifies key structural elements and camera positions from multiple photos, then progressively refines the layout by analyzing relationships between segments. This modular approach reduces computational complexity compared to analyzing all images simultaneously while maintaining precision.
Solution Approach 2:
The patent uses partial action by selectively analyzing only the most informative photographs for detailed measurement. The system identifies key images that provide the most constraint information for layout accuracy and focuses computational resources on these critical images rather than processing every photograph with equal intensity.
4Manufacturing precision
If depth measurements are obtained to improve floor plan accuracy, then scaling precision is enhanced, but the complexity of data collection and processing increases
Solution Approach 1:
The patent introduces scale factors as intermediary variables that connect photograph measurements to real-world dimensions. Instead of directly measuring depth in three dimensions, the system uses two-dimensional photograph analysis to calculate scale factors, which then serve as mediators to accurately scale all floor plan elements without requiring complex depth sensing hardware.
Data Source
AI summary
Techniques are described for using computing devices to perform automated operations to generate mapping information via analysis of visual data of photos of a defined area, and for using the generated mapping information in further automated manners, including to display the generated mapping information via various types of visualizations corresponding graphical user interfaces. In some situations, the defined area includes an interior of a multi-room building, and the generated information includes at least a partial floor plan and/or other modeled representation of the building—in addition, the generating may be further performed without having measured depth information about distances from the photos' acquisition locations to walls or other objects in the surrounding building. The generated floor plan and/or other mapping-related information may be further used in various manners, including for controlling navigation of devices (e.g., autonomous vehicles), etc.