Automated Building Mapping From Images Without Depth Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating and utilizing building interior information, such as floor plans, are inefficient and inaccurate, particularly in capturing and representing interior layouts without physical presence, and require significant effort to maintain and scale accurately.
Innovation Solution
An automated system using computing devices to generate mapping information from acquired images, including 360° panorama images, without depth information, which assesses image quality and process characteristics to improve generation efficiency and accuracy, and provides feedback for image acquisition adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If floor plans are manually constructed to represent building interiors, then accuracy of layout representation is improved, but time and effort required for construction and maintenance increases
Solution Approach 1:
The patent replaces manual mechanical construction of floor plans with an automated computer vision system that processes images to generate floor plans automatically. The system uses image acquisition devices, processing modules, and database storage to substitute human manual work with automated computational processes, thereby reducing time and effort while maintaining accuracy through systematic image analysis.
Solution Approach 2:
The patent creates copies of building interior information by generating floor plan representations from captured images. Instead of manually recreating layout information, the system automatically copies spatial relationships and structural elements from images into standardized floor plan formats, enabling rapid reproduction and maintenance of accurate building representations.
2Measurement precision
If depth-sensing equipment is used to acquire building interior information, then measurement precision of distances and dimensions is improved, but device complexity and cost increases
Solution Approach 1:
The patent extracts depth and dimensional information from standard 2D images through computational analysis rather than requiring specialized depth-sensing hardware. The system takes out the need for complex depth sensors by using image processing techniques, feature detection, and geometric reasoning to infer three-dimensional spatial relationships from two-dimensional image data.
Solution Approach 2:
The patent substitutes physical depth-sensing equipment with a computational image processing system. Instead of using LiDAR, time-of-flight cameras, or other active depth-sensing hardware, the system replaces these mechanical/optical systems with software-based analysis of standard images, thereby reducing device complexity while achieving comparable measurement precision.
3Ease of manufacture
If traditional floor plans are used to display building interior information, then ease of creation is improved, but ease of operation and visualization for remote users deteriorates
Solution Approach 1:
The patent creates a multi-functional system that generates floor plans with embedded navigation capabilities, allowing the same output to serve both as a static reference document and as an interactive navigation guide. The floor plans include directional information, spatial relationships, and visual cues that enable remote users to navigate and visualize building interiors effectively, combining the simplicity of traditional floor plans with enhanced operational functionality.
4Productivity
If automated image processing is used to generate floor plans, then productivity is improved, but measurement precision of generated mapping information may deteriorate
Solution Approach 1:
The patent incorporates feedback mechanisms where the automated system processes images to generate floor plans, then uses analysis modules to verify the accuracy of generated mapping information against the original images and spatial constraints. The system provides feedback loops that validate measurements, check geometric consistency, and ensure that automated generation maintains precision requirements while achieving high productivity through automation.
Data Source
AI summary
Techniques are described for computing devices to perform automated operations related to using images acquired in a building as part of an automated generation process of a floor plan or other mapping information for the building, in some cases without using depth information from depth-sensing equipment about distances from the images' acquisition locations to objects in the surrounding building, and for subsequent use in further automated manners, such as controlling navigation of mobile devices and/or for display to end users in a corresponding graphical user interface. The analysis and assessment of the building images may, for example, include performing an automated assessment of one or more characteristics of the mapping information generation process (e.g., a predicted amount of time for completion) and to provide automated instructions (e.g., to adjust image acquisition device settings) or other feedback to improve the generation process (e.g., reduce that predicted time).