Indoor Image Localization on Floor Plans Without Depth Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in accurately determining the acquisition location of images within building interiors and effectively utilizing this information for navigation and representation.
Innovation Solution
The use of computing devices to automate the determination of image acquisition locations by analyzing visual data and comparing it to floor plan information, without requiring depth sensors or other distance-measuring devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If floor plans are manually constructed and maintained to represent building interiors, then layout and detail information can be provided, but the process becomes difficult and time-consuming
Solution Approach 1:
The patent replaces manual mechanical processes of constructing and maintaining floor plans with an automated computer vision system. The system uses image processing algorithms to automatically generate and update floor plans from photographs, eliminating the need for manual measurement, drawing, and maintenance while preserving complete building interior information.
Solution Approach 2:
The patent creates automated visual copies of building interiors through systematic photography and image processing. Multiple photographs are processed to generate accurate floor plan representations that can be easily updated by simply capturing new images, rather than manually redrawing entire plans.
2Measurement precision
If depth sensors or distance-measuring devices are used to determine image acquisition locations, then navigation accuracy can be improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces physical depth sensors and distance-measuring devices with a computer vision-based optical system. The method uses 2D image analysis and geometric relationships to infer 3D spatial information and determine camera positions, achieving accurate location determination without requiring additional sensing hardware.
Solution Approach 2:
The patent introduces floor plan images and feature point correspondence as an intermediary between the captured images and the final location determination. By matching features between reference floor plans and captured images, the system indirectly determines acquisition locations through visual correspondence rather than direct measurement.
3Loss of information
If comprehensive building interior information is captured and represented, then navigation and representation quality improve, but data processing and visualization complexity increase
Solution Approach 1:
The patent divides the building interior into discrete manageable units represented as floor plans for individual rooms or areas. Each floor plan captures local geometric and semantic information, which can be independently processed and then integrated into a complete building representation, reducing overall system complexity.
Solution Approach 2:
The patent transforms 3D spatial information into 2D floor plan representations that preserve essential geometric relationships and navigation information. This dimensional reduction simplifies data processing and visualization while maintaining the information needed for navigation and spatial understanding.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
Techniques are described for using computing devices to perform automated operations for determining the acquisition location of an image using an analysis of the image's visual contents. In at least some situations, images to be analyzed include panorama images acquired at acquisition locations in an interior of a multi-room building, and the determined acquisition location information includes a location on a floor plan of the building and in some cases orientation direction information - in at least some such situations, the acquisition location determination is performed without having or using information from any distance-measuring devices about distances from an image's acquisition location to objects in the surrounding building. The acquisition location information may be used in various automated manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc.