Indoor Localization via Building-Perimeter Feature Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Indoor localization technologies face challenges in accurately determining the location of mobile devices within buildings due to the unavailability and inaccuracy of Global Navigation Satellite System (GNSS) signals, and the difficulty in learning the location of radio nodes in indoor environments, which hinders efficient radio mapping and positioning.
Innovation Solution
The method involves detecting building-perimeter features in captured sensor data, such as images, to determine the location of a mobile device relative to the building perimeter, using machine-learning trained classifiers to identify geometric planes and orientations, and associating this information with radio data to update radio maps and estimate device positions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If radio-based positioning is used indoors, then positioning can be achieved where GNSS is unavailable, but the location of access points must be learned which complicates the system
Solution Approach 1:
The patent uses building perimeter features (windows, doors, walls) detected via imaging sensors as intermediary objects to establish location references. These physical features serve as mediators between the mobile device and the building structure, enabling the system to learn access point locations indirectly through geometric relationships rather than direct measurement, thus reducing radio mapping complexity while maintaining positioning reliability
Solution Approach 2:
The system performs preliminary detection and identification of building perimeter features before conducting radio mapping. By first establishing the geometric framework of the building through image analysis and feature detection, the system prepares the spatial context in advance, making subsequent radio node location learning more efficient and less complex
2Measurement precision
If radio mapping is performed to learn access point locations, then positioning accuracy improves, but the process requires frequent reference location fixes which reduces efficiency
Solution Approach 1:
The system uses the mobile device's own imaging sensors and detected building perimeter features to establish location references, rather than relying on external reference locations. This self-service approach allows the device to autonomously learn access point locations through geometric relationships with detected features, eliminating the need for frequent external reference fixes and improving positioning efficiency while maintaining accuracy
Solution Approach 2:
The patent transitions from traditional 2D radio signal-based positioning to 3D spatial positioning by incorporating depth information from imaging sensors and geometric relationships with building features. This dimensional enhancement provides more robust location references that reduce the frequency of required reference fixes, thereby improving both accuracy and efficiency
3Measurement precision
If building perimeter features are detected using imaging sensors, then location determination accuracy improves, but the device complexity increases
Solution Approach 1:
The patent employs the mobile device's existing imaging sensors (camera) for dual purposes: traditional photography/capture and building perimeter feature detection for positioning. By making the imaging sensor multi-functional, the system achieves improved location determination accuracy without adding dedicated detection hardware, thus limiting the increase in device complexity to software processing only
Data Source
AI summary
A geometric plane defined by a building-perimeter feature in an image capture by a mobile device is identified. The building-perimeter feature is co-located with an exterior wall of a building within which the mobile device is located. An orientation and/or location of the mobile device with respect to the geometric plane and an orientation of the mobile device with respect to a defined geographical direction are determined. A building model for the building and defining perimeter portions of the building (each perimeter portion corresponding to a respective exterior wall) is obtained or accessed. Based on the orientation and/or location of the mobile device with respect to the geometric plane, the orientation of the mobile device with respect to the defined geographical direction, and/or the building model, a particular perimeter portion of the building model that corresponds to the building-perimeter feature is identified and corresponding location information is determined.