AR Location Refinement via Scene Image Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing location-based services struggle to provide accurate user location information, especially in multistory buildings, as current positioning methods fail to determine elevation information, leading to inefficient delivery of promotional information and increased telecommunication network bandwidth usage.
Innovation Solution
An augmented reality (AR) technology approach that captures and matches scene pictures with a database of images marked with detailed location information, refining user location to include elevation data, allowing for precise service information delivery based on floor level.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional positioning methods are used to determine user location, then the positioning process is simple, but elevation information cannot be determined and location precision is insufficient
Solution Approach 1:
The positioning process is segmented into two stages: first obtaining initial location information through traditional positioning methods, then refining it by matching captured images with database images to determine elevation and floor level. This segmentation allows the system to achieve high precision without requiring complex positioning hardware throughout.
Solution Approach 2:
Image matching serves as an intermediary mechanism between traditional positioning and precise location determination. By using captured images as a mediator to query the database for elevation and floor information, the system achieves three-dimensional location precision without directly complexifying the positioning hardware.
2Productivity
If promotional information is sent to all users in a multistory building, then all users receive information, but telecommunication network bandwidth is wasted
Solution Approach 1:
The system applies local quality by delivering promotional information specifically to users on the same floor as the target merchant, rather than broadcasting to all users in the building. This localized delivery approach improves service efficiency while reducing unnecessary network bandwidth consumption.
Solution Approach 2:
The system changes the parameter of location information from two-dimensional (latitude and longitude) to three-dimensional by incorporating elevation and floor level data. This parameter enhancement enables precise filtering and targeting of promotional information to specific floors, optimizing both service delivery efficiency and network resource utilization.
3Measurement precision
If image matching is performed between captured scene picture and scene picture set, then refined location information including elevation is obtained, but processing time increases
Solution Approach 1:
The system performs preliminary action by pre-establishing a database of images with associated location and elevation information before actual positioning is needed. During runtime, the system only needs to capture an image and query the pre-built database, significantly reducing processing time compared to real-time analysis.
Solution Approach 2:
The system applies partial action by first using traditional positioning methods to obtain initial location information, then selectively performing image matching only to determine elevation and floor level. This partial approach achieves necessary precision without the excessive processing time of complete real-time image analysis.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An augmented reality (AR) client terminal identifies initial location information for a location of a user. A scene picture associated with the location of the user is captured. Image matching is performed between the captured scene picture and scene pictures in a scene picture set. The scene picture set is generated based on the initial location information. Each scene picture in the scene picture set is associated with detailed location information. In response to the captured scene picture matching a particular scene picture in the scene picture set, refined location information for the location of the user is determined based on the detailed location information of the particular scene picture.