Hybrid Indoor Positioning via Wireless-Guided Visual Sub-Map Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing indoor positioning technologies, such as wireless and visual positioning, face challenges in accuracy and efficiency, particularly in large venues like malls and supermarkets, where wireless positioning lacks precision and visual positioning requires high computational capacity and large data processing, making real-time positioning difficult.
Innovation Solution
A hybrid positioning method that integrates wireless and visual positioning technologies by using wireless positioning coordinates to select relevant visual sub-maps, reducing data processing and improving accuracy, involving steps like determining matching key frames and projecting coordinates onto accessible paths within a planar environment map.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If visual positioning technology is used to improve positioning accuracy in indoor scenarios, then positioning precision is improved, but computational capacity requirements and data processing load increase significantly
Solution Approach 1:
The patent divides the large-scale venue into multiple visual sub-maps, each covering a specific area. Instead of processing the entire venue map at once, the system segments the positioning problem into smaller sub-problems, matching images against relevant sub-maps only. This reduces computational complexity while maintaining positioning accuracy across the entire large venue.
Solution Approach 2:
The patent extracts and uses wireless positioning coordinates as auxiliary information to guide the visual positioning process. By taking out the wireless positioning data and using it to pre-select relevant visual sub-maps, the system reduces the data processing load for visual positioning while maintaining accuracy, as only relevant sub-maps need to be processed.
2Area of stationary object
If visual positioning technology is applied to large venues like malls and supermarkets, then positioning coverage area is improved, but data processing load and time consumption increase
Solution Approach 1:
The patent segments the large venue into multiple visual sub-maps, allowing the system to handle large coverage areas by processing only relevant portions at a time. This segmentation enables scalable positioning across large venues without proportionally increasing data processing load, as each sub-map can be processed independently and in parallel.
Solution Approach 2:
The patent performs preliminary action by using wireless positioning coordinates to pre-select relevant visual sub-maps before conducting image matching. This preliminary selection step reduces the data processing load for visual positioning, as the system only processes pre-selected sub-maps that are relevant to the current location, rather than processing the entire venue map.
3Device complexity
If wireless positioning technology is used to reduce computational requirements, then device complexity is reduced, but positioning accuracy deteriorates
Solution Approach 1:
The patent merges wireless positioning and visual positioning technologies into a hybrid system. The wireless positioning provides coarse location information with low computational requirements, while visual positioning provides fine-grained accuracy. By combining both technologies, the system achieves high positioning accuracy without requiring the visual positioning system to process all data independently, as wireless data guides the visual processing.
Solution Approach 2:
The patent uses wireless positioning coordinates as an intermediary to guide the visual positioning process. The wireless positioning data acts as a mediator that pre-selects relevant visual sub-maps, reducing the computational load for visual positioning while maintaining its accuracy benefits. This intermediary approach allows the system to leverage both technologies' strengths without fully committing to the high computational requirements of pure visual positioning.
Data Source
AI summary
The present disclosure relates to a positioning method, a positioning server, and a positioning system. The positioning method includes: receiving a wireless positioning coordinate of a moving object; determining a visual sub-map to be matched in a visual map database based on the wireless positioning coordinate; and obtaining a visual positioning coordinates corresponding to a current image of the moving object captured at time of wireless positioning as a positioning result, based on the determined visual sub-map to be matched.