Indoor Positioning via Visual Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional indoor positioning systems face challenges in achieving accurate three-dimensional positioning within indoor environments due to signal instability and limitations in receiving GPS signals, leading to unsuitable positioning techniques for mass use.
Innovation Solution
An indoor positioning method and system that converts panorama images into perspective images, extracts reference feature points, records three-dimensional coordinate values, and generates an indoor map offline, allowing for real-time positioning of portable electronic devices by comparing real-time images with the stored map.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional outdoor positioning systems (GPS) are used for indoor positioning, then positioning speed is fast and accuracy is high in outdoor environments, but positioning accuracy deteriorates significantly indoors due to signal attenuation
Solution Approach 1:
The patent replaces the electromagnetic signal-based GPS positioning system with an image-based visual positioning system. Instead of relying on satellite signals that are blocked indoors, the system uses cameras to capture images and extract feature points for positioning, substituting a mechanical/optical system for an electromagnetic wave-based system that doesn't work indoors.
Solution Approach 2:
The patent introduces feature points and image descriptors as intermediaries between the camera and the positioning system. Rather than directly using GPS signals, the system captures images, extracts feature points, matches them with a pre-built map, and determines position through this intermediary process that works independently of signal strength.
2Reliability
If signal-based indoor positioning techniques are used, then positioning can be achieved without GPS signals, but positioning accuracy deteriorates due to environmental influences making signals unstable
Solution Approach 1:
The patent replaces wireless signal-based positioning (WiFi, Bluetooth, RFID) with an optical image-based positioning system. Instead of measuring signal strength or time of flight of radio waves that are affected by environmental factors, the system uses visual feature matching which is not subject to the same environmental interference.
Solution Approach 2:
The patent creates a pre-built visual map of the indoor environment by capturing images and extracting feature points in advance. This copy of the environment is stored and later used for comparison with real-time images, allowing positioning without relying on unstable signal measurements.
3Loss of information
If RFID tags are disposed on indoor objects for positioning, then specific targets can be identified, but distance determination capability is lost and budget increases
Solution Approach 1:
The patent extracts positioning information from the visual environment itself rather than requiring separate identification tags on objects. Feature points are extracted directly from images of the environment, eliminating the need for RFID tags while maintaining the ability to identify and locate specific positions.
Solution Approach 2:
The patent makes the camera system multi-functional by using it for both capturing images for visual mapping and extracting positioning information. The same imaging device that documents the environment also provides the data for positioning, eliminating the need for separate RFID readers and tags.
4Ease of operation
If base station positioning method is used, then positioning can be achieved through signal time calculation, but positioning accuracy deteriorates with errors reaching hundreds of meters
Solution Approach 1:
The patent replaces the time-based signal measurement system with an image-based visual recognition system. Instead of calculating position from signal travel time which accumulates errors over distance, the system uses visual feature matching which provides accurate positioning regardless of distance from any reference point.
Data Source
AI summary
An indoor positioning method, indoor positioning system and indoor maps creating device thereof are provided. The method includes converting a panorama image corresponding to an indoor environment into a plurality of perspective images, and extracting a plurality of reference feature points and descriptors of the reference feature points from the perspective images; taking a shooting position of the panorama image as an origin, and recoding a plurality of 3D reference coordinate values corresponding to a central position of each perspective images; calculating 3D coordinate values of the reference feature points base on the 3D reference coordinate values, and storing the 3D coordinate values and the descriptors of the reference feature points as an indoor map corresponding to the indoor environment. The method also includes determining a 3D target coordinate value of a portable electronic device with respect to the origin of the indoor maps in the indoor environment.