Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Indoor positioning method based on Wi-Fi and image fusion fingerprints

An indoor positioning and image fusion technology, which is applied in the directions of location information-based services, specific environment-based services, and image enhancement.

Active Publication Date: 2021-08-27
BEIJING UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem of low accuracy of the single fingerprint positioning method, the present invention proposes to use KPCA to extract the positioning features in the RSSI signal, use LBP to extract the positioning features of the scene image, and realize the prediction of the position coordinates by constructing the LightGBM positioning model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Indoor positioning method based on Wi-Fi and image fusion fingerprints
  • Indoor positioning method based on Wi-Fi and image fusion fingerprints
  • Indoor positioning method based on Wi-Fi and image fusion fingerprints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The method of the present invention see examples figure 1 . Implementation of the offline phase is the RSSI value and the surrounding scene image at the AP at the point of the mobile device, and record the real coordinates of the location. The primitive Wi-Fi fingerprint is subjected to the primitive Wi-Fi fingerprint, and the noise signal is removed; the LBP is extracted with the scene image, and the histogram is calculated as the image fingerprint, and the Wi-Fi fingerprint feature and scene image characteristics are calculated. Get a fusion fingerprint; use the generated fusion fingerprint data set to classify the returning tree as the base learner, in the negative direction of the previous library loss function, in the negative direction of the gradient direction, use the addition model to subclassify the marked tree linear combination, generate LightGBM positioning model. At this stage, the RSSI value of the AP at the test point and the surrounding scene images are use...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an indoor positioning algorithm based on Wi-Fi and image fusion fingerprints, and belongs to the field of indoor positioning. In the off-line stage, reference points are divided for an experiment area. LBP and KPCA positioning features are respectively extracted from the scene image and the Wi-Fi RSSI obtained at the reference point, a fusion fingerprint database is generated, a LightGBM positioning model is obtained through training, and a mapping relation between a fusion fingerprint and a physical position coordinate is established. And then, for Wi-Fi RSSI and a scene image acquired at a test point in an online stage, extracting a KPCA feature of an original Wi-Fi fingerprint, extracting an LBP feature of the scene image, splicing the two features to generate a fusion fingerprint of a point to be positioned, and predicting a current position coordinate by using a trained LightGBM positioning model. According to the method, main positioning features are reserved; the LBP feature has the advantages of gray scale and rotation invariance, and meanwhile, the LBP feature and the Wi-Fi fingerprint are data of the same dimension, so that convenience is provided for fusion, and position modeling can be accurately carried out.

Description

Technical field: [0001] The present invention belongs to the area of ​​the indoor positioning, and is an indoor positioning method for extracting the Wi-Fi fingerprint with the Wi-Fi fingerprint in the offline stage and extracting the LBP feature of the scene image, and splicing to generate a fusion fingerprint, and build a positioning method of the positioning model through the LightGBM. This method can effectively improve indoor positioning accuracy. Background technique: [0002] Location-based service (LBS) has huge research and commercial value has become a researcher's consensus, and the Global Navigation Satellite System (GNSS) provides reliable location service outdoors. Integrating wireless sensors, visual sensors, and acceleration metering smartphones have facilitated indoor positioning services. However, due to the complexity of the indoor environment, there is currently no indoor positioning scheme for large-scale applications. The researchers use the indoor signals f...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04W4/02H04W4/021H04W4/33H04W64/00G06T5/00G06T5/40G06K9/46G06K9/62
CPCH04W4/021H04W4/023H04W4/025H04W4/33H04W64/00G06T5/40G06V10/44G06V10/467G06F18/214G06T5/70Y02D30/70
Inventor 张会清李岳清
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com