A wifi indoor positioning method based on convolutional neural network recognition technology

A convolutional neural network, indoor positioning technology, applied in positioning, instruments, measuring devices, etc., can solve the problems of a large amount of investment in underlying hardware facilities, poor indoor positioning effect, and easy interference from other lights.

Active Publication Date: 2021-09-14
HEFEI UNIV OF TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The positioning system is complex and consumes a lot of power. Since the light cannot pass through obstacles, the infrared rays can only be transmitted at the line of sight and are easily interfered by other lights. In addition, the transmission distance of infrared rays is relatively short, making the indoor positioning effect very poor.
When the mobile device is placed in the pocket or blocked by the wall, it cannot work normally, and the receiving antenna needs to be installed in each room and corridor, resulting in a higher overall cost
[0006] Ultrasound-based positioning technology is used in some experimental work, but there are few commercial devices that actually use ultrasonic waves, so there are not many practical applications, and it is easily affected by multipath effects and non-line-of-sight propagation, which reduces positioning accuracy; at the same time , it also requires a large investment in underlying hardware facilities, and the overall cost is relatively high
[0007] Radio frequency identification and positioning technology uses radio frequency to conduct non-contact two-way communication and exchange data to achieve the purpose of mobile device identification and positioning, but this technology is not easy to integrate into mobile devices, and the working distance is short

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
  • A wifi indoor positioning method based on convolutional neural network recognition technology
  • A wifi indoor positioning method based on convolutional neural network recognition technology
  • A wifi indoor positioning method based on convolutional neural network recognition technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] see figure 1 and figure 2 In this embodiment, the WIFI indoor positioning method based on the convolutional neural network recognition technology is carried out as follows:

[0040] Step 1. Use the circumscribed rectangle of an indoor space as the WIFI indoor positioning area, divide the WIFI indoor positioning area evenly into a square grid, and use the center point of each square grid as a reference point to form a reference point set CP, CP ={CP 1 ,CP 2 ,...,CP i ,...,CP a}, CP i is the i-th reference point, which refers to the reference point in the i-th square grid, i=1,2,...,a.

[0041] The number of square grids and the size of the square grids are related to the specific positioning requirements and the size of the indoor scene. The larger the number of square grids and the smaller the size of the square grids, the higher the positioning accuracy, and at the same time, the higher the cost required for building the training set of the positioning fingerpr...

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 a WIFI indoor positioning method based on convolutional neural network identification technology. Firstly, the indoor positioning area is divided into reference points, and each reference point is subjected to WIFI signal acquisition, and then the data of each reference point is respectively processed and passed through The wavelet transform constructs a primary positioning fingerprint library for the feature map of the corresponding position; then performs pixel transformation on the feature map of each reference point to construct a training set of the positioning fingerprint library, and tags the feature map of each reference point in the training set and sends it to the improved The classification model is obtained by training in the convolutional neural network model; finally, by sampling the WIFI signal of the location to be tested, after data processing, the feature map of the corresponding location is sent to the obtained classification model for classification by wavelet transform, and the location category is weighted and averaged. In this way, the positioning for the position to be measured is realized, that is, the WIFI indoor positioning is realized. The invention is particularly suitable for application in commercial occasions, and has simple equipment and low power consumption.

Description

technical field [0001] The invention relates to a WIFI indoor positioning method, in particular to a WIFI indoor positioning method based on convolutional neural network identification technology, which is applicable to various indoor positioning technologies such as product positioning in large supermarkets or shopping malls, and mobile phone positioning. Background technique [0002] With the continuous development and popularization of wireless communication technology and network technology, various new services and new needs emerge in an endless stream, among which location-aware computing and location-based services play a vital role in people's production and life, how to determine the user Location is the primary issue for implementing the aforementioned applications, so positioning technology is a core issue for location-aware computing and location-based services. Although the mature application of GPS technology can meet people's various needs for outdoor position...

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 Patents(China)
IPC IPC(8): G01S5/02
CPCG01S5/0278
Inventor 李奇越周娜娜曲恒何云鹏余浩
Owner HEFEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products