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

Visual visible light positioning LED-ID detection and recognition method based on machine learning

A technology of machine learning and recognition methods, applied in machine learning, character and pattern recognition, instruments, etc., can solve the problem that high-precision positioning algorithms are meaningless, and different LED detection and recognition are not discussed in detail, so as to promote promotion and use. , the effect of increasing the allowable error range

Pending Publication Date: 2019-12-10
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] So far, indoor VLC localization based on image sensors has been studied in depth, and the positioning accuracy can reach centimeter level, but all these methods have not discussed the detection and identification of different LEDs in detail.
In fact, LED detection and identification are more important than positioning algorithms. If LED-ID cannot be correctly and effectively identified, all high-precision positioning algorithms will be meaningless

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
  • Visual visible light positioning LED-ID detection and recognition method based on machine learning
  • Visual visible light positioning LED-ID detection and recognition method based on machine learning
  • Visual visible light positioning LED-ID detection and recognition method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0030] This embodiment adopts the visual visible light positioning LED-ID detection and recognition method based on machine learning to realize indoor positioning. figure 1 It is a schematic diagram of the implementation of the machine learning-based visual visible light positioning LED-ID detection and recognition method disclosed in this embodiment.

[0031] In this embodiment, the transmitter is composed of STM32 single-chip microcomputer, DD311 driver chip, ordinary white LED, etc., and PWM modulation is performed by STM32 single-chip microcomputer to generate pulse signals with different periods and duty ratios, and the generated pulse signals are input into the DD311 driver chip to drive ordinary White LED emits high-frequency light with different frequencies and zero degrees.

[0032] In this embodiment, the receiving end is a CMOS sensor camera carried by a device for daily use, including: a smart phone, a notebook computer, a tablet computer and a handheld Internet de...

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 visual visible light positioning LED-ID detection and recognition method based on machine learning, and the method comprises the following steps: enabling different LEDs to emit light with different frequencies and duty ratios at a transmitting end through PWM modulation, and achieving the giving of unique IDs to the different LEDs; at a receiving end, using a CMOS camerato shoot an LED, processing an LED picture through an image processing technology, and extracting LED area, stripe number and black and white stripe duty ratio characteristics; training the extractedLED features through a machine, and establishing a classifier; according to the features extracted by the unjudged LEDs, using the classifiers to judge the categories to which the LEDs belong, and achieving LED-ID detection and recognition; and using the detected LED to carry out positioning through an approach method. The LED-ID visible light positioning method is established through machine learning and image processing, the method is simple and feasible, the method can be achieved by modifying an existing lamp and combining a mobile terminal, and wide market value is achieved.

Description

technical field [0001] The invention relates to the technical field of LED visual detection and identification, in particular to a machine learning-based visual visible light positioning LED-ID detection and identification method. Background technique [0002] In recent years, with the development of the economy and the advancement of technology, the demand for indoor navigation and positioning is also increasing, such as indoor service robots, indoor parking, and indoor positioning services (LBS). However, traditional indoor positioning methods, such as wireless local area network (WLAN), ZigBee, Bluetooth, infrared positioning, ultrasonic positioning, etc., can only provide positioning accuracy of tens of centimeters to several meters, and they are also susceptible to electromagnetic wave interference. Therefore, it is urgent to propose a high-precision indoor positioning method based on visible light communication (VLC). [0003] There are two types of indoor positioning...

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
IPC IPC(8): G06K9/62G06N20/00G06T7/11G06T7/187G06T7/62H04B10/116H04B10/516
CPCG06T7/11G06T7/187G06T7/62G06N20/00H04B10/116H04B10/516G06F18/2411G06F18/214
Inventor 文尚胜李竞宜关伟鹏
Owner SOUTH CHINA 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