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

Indoor positioning method based on significance feature recognition

A feature recognition and indoor positioning technology, applied in the direction of electromagnetic wave re-radiation, measuring devices, instruments, etc., can solve the problem of weak GPS positioning signal, achieve the effect of narrowing the search range, improving accuracy, and ensuring real-time performance

Active Publication Date: 2019-02-19
SHANDONG INSPUR SCI RES INST CO LTD
View PDF10 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above technical problems, the present invention proposes an indoor positioning method based on salient feature recognition, which solves the problem of weak indoor GPS positioning signals and improves the accuracy of indoor positioning

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 significance feature recognition
  • Indoor positioning method based on significance feature recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Below in conjunction with accompanying drawing, content of the present invention is set forth in more detail:

[0031] Such as figure 1 As shown in , use a high-definition camera to collect indoor panoramic images, and complete the distance measurement with the point cloud data of the lidar. Based on the panoramic map, the salient features are identified, the image is segmented, and then the real-scene shooting images of the actual mobile camera equipment in different time periods are used to perform the distance measurement. Calibrate and process to form a panoramic positioning model rule library, compress the model and rule library, and place them in a mobile smart device with a camera function; the mobile smart device shoots multiple real scenes in different directions at a fixed point, performs image matching, and extracts The spatial structure information of the image is cross-referenced and positioned. In addition, mobile smart devices can also use wifi, bluetoot...

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 provides an indoor positioning method based on a significance feature identification, and relates to the technical fields of significance target detection, deep learning and indoor positioning. The method comprises the following steps: adopting a high-definition camera cooperating with a laser radar to complete an indoor panoramic map modeling, extracting image saliency features adopting a computer vision technique; performing training, correcting and processing through a large number of real-scene images to form a model; finally performing an image matching through a real-scenephotographing of an intelligent equipment to extract space structure data, so as to realize an accurate positioning. The indoor positioning method based on the significance feature identification solves the problem that indoor GPS positioning signals are weak, and eliminates influences generated by movements of a dynamic object, so that the instantaneity of scenes of the real-scene images is guaranteed, the accuracy of an image identification is improved, thereby improving the precision of the indoor positioning.

Description

technical field [0001] The present invention relates to salient target detection, deep learning and indoor positioning technology, in particular to an indoor positioning method based on salient feature recognition. Background technique [0002] With the development of strong applications such as precision marketing and indoor navigation services, indoor positioning has attracted more and more attention. There are a large number of application cases in various indoor scenarios such as airports, railway stations, shopping malls, factories, and schools. Indoor positioning refers to the position positioning in the indoor environment. Due to the limitation of the environment, outdoor smart phones can easily achieve positioning using GPS sensors. However, when entering indoors, smart devices often cannot receive GPS signals, and it is difficult to achieve accurate positioning. . [0003] At present, the traditional indoor method in the industry is to use indoor WiFi, Bluetooth, R...

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): G01C21/20G01S17/08
CPCG01C21/206G01S17/08
Inventor 孙善宝徐驰于治楼
Owner SHANDONG INSPUR SCI RES INST CO LTD
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