Indoor navigation method and system based on CAD architectural drawing and computer vision discrimination

A technology of computer vision and indoor navigation, which is applied in the field of positioning and navigation, and can solve problems such as signal interference, difficulty in sampling, and signal weakening

Inactive Publication Date: 2018-10-23
HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
View PDF15 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing technology has the following defects: 1. The indoor signal of traditional outdoor navigation technology weakens rapidly, and the signal is easily interfered at the same time
2. The existing indoor navigation techn

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 navigation method and system based on CAD architectural drawing and computer vision discrimination

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0029] The invention extracts features from building CAD drawings based on machine learning principles, and realizes indoor building positioning and navigation functions. Such as figure 1 Shown, the inventive method mainly comprises the following contents:

[0030] Machine Learning for Architectural CAD Drawings. Through computer vision recognition technology, feature training is performed on a large number of architectural CAD drawings to obtain the topological relationship of each unit (room, toilet, staircase, passage, etc.) of the architectural CAD drawing.

[0031] Hierarchical path planning algorithm. Establish a hierarchical path planning algorithm based on the D* algorithm to obtain the global optimal path when the starting point and end point are known.

[0032] Sensor data processing. Obtain various sensor data (acceleration sens...

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 navigation method and system based on CAD architectural drawing and computer vision discrimination. Through a large amount of indoor CAD architectural drawings of a building, machine learning is carried out to obtain the topological information characteristics of each indoor unit of the building; at the same time, the indoor unit coordinates and topological relationship of the building are obtained, and the CAD drawings can be automatically identified by a machine. On a server, a machine learning model database is established, a user can choose a correspondingindoor building on the interface end of APP and determines a start position and a final position. The mobile phone APP can obtain the sensor data of the user in real time to obtain the motion state ofthe user and feeds back the motion state to a backstage server, and the server carries out a hierarchical path plan algorithm and gives out the real-time positioning and navigation information of theuser. The provided method and system guarantee the positioning and navigation precision, at the same time, the cost is low, the system does not need a large amount of WIFI terminals and bluetooth terminals, and thus has a strong performance on resisting signal interference, and the positioning and navigation precision is guaranteed effectively.

Description

technical field [0001] The invention relates to the technical field of positioning and navigation, in particular to an indoor navigation method and system. Background technique [0002] At present, GPS and Beidou are widely used in outdoor navigation systems, but how to solve the problem of "navigating the last mile" is the current development trend of navigation systems. The mainstream technology currently applied to indoor navigation systems is the indoor navigation system based on Wi-Fi technology and Bluetooth technology, which obtains the user's coordinates and plans the navigation path by arranging wireless communication modules indoors. With the development of computer vision recognition technology, indoor navigation technology based on computer vision recognition is becoming popular, which matches the image information of the user's location with the background database to obtain the coordinate information of the user's location. At the same time, indoor route navig...

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): G01C21/20
CPCG01C21/206
Inventor 孙路伟张金萍
Owner HARBIN INST OF TECH SHENZHEN GRADUATE SCHOOL
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap