A fast and robust indoor positioning method for robots based on panoramic vision

A panoramic vision and high robustness technology, applied in the direction of instruments, measuring devices, surveying and navigation, etc., can solve the problems of relatively high light requirements, poor robustness, difficult to apply, etc., to achieve streamlined search area and precise positioning capabilities , The effect of shortening the operation time

Active Publication Date: 2018-08-31
HARBIN ENG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the image collected by the panoramic camera is a distorted image, so the color information of the road sign is usually used for positioning, which requires relatively high environmental light and requires no interference of the same color in the environment, so the robustness is poor. Difficult to apply in more complex environments

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 fast and robust indoor positioning method for robots based on panoramic vision
  • A fast and robust indoor positioning method for robots based on panoramic vision
  • A fast and robust indoor positioning method for robots based on panoramic vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0027] The present invention designs a fast and highly robust indoor positioning method for mobile robots based on artificial landmarks, including artificial landmark design, landmark recognition algorithms and positioning algorithms based on panoramic vision. Aiming at the problem that color road signs are greatly affected by light intensity, road signs that are beneficial to feature point recognition are designed, and an artificial road sign recognition algorithm based on feature points is proposed. The problem that the recognition algorithm is affected by the light intensity; for the misrecognition problems caused by factors such as the large amount of calculation of the feature extraction of the panoramic image, the image distortion, the change of the viewing angle and the complex environment, the traditional feature point matching algorithm is improved, and the d...

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

Belonging to the technical field of mobile robot vision positioning, the invention in particular relates to a rapid and high robustness robot indoor positioning method based on panoramic vision. The method consists of: (1) designing road signs based on SURF feature points; (2) in a panoramic image, using an improved SURF feature point matching algorithm to accurately identify the designed road signs rapidly; and (3) according to the identification result of three road signs set in the environment, calculating the accurate position of a robot in a two-dimensional space. The method provided by the invention realizes the indoor positioning function of a mobile robot, is suitable for a robot positioning task under a complex indoor environment, and can be widely applied to navigation of home service robots and industrial robots, and the rapidity and robustness of the algorithm can ensure robot precise positioning ability in the movement process.

Description

technical field [0001] The invention belongs to the technical field of mobile robot visual positioning, and in particular relates to a fast and highly robust indoor positioning method for a robot based on panoramic vision. Background technique [0002] The self-localization of mobile robots has always been a basic and hot issue in the field of robotics research. With its advantages of large amount of information and low price, machine vision is widely used in the research of robot positioning. [0003] In the traditional visual positioning methods, the positioning method based on natural features usually needs to extract a large number of features, the algorithm has a large amount of calculation, is not real-time, and is easily affected by light changes or environmental changes. Compared with the positioning method based on artificial landmarks, it has higher flexibility. By manually setting the characteristics of landmarks, the landmarks can be identified in a targeted man...

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): G01C21/00G01C21/20
CPCG01C21/00G01C21/206
Inventor 朱齐丹刘鹏蔡成涛吕晓龙
Owner HARBIN ENG UNIV
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