Check patentability & draft patents in minutes with Patsnap Eureka AI!

Loopback detection method based on image blocking

A technology of image segmentation and detection methods, applied in the field of visual positioning and navigation, can solve the problems of poor positioning performance and achieve high accuracy

Active Publication Date: 2019-08-30
ZHEJIANG UNIV
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the visual positioning and navigation system is a process of continuously accumulating relative sensor information, it is impossible to fundamentally remove the impact of errors on the positioning system, and the positioning performance is poor in long-term positioning applications.

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
  • Loopback detection method based on image blocking
  • Loopback detection method based on image blocking
  • Loopback detection method based on image blocking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described below in conjunction with the accompanying drawings.

[0031] refer to Figure 1 ~ Figure 3 , a method for loop detection based on image segmentation, comprising the following steps:

[0032] Step 1. For each input image frame, divide the image into grid images, extract the feature vector of each grid image, and search for several grid images that are similar to the input image frame blocks from the grid images of historical image frame blocks. The grid image forms a grid image candidate for loop closure;

[0033] Step 2: Sorting several grid image candidates that form loops with each grid image of the input image frame blocks, and comprehensively sorting the result to calculate the spatial similarity between the historical image frame and the input image frame, and selecting the corresponding grid image according to the calculation result. The historical image frame with the largest spatial similarity of the input image...

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

A loopback detection method based on image blocking comprises the following steps of 1, for each input image frame, blocking an image into grid images, and extracting a feature vector of each grid image; 2, sequencing, calculating the spatial similarity between the historical image frames and the input image frames through a comprehensive sequencing result, and selecting and recording the historical image frames with the maximum spatial similarity with the input image frames as the optimal candidate image frames; 3, calculating the normalized average texture similarity between the optimal candidate image frame and the input image frame, and calculating the loop reasonability of the optimal candidate image frame and the input image frame according to constraint conditions; 4, if the optimalcandidate image frame satisfies loop reasonability, marking the optimal candidate image frame and the input image frame as a loop image pair, otherwise, not marking the optimal candidate image frameand the input image frame; and 5, adding the input image frame information into the historical image frame to obtain a new input image frame. According to the present invention, the loop detection process can be accelerated, and the accuracy is higher.

Description

technical field [0001] The invention relates to the technical field of visual positioning and navigation, in particular to a loop detection method based on image segmentation. Background technique [0002] With the increasing demand for location-based services, such as shopping mall navigation, hospital guidance, advertisement push, etc., visual positioning and navigation technology has been extensively researched and applied. Since the visual positioning and navigation system is a process of continuously accumulating relative sensor information, it is impossible to fundamentally remove the impact of errors on the positioning system, and the positioning performance is poor in long-term positioning applications. [0003] The introduction of loop detection solves the performance limitations of visual localization well. Its main task is to find the places that have been visited repeatedly in the image sequence, and correct the system error by comparing the positioning data diff...

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): G06K9/62G06F16/587
CPCG06F16/587G06F18/22
Inventor 潘赟杨哲包瑶琦朱怀宇
Owner ZHEJIANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com