Supercharge Your Innovation With Domain-Expert AI Agents!

Visual odometer method based on FREAK algorithm and key frame judgment algorithm

A visual odometry and judgment algorithm technology, applied in the field of pattern recognition, can solve the problems of difficult detection of specific environmental features, poor real-time performance, and too much redundant information stored in the map, so as to reduce the number of matching times, improve real-time performance, and reduce The effect of redundant information

Pending Publication Date: 2021-04-13
BEIJING UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is: in order to solve these problems of existing algorithm, the present invention provides a kind of visual odometry method based on FREAK algorithm and key frame judgment algorithm, and its purpose is to solve existing real-time performance is not good, specific environment Difficulty in feature detection and technical problems of too much redundant information stored in the map

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 odometer method based on FREAK algorithm and key frame judgment algorithm
  • Visual odometer method based on FREAK algorithm and key frame judgment algorithm
  • Visual odometer method based on FREAK algorithm and key frame judgment algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments, but the examples are only used to explain the present invention and are not limited thereto.

[0033] Step 1: Obtain the video stream through the camera, set one frame as the first frame, and use it as the first key frame;

[0034] Step 2: Establish a multi-scale image pyramid space for the current image;

[0035] Step 3: Draw a circle with a radius of 3 pixels with a pixel P as the center, and the circle passes through a total of 16 surrounding pixels.

[0036] Step 4: Calculate the pixel difference between the upper and lower pixel points and the center point p, if their absolute values ​​are less than 20% of the center point P pixel, point p cannot be a feature point, and judge the next pixel point; otherwise, Use the central point P as the candidate point of this step, and continue to make subsequent judgments;

[0037] Step 5: If p is the candida...

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 odometer method based on an FREAK algorithm and a key frame judgment algorithm, and belongs to the technical field of pattern recognition. According to the method, a feature detection method based on FREAK is adopted, the problems of real-time performance, illumination scale invariance and feature detection difficulty in some environments are solved, redundant information of map storage is greatly reduced through a new key frame judgment method, the matching frequency is reduced, and therefore the real-time performance of the system is further improved.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and more specifically relates to a visual odometer method based on a FREAK algorithm and a key frame determination algorithm. Background technique [0002] Visual odometry is a method that uses the video stream collected by the camera to provide the relative motion trajectory of the object. At present, the existing methods can achieve certain effects, but there are still some problems, such as poor real-time performance, and the problem of not being able to detect feature points in environments such as dim light, and after the system has been running for a period of time, there are map storage problems. The problem of too much redundant information. Contents of the invention [0003] The purpose of the present invention is: in order to solve these problems of existing algorithm, the present invention provides a kind of visual odometry method based on FREAK algorithm and key frame j...

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): G06K9/00G06T7/73
CPCG06T7/73G06T2207/10016G06T2207/20016G06V20/48G06V20/46
Inventor 杨胜齐陈峥陈继良
Owner BEIJING UNIV OF TECH
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