Supercharge Your Innovation With Domain-Expert AI Agents!

Visual image feature extraction and matching method based on orb and active vision

An image feature extraction and active vision technology, which is applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as EKF dimension disaster, and achieve the effects of shortened operation time, small amount of algorithm calculation, and real-time performance

Active Publication Date: 2020-08-11
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the document "Improving computational and memory requirements of simulation and mapbuilding algorithms", it is pointed out that for EKF-SLAM with full state estimation, the number of feature points continues to increase, which will bring dimensionality disaster to EKF

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 image feature extraction and matching method based on orb and active vision
  • Visual image feature extraction and matching method based on orb and active vision
  • Visual image feature extraction and matching method based on orb and active vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0035] For the convenience of description, the relevant technical terms appearing in the specific implementation are explained first:

[0036] ORB (Oriented Brief) comes from the article "ORB: an efficient alternative to SIFT orSURF", which is a new corner detection and feature description algorithm.

[0037] figure 1 It is a flow chart of the visual image feature extraction and matching method based on ORB and active vision in the present invention.

[0038] In this embodiment, the experimental images are image sequences of the surface of cardiac soft tissue collected by a monocular endoscope. The image sequence resolution is 320×240, and 30 frames of images are taken per second. The internal parameters of the endoscope are: f u =530.9003,f v =581.00362,u 0 =136.63037,v 0 =161.32884,k 1 =-0.2865,k 2 = 0.29524. The hardware and software environment used in the experiment is: Intel(R) Core(TM) i5-2450M@2.5GHz, memory 4G, Windows 7 system, and implemented in MATLAB 2012a...

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 image feature extraction and matching method based on ORB and active vision, which adopts an efficient and fast ORB feature extraction algorithm to extract feature parameters, and then calculates the regional feature distribution index by using the probability statistics method to ensure that the feature points are evenly distributed Under the premise of the premise, select a certain number of feature points according to the probability, and combine the principle and application of active vision to calculate the ellipse search domain of interest, and then use the nearest neighbor matching algorithm and RANSAC algorithm to obtain evenly distributed and stable number of map feature points , with simple calculation and good matching effect, meeting the real-time requirements of the system.

Description

technical field [0001] The invention belongs to the technical field of computer vision image processing, and more specifically relates to a visual image feature extraction and matching method based on ORB and active vision. Background technique [0002] Simultaneous localization and mapping (SLAM) is an important research content of autonomous robot navigation. Its purpose is to estimate the trajectory of the robot and the location of environmental landmarks in a full state while the robot is moving. At present, in terms of algorithms, there are mainly two methods, EKF-SLAM and particle filter-based SLAM. In terms of sensing methods, visual SLAM has gradually become the mainstream in SLAM research due to the advantages of convenient feature extraction, large amount of information, and low cost of visual sensors. [0003] Feature extraction and matching are two important issues in SLAM. The number of features extracted by the feature extraction algorithm and the position di...

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): G06K9/46G06K9/62
CPCG06V10/462G06V10/757
Inventor 刘珊郑文锋曾庆川杨波李晓璐彭小羽
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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