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

Improved ORB algorithm based on fusion of improved LBP features and LNDP features

An algorithm and feature point technology, which is applied in the field of image processing to reduce sensitivity, speed up the detection process, and improve matching accuracy.

Inactive Publication Date: 2020-01-31
TAIYUAN UNIV OF TECH
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Aiming at the problem that LBP features and LNDP features are too sensitive to noise and local image changes, the image block method is applied to the generation of improved LBP features and LNDP features

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
  • Improved ORB algorithm based on fusion of improved LBP features and LNDP features
  • Improved ORB algorithm based on fusion of improved LBP features and LNDP features
  • Improved ORB algorithm based on fusion of improved LBP features and LNDP features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] An improved ORB algorithm based on the fusion of improved LBP features and LNDP features, such as figure 1 As shown, it includes the following two steps:

[0051] Step 1: Feature point detection algorithm based on multi-scale FAST detection, the specific steps are as follows:

[0052] (1) Establish a scale pyramid to achieve multi-scale invariance of feature points. Set a scaling factor scaleFactor (1.2 by default) and nlevels of the pyramid (8 by default). Reduce the original image into nlevels images according to the scaling factor. The scaled image is: I'=I / scaleFactor k (k=1, 2, . . . , nlevels).

[0053] (2) Use Fast to detect feature points on images of different scales: For 16 points on the image with point p as the center and a radius of 3, calculate the pixel difference between p1, p9 and the center p, if their absolute values ​​are less than the threshold, then Point p cannot be a feature point, so it is removed directly; otherwise, it is used as a candid...

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 improved ORB algorithm based on fusion of improved LBP features and LNDP features, belongs to the field of image processing, and is mainly used for solving the problem of lowmatching precision of a traditional ORB feature extraction algorithm. The algorithm is mainly divided into two steps: step 1, rapidly detecting feature points through a multi-scale FAST algorithm, calculating a main direction for the feature points, and endowing the feature points with rotation invariance and scale invariance; and 2, extracting LBP / LNDP features of the feature points, and adopting a method of replacing the pixel points with the pixel blocks to improve the robustness of the feature points to noise. According to the method, the LBP features and the LNDP features are combined, local information of the feature points is described more sufficiently, and the feature matching performance is improved on the basis that the real-time performance of the algorithm is not reduced.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to an improved ORB algorithm based on the fusion of improved LBP features and LNDP features. Background technique [0002] As the key technology of image processing, image matching has always been a research hotspot in image processing. It has been widely used in face recognition, text matching, object tracking, image stitching, object recognition and other fields. [0003] Scale Invariant Feature Transform (SIFT) is a feature point detection method based on scale space formally proposed by Lowe in 1999 and improved in 2004. The SIFT algorithm has complete scale invariance in theory, and has good anti-interference ability to illumination, noise, rotation, scaling, and occlusion, and is one of the best performing algorithms at present. However, feature point detection based on scale space extremum and feature description based on gradient histogram severely restrict the computationa...

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): G06K9/62G06K9/46
CPCG06V10/40G06V10/467G06F18/22G06F18/253
Inventor 王志飞程兰任密蜂阎高伟续欣莹
Owner TAIYUAN 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