Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A very large-scale image feature point matching method and system

An image feature point and ultra-large-scale technology, applied in the field of computer vision, can solve problems such as efficiency reduction, and achieve the effects of improving efficiency, reducing I/O operations, and reducing frequent I/O operations

Active Publication Date: 2019-08-13
HUAZHONG UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This solves the technical problems of memory overflow and frequent I / O exchanges that lead to decreased efficiency in the prior art

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 very large-scale image feature point matching method and system
  • A very large-scale image feature point matching method and system
  • A very large-scale image feature point matching method and system

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0053] Such as figure 1 Shown is a schematic flowchart of a very large-scale image feature point matching method disclosed in an embodiment of the present invention. exist figure 1 Among them, the core innovation includes two parts: one is breadth-first traversal to sort images and image pairs; the other is out-of-core feature matching based on efficient memory management. The final matching information is saved as a file and can be used for subsequent 3D reconstruction. Its specific implementation is as follows:

[0054] (1) Feature point extraction and initial filtering of image pairs: extract scale-invariant feature transform (SIFT) feature points for each image, and then use an image retrieval method to find image neighbors, and eliminate inappropriate features. Related image pairs to obtain image pairs with overlapping scenes;

[0055] (2) Breadth-first traversal to rearrange the sequence of images and image pairs: use images as nodes and image pairs to form edges to ...

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 super-large scale image feature points matching method and system thereof. The method comprises the following steps: firstly, image matching pairs are obtained by caring out image near neighbor search; images are acted as nodes, the edges of constitution among the image neighbors form an undigraph, the undigraph is caring out priority sorting of breadth, then the images and image pairs are obtained; the feature information of the images are sorted again according to the sorting result, and the feature information of the images is divided and stored as binary files; the binary files with the feature information are read according to the order of sequence; according to the images after being sorted, the characteristics match is being carried out in sequence, and the subsequent useless feature information is released in time; the feature information is iteratively read and the feature matching is being carried out until all images finish matching. The method and system has the advantages that one read and local full both of image feature points in the process of image matching are ensured, memory is not spilled and at the same moment, the efficiency of algorithm is ensured.

Description

technical field [0001] The invention belongs to the field of computer vision, and more specifically relates to a method and system for matching feature points of super-large-scale images. Background technique [0002] 3D reconstruction of large-scale unordered image sets has been a popular research topic in the field of computer vision in recent decades. This technology can be used in the construction of urban digital maps, the construction of digital museums and the reconstruction of post-disaster buildings. For the 3D reconstruction of large-scale unordered image data sets, in recent years, a complete set of relatively mature and academically recognized reconstruction processes has been established, which mainly includes the following steps: 1) image feature point extraction, 2) feature points between images Matching, 3) Geometry verification of image matching pairs, 4) Estimation of camera pose and sparse 3D point cloud from the matching. Most researchers follow such a ...

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): G06T7/33G06T7/38G06F16/583
CPCG06F16/583G06T2207/10016
Inventor 陶文兵黄文杰孙琨
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com