Data-clustering-based adaptive image SIFT (Scale Invariant Feature Transform) feature matching method

A technology of feature matching and data clustering, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve problems such as the impact of matching efficiency, achieve a balance between matching efficiency and matching robustness, ensure uniqueness, and improve adaptability sexual effect

Inactive Publication Date: 2011-09-21
BEIHANG UNIV
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But for the methods of Schindler, Muja, etc., since the matching process is constrained by the approximate nearest neighbor query, simply adjusting the control parameters has little effect on the matching efficiency

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
  • Data-clustering-based adaptive image SIFT (Scale Invariant Feature Transform) feature matching method
  • Data-clustering-based adaptive image SIFT (Scale Invariant Feature Transform) feature matching method
  • Data-clustering-based adaptive image SIFT (Scale Invariant Feature Transform) feature matching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Table 1 has provided concrete steps of the present invention:

[0025]

[0026] Table 1

[0027] The process of the present invention includes a two-stage feature clustering part based on the cascaded vocabulary tree in the offline stage and a two-stage feature matching part based on the cascaded vocabulary tree in the online stage. The cascaded vocabulary tree is constructed as follows.

[0028] 1. Cascade Vocabulary tree and its construction

[0029] figure 1 A schematic diagram of the cascaded Vocabulary tree is given.

[0030] The generation of cascaded vocabulary trees is controlled by parameter sets (b, d, f) and (b', d'). The vocabulary tree controlled by (b', d') is called the first type of vocabulary tree, where b' and d' represent branch parameters and depth parameters respectively; the vocabulary tree controlled by (b, d, f) is called the second type of vocabulary tree tree, where (b, d) and (b', d') have the same meaning, and f represents the feature t...

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 data-clustering-based adaptive image SIFT (Scale Invariant Feature Transform) feature matching method, which comprises the following steps of: (1) acquiring a reference image sequence, extracting image SIFT feature sets and clustering all image SIFT feature sets by adopting a k-d (k-dimensional) tree; (2) organizing all the image SIFT feature sets by adopting a cascaded vocabulary tree and carrying out secondary feature clustering on the feature sets contained in vocabulary tree nodes; (3) matching BBF (Best Bin First) purified based on a specific value with a dual-mode clustering feature based on comentropy by using the cascaded vocabulary tree to finish the first-stage feature matching; and (4) finishing the second-stage feature matching by using a key image and combining the feature matching results of the two stages; and finally rejecting exterior points by adopting RANSAC (Random Sample Consensus), basic matrix and other technologies. By using the matching method, the robustness of the feature matching can be greatly improved and the adaptability of the feature matching can be effectively enhanced.

Description

technical field [0001] The invention belongs to the technical field of computer augmented reality, and specifically performs adaptive matching on an image SIFT feature set under the condition of a large amount of data, and improves the robustness of feature matching. Background technique [0002] The nearest neighbor (Nearest Neighbor) feature query technology is an important part of image SIFT feature matching, and has been widely used in motion restoration structure, object recognition, image retrieval, and scene understanding. [0003] As one of the most important spatial subdivision methods, the k-d tree is widely used in the nearest neighbor feature matching work, but as the feature dimension increases, since each branch needs to be traversed to accurately locate the matching feature, the matching efficiency of this method will be rapid decline. Arya et al. extended the method to find Approximate Nearest Neighbor features. By setting the approximate precision paramete...

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 Applications(China)
IPC IPC(8): G06K9/64
Inventor 范志强沈旭昆赵沁平
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap