An Image Matching Method Combining Point Features and Line Features

A matching method and line feature technology, which is applied in the field of image matching combining point features and line features, can solve the problems of time-consuming calculation, insufficient description ability, and many repeated patterns.

Inactive Publication Date: 2017-09-29
HUAZHONG UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Binary (multi-valued) templates are applied to the matching of complex scenes, which can partially eliminate the impact of adapting to grayscale changes in a statistical sense, but there will be more repetitive patterns and insufficient description capabilities.
Region-based matching recognition has a strong prior in the selection of regions, and it takes a long time to calculate when the template is large.

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
  • An Image Matching Method Combining Point Features and Line Features
  • An Image Matching Method Combining Point Features and Line Features
  • An Image Matching Method Combining Point Features and Line Features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.

[0057] Point features use local grayscale information, which is relatively stable, but due to the limitation of local window size, repeated patterns are prone to appear. Line features are more global and have a strong ability to distinguish structures, but edge extraction may be unstable in complex scenes. First use stable point features to first select the corner points to obtain candidate poin...

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 an image matching algorithm combining point features and line feature descriptors, including: (1) extracting corner points from template images and real-time images at multiple scales; (2) obtaining corner points from real-time images and template images The surrounding edge set; (3) the final selected real-time graph obtained in calculation step (1) and the class ORB point feature descriptor of the corner point of the template graph; (4) using the least truncated square Hausdorff distance to describe the obtained in step (2) The matching similarity of the edge set of the real-time graph and the template graph; (5) the matching similarity of the real-time graph obtained in step (3) and the ORB point feature descriptor of the corner point of the template graph; (6) synthesis of matching results. The method of the present invention first uses stable point features to perform primary selection on corner points to obtain candidate point sets to ensure that the correct positions are included, and then uses relatively global line features to screen candidate point sets, which can reduce repetitive patterns and improve accuracy .

Description

technical field [0001] The invention belongs to the technical fields of image matching, computer vision and digital image processing, and in particular relates to an image matching method combining point features and line features. Background technique [0002] With the rapid development of science and technology, especially computer technology, scene matching and recognition technology has become an extremely important and basic technology in the field of information processing, especially in the fields of aerospace, UAV navigation and missile terminal guidance. [0003] Scene matching and recognition is the process of matching and recognizing the real-time image taken by the aircraft on-site with the pre-prepared template image. The position of the aircraft is determined through image recognition, so that the heading deviation can be corrected. The currently used template images are mainly derived from satellite or aerial images, and the real-time images are the lower ima...

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): G06T7/33G06T7/13G06T7/155
Inventor 王岳环王康裕吴明强张天序范蓉
Owner HUAZHONG UNIV OF SCI & TECH
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