Visible-light and infrared heterologous image recognition method based on mixed features

A heterogeneous image and recognition method technology, applied in the field of computer vision, can solve the problems of complex heterogeneous image matching algorithm implementation, algorithm efficiency and matching accuracy need to be improved

Inactive Publication Date: 2017-12-12
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF6 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In general, the implementation of the above-mentioned heterogeneous image matching algorithm is relatively complicated, and the algorithm efficiency and matching accuracy still need to be improved.

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
  • Visible-light and infrared heterologous image recognition method based on mixed features
  • Visible-light and infrared heterologous image recognition method based on mixed features
  • Visible-light and infrared heterologous image recognition method based on mixed features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The technical solutions and beneficial effects of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0055] Such as figure 1 As shown, the present invention provides a visible light and infrared heterogeneous image recognition method based on mixed features, using the canny operator based on the improved maximum inter-class variance method and the multi-scale FAST feature point detection method, combining edge features and point features, Improving the RANSAC fine matching on the basis of the nearest rough matching, the method specifically includes the following steps:

[0056] Step 1: Use the adaptive canny operator based on the improved maximum inter-class variance method to extract edge information, and obtain the edge images V' and I' of the visible light image V and infrared image I;

[0057] Such as figure 2 As shown, the specific implementation form of the adaptive canny operator based on the improved maxim...

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 visible-light and infrared heterologous image recognition method based on mixed features. The method comprises the following steps: utilizing a self-adaptive canny operator, which is based on an improved Otsu method, to extract edge information, and acquiring edge images of a visible-light image and an infrared image; carrying out multi-scale FAST feature detection on the edge images of the visible-light image and the infrared image, and obtaining main directions of feature points according to a gray centroid method; respectively carrying out ORB feature description on feature point point sets, adopting Hamming distances to measure similarity between the feature points according to a nearest secondary-near principle to carry out rough matching to respectively obtain rough-matching feature point point sets of the edge images; and utilizing an improved RANSAC algorithm to eliminate mismatch point pairs therein, and showing a result in the visible-light image and the infrared image. According to the method, matching of the visible-light image to the infrared image can be effectively realized, and the algorithm efficiency and the matching accuracy can be improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision, in particular to a recognition method for visible light and infrared heterogeneous images based on mixed features. Background technique [0002] Image matching technology was first proposed by the United States. Since the 1970s, the United States has been engaged in the research of aircraft auxiliary navigation systems, guidance and search of weapon projection systems, and other applications. At present, the application of this technology has gradually expanded from the initial military application to the fields of computer vision, medical diagnosis, target recognition, target positioning and tracking in heterogeneous images, etc. Image matching technology is divided into homologous image matching and heterologous image matching, and the classification is based on whether the image is obtained by the same imaging equipment. The gray information gap between heterogeneous images is large, ...

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): G06T7/13G06T7/136G06T7/33G06K9/46
CPCG06T7/13G06T7/136G06T7/33G06T2207/10004G06T2207/10048G06V10/462G06V10/44
Inventor 陈艳曾庆化王云舒刘建业张月圆孙克诚戴宇庭孙永荣赖际舟熊智
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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