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
CN107464252AInactive Publication Date: 2017-12-12NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
6 Cites 21 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Publication Date
2017-12-12
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

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.
Need to check novelty before this filing date? Find Prior Art

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