Infrared and visible-light different-source image matching method based on context of line segments

A technology of heterogeneous images and matching methods, applied in image analysis, image data processing, instruments, etc., can solve problems such as no modality invariance, high false matching rate, and matching failure

Inactive Publication Date: 2016-06-15
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
View PDF1 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional feature descriptors (such as classic SIFT, SURF and other operators) are designed for homologous image matching, and usually use the gradient distribution attributes near feature points to construct descriptors, which do not have modal invariance. When used in infrared When matching with visible light images, the error matching rate is often high, and even the matching fails

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
  • Infrared and visible-light different-source image matching method based on context of line segments
  • Infrared and visible-light different-source image matching method based on context of line segments
  • Infrared and visible-light different-source image matching method based on context of line segments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] Example 1. Matching results

[0072] In order to prove the effectiveness of the algorithm of the present invention, the software and hardware environment of the simulation experiment example is CPUDual-Core2.5GHz, memory 2GB, WindowsXP+SP3, VisualStudio2013, and the image resolution used in the experiment example is 256×512. In the experimental example, the number of concentric circles is 2, and the number of uniform sampling points on the concentric circles is 8. When the radius interval of the concentric circles is small, the sampling points are relatively dense, resulting in excessive overlap between the local neighborhoods of the sampling points, and the repeatability of the feature values ​​of different dimensions of the feature descriptor is too high, which makes the distinguishing ability of the feature descriptor weak; When the radius of the concentric circle is large, the sampling points are relatively sparse, and some significant features may be missed, result...

Embodiment 2

[0073] Embodiment 2. Comparative results

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 relates to a method for matching infrared and visible light heterogeneous images based on the straight line segment context, which includes the following process: using the LSD algorithm to detect the straight line segment in the image, and selecting the key straight line segment according to the geometric constraint rules; through the improved image angle The point detection method detects corner points; by calculating the Manhattan distance of the line segment in the four-quadrant neighborhood of the feature point, the contribution of each straight line segment to the feature point is obtained. On this basis, a circular array is used to construct a feature description based on the context of the straight line segment sub; using bidirectional matching strategy and RANSAC algorithm to achieve infrared and visible light image matching. The algorithm of the present invention can obtain more correct matching point pairs, can adapt to the precise matching of infrared and visible light images with serious gray scale differences, and is superior to mainstream heterogeneous image matching algorithms in terms of robustness and time efficiency .

Description

technical field [0001] The invention relates to the technical field of infrared and visible light heterogeneous image matching, in particular to a line context-based infrared and visible light heterogeneous image matching method. Background technique [0002] The matching of infrared and visible light images is an important branch of heterogeneous image matching, and has important applications in the fields of image fusion, automatic target recognition, and change detection. The infrared sensor has the advantages of all-weather work and strong anti-interference ability, while the image acquired by the visible light sensor has the characteristics of high contrast, rich texture information, and clear image. In the field of image fusion, in order to obtain richer scene information, it is necessary to achieve information fusion on the basis of matching infrared and visible light images, enhance complementarity, and reduce uncertainty in scene analysis and understanding; in the f...

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): G06T7/00
Inventor 史泽林夏仁波刘云鹏向伟惠斌田政
Owner SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
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