Heterogeneous image block matching method based on image conversion

An image conversion and heterogeneous image technology, applied in the field of image processing, can solve problems such as poor network matching accuracy and generalization, inability to extract targeted features from different images, and loss of spatial information of features, so as to overcome the inconsistency of feature calculation distance Accurate, overcome low matching accuracy and poor robustness, improve accuracy and robustness

Active Publication Date: 2018-09-21
XIDIAN UNIV
View PDF11 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a heterogeneous image block matching method based on image conversion, which solves the problem that existing matching methods cannot perform targeted feature extraction on

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
  • Heterogeneous image block matching method based on image conversion
  • Heterogeneous image block matching method based on image conversion
  • Heterogeneous image block matching method based on image conversion

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0046] The present invention will be further described below in conjunction with the drawings.

[0047] Such as figure 1 As shown, the heterogeneous image block matching method based on image conversion provided by the present invention includes the following steps:

[0048] Step 1. Obtain training samples and test samples:

[0049] (1a) Read in the registered heterogeneous image, which includes SAR image and optical image;

[0050] (1b) The Harris method is used to detect the corner points of the optical image, and the coordinates of the detected corner point A are used as the center point, and the fixed value w is used as the side length to cut the optical image to obtain the optical image block. In the example, the value of w is 32;

[0051] (1c) Take the feature point B corresponding to the corner point coordinates on the SAR image. At the same time, randomly select a feature point C on the SAR image, and then use the coordinates of feature point B and feature point C on the SAR i...

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

An image conversion-based heterogeneous image block matching method provided by the invention has the following steps: acquiring training samples and test samples, constructing an image conversion network, training the image conversion network, constructing a feature extraction and matching network, training the feature extraction and matching network, predicting a matching result. The invention overcomes the problem that the feature difference of the heterogeneous image extraction is large and inaccurate in the prior art, effectively reduces the matching difficulty, and improves the accuracyand robustness of the heterogeneous image block matching.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a heterogeneous image block matching method based on image conversion in the image matching method. Background technique [0002] Image registration technology has been proven to be applicable to many practical applications, and its related fields include remote sensing image analysis, image fusion, medical image processing, 3D reconstruction, pattern recognition, etc. As a key technology in the process of image registration based on deep neural network, image patch matching method has very important research significance and value. [0003] The widely used image block matching methods are mainly divided into two types, one is a method based on traditional manual feature extraction, and the other is a method based on neural network feature extraction. Among them, the method based on manual feature extraction is to extract the local salient features of the image by...

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): G06T7/33G06T3/00
CPCG06T3/0068G06T7/33G06T2207/20164G06T2207/10044G06T2207/10052G06T2207/20021G06T2207/20084G06T2207/20081
Inventor 王爽焦李成王若静权豆方帅梁雪峰郭雨薇刘飞航
Owner XIDIAN 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