SAR image registration method based on deep neural network

A deep neural network and image registration technology, applied in the field of image processing, can solve problems such as unreliable methods, large amount of calculation, and affect registration accuracy, etc., to achieve reduced calculation amount and complexity, high registration accuracy, and robustness strong effect

Active Publication Date: 2018-11-16
XIDIAN UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that the artificially designed Harris, SIFT, and SURF methods to extract features have a large amount of calculation, and the Harris method is unstable when extracting feature points. In SAR images, SIFT and SURF methods are easy to mistake noise points as Feature points, which affect the accuracy of registration
The shortcomings of this method are: First, the existing artificially designed line detection methods in SAR images are not effective, which affects the detection of characteristic lines, and the prior information is insufficient, which reduces the accuracy of image registration
Second, the method of registration based only on features is not reliable

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
  • SAR image registration method based on deep neural network
  • SAR image registration method based on deep neural network
  • SAR image registration method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described below in conjunction with the accompanying drawings.

[0042] refer to figure 1 , the concrete steps that the present invention realizes are as follows:

[0043] Step 1, get training samples.

[0044] Step 1, read in the registered SAR image;

[0045] Step 2: Carry out sliding window segmentation on the registered SAR image, the step size of the sliding window is 5, and obtain 7500 pairs of image blocks with a size of 28×28 with matching labels, among which 5000 pairs of image blocks will be randomly selected As training samples, the remaining 2500 pairs of image patches are used as testing samples.

[0046] Step 2, design and train a deep neural network.

[0047] Step 1, design a deep neural network with an input layer, two hidden layers and an output layer, the number of nodes in each layer is 1568, 784, 100, 1;

[0048] Step 2, input the training samples into the deep neural network;

[0049]The third step is to u...

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 provides a SAR image registration method based on deep neural networks, and the method comprises the realization steps: (1) a training sample is acquired; (2) the deep neural networks are designed and trained; (3) matching relations are predicted; (4) wrong matching points are removed; (5) a geometric transformation parameter is calculated; and (6) the image is registrated. According to the invention, the SAR image registration method based on deep neural networks is adopted, the artificial design feature extraction operator defects including high complexity, large amount of computation, poor robustness in a process and the like in prior art can be effectively overcome, the amount of computation can be effectively reduced, the deep neural networks can extract substantive characteristics of the image, the robustness is better than before, and the precision of the registration is higher than before.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a synthetic aperture radar (synthetic aperture radar, SAR) image registration method based on a deep neural network. The invention can be applied to the fields of computer vision, remote sensing image processing, pattern recognition and the like for image fusion, change detection, target detection and recognition, and the like. Background technique [0002] Synthetic aperture radar is a high-resolution active microwave remote sensing imaging radar, which has the advantages of all-weather, all-weather, high resolution, and side-view imaging. It can be used in many fields such as military, agriculture, navigation, and geographical surveillance. . SAR image registration can be used for change detection, object detection and recognition. [0003] The existing image registration methods are mainly divided into grayscale-based registration methods and feature-bas...

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): G06T7/33
CPCG06T2207/10044
Inventor 权豆王爽焦李成宁梦丹郭岩河侯彪马晶晶
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