Space object image ultra-high resolution reconstruction method

A technology of super-resolution reconstruction and space object, which is applied in the field of space object image super-resolution reconstruction, can solve the problems of local edge and texture distortion, without considering the influence of local mode image quality, etc., achieve accurate representation, improve reconstruction effect, The effect of enhancing expressive ability

Active Publication Date: 2017-07-04
BEIHANG UNIV
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional sparse representation super-resolution reconstruction algorithm only considers minimizing the pixel-level reconstruction error of the image in the process of dictionary construction, but does not consider the influence of local modes on the quality of the reconstructed image, so the reconstruction of the spatial target image will appear Local edge and texture distortion

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
  • Space object image ultra-high resolution reconstruction method
  • Space object image ultra-high resolution reconstruction method
  • Space object image ultra-high resolution reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to make the purpose, content, and advantages of the present invention clearer, the specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0039] Such as image 3 As shown, the spatial object image super-resolution reconstruction method of the embodiment of the present invention includes the following steps:

[0040] S1. Training sample extraction and subspace low-rank dictionary construction

[0041] Since dictionary construction depends on training samples, it is necessary to prepare high-resolution and corresponding low-resolution images as the training image set first, and randomly select image block features from the training image set to generate a training sample set. After completing the construction of the training sample set, the algorithm divides the training sample set into subspaces based on the Euclidean distance between the features of the...

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 space object image ultra-high resolution reconstruction method and belongs to the technical field of digital image processing. According to the invention, the method improves the capability of a dictionary in representing a local sample structure by training an independent dictionary for each word space. The method, by introducing the low-rank matrix restoring method to the construction of an ultra-high resolution reconstruction sub-space dictionary, improves the capability and precision of a sub-space dictionary in representing a local sample mode of the rules of a space object image, and further improves the effects of ultra-high resolution reconstruction of the space object image. According to the invention, the dictionary obtained by training with the method herein can represent a low-resolution sample in a more accurate manner, and can reconstruct an ultra-high resolution sample in a way much similar to the local sample mode of an ultra-high resolution space object observation image.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a super-resolution reconstruction method of a space object image. Background technique [0002] With the continuous development of space target observation technology, people need to obtain more detailed information from space target images, which can help to interpret and identify space targets in images. However, the imaging conditions of space objects are complex. In the process of image imaging, affected by factors such as sampling, blur and noise, the image quality is degraded and the image details are seriously lost, which has a great impact on the extraction of image detail information and image interpretation and recognition. Image super-resolution reconstruction is a signal processing technique that recovers high-resolution image detail information from low-resolution images. This technology has shown great application prospects in frontier fields such ...

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): G06T3/40
CPCG06T3/4053
Inventor 姜志国张浩鹏张鑫谢凤英罗晓燕尹继豪史振威赵丹培
Owner BEIHANG 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