A multispectral and panchromatic image fusion spatial quality evaluation method based on a regional convolutional network

A full-color image and spatial quality technology, applied in the field of information processing, can solve the problems of information loss and poor generalization ability, achieve the effect of strong representation ability and generalization ability, and avoid the loss of spatial information

Pending Publication Date: 2019-06-28
NORTHWESTERN POLYTECHNICAL UNIV
View PDF15 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the problem of poor generalization ability and information loss in the evaluation process of the traditional space quality evaluation method based on the fusion results of multi-spectral images and panchromatic images based on regions, and perform feature-level evaluation in units of regions on the fusion results space quality evaluation

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
  • A multispectral and panchromatic image fusion spatial quality evaluation method based on a regional convolutional network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0018] A spatial quality assessment method for multispectral image and panchromatic image fusion based on regional convolutional network, the steps are as follows:

[0019] Step 1 extracts the R, G, and B bands of the fused image as input, performs SLIC superpixel segmentation on it, and obtains the segmentation information of the segmentation map, that is, the information of each region. Includes bounding rectangle coordinates, dimensions, and region image markers for each region.

[0020] Step 2 Obtain the coordinates and dimensions of the circumscribed rectangle of the region image in the segmentation information through step 1, perform rectangular cropping on the fused image, and repeat the same operation on the panchromatic image.

[0021] Step 3. Dot multiplication operation on the image block of the fused image obtained in step 2 and the region image mark...

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 multispectral and panchromatic image fusion space quality evaluation method based on a regional convolutional network. The processing process of a fusion image and a panchromatic image in a traditional regional multispectral image and panchromatic image fusion space quality evaluation method is improved. A GoogLeNet network is directly used for extracting spatial features of region images in an original fusion image and a panchromatic image instead of carrying out gray level image conversion and discrete cosine transform on the fusion image. While the spatial information loss of the image is effectively avoided, the depth features with stronger representation capability and generalization capability are extracted, and the feature-level spatial quality evaluationis carried out on the fusion result. Finally a visual spatial quality distribution map representing the spatial quality of the local area of the fusion result is obtained.

Description

technical field [0001] The invention belongs to the technical field of information processing, and relates to a method for evaluating the quality of fusion results of remote sensing images, in particular to a spatial quality evaluation method for fusion of multispectral images and panchromatic images based on regional convolutional networks. Background technique [0002] The remote sensing image obtained by image fusion technology has a large amount of information, and has high resolution in both the spatial domain and the spectral domain, and is more and more widely used in the field of remote sensing. Quality evaluation of remote sensing image fusion plays an important role in these applications. It is not only a benchmark for measuring remote sensing image fusion methods, but also an important tool for improving remote sensing image fusion methods. [0003] The traditional method is to evaluate the spatial quality of the fusion results of multispectral and panchromatic im...

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): G06T7/00G06T7/11G06T5/50
Inventor 李映杨恺行张谷雨汪亦文
Owner NORTHWESTERN POLYTECHNICAL 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