Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A region-based multi-feature fusion high-resolution remote sensing image segmentation method

A multi-feature fusion, remote sensing image technology, applied in the field of image processing, can solve the problems of insufficient use of image features, poor adaptability, and low algorithm efficiency.

Active Publication Date: 2017-09-01
CHANGAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In view of the defects or deficiencies in the above-mentioned prior art, the purpose of the present invention is to provide a region-based multi-feature fusion high-resolution remote sensing image segmentation method to solve the problems of insufficient utilization of image features and relatively low algorithm efficiency in the prior art. Problems and defects of low and poor adaptability

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 region-based multi-feature fusion high-resolution remote sensing image segmentation method
  • A region-based multi-feature fusion high-resolution remote sensing image segmentation method
  • A region-based multi-feature fusion high-resolution remote sensing image segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail in conjunction with the accompanying drawings and embodiments. A region-based multi-feature fusion high-resolution remote sensing image segmentation method of the present invention specifically includes the following steps :

[0073] Step 1: Perform principal component analysis on the high-resolution remote sensing image to obtain the base image. After performing NSCT transformation on the base image, extract the texture feature vector of each point in the base image, and then perform fuzzy C-mean aggregation on the texture feature vectors of all points. class, get the clustering set;

[0074] Step 1.1: Perform principal component analysis on the high-resolution image, and select the first principal component as the base image I for NSCT transformation;

[0075] Step 1.2: Set the number of layers k (k is 2 to 5) for...

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 present invention disclosed a regional -based multiced -based fusion high -resolution remote sensing image segmentation method. First of all, the initial high -resolution image was initially divided, and then the texture characteristic distance and spectral characteristics of any neighborhood in the initial segmentation area were calculated.Followed by the shape features, finally the regional merger based on RAG and NNG; the present invention uses the characteristics of spectrals, textures, and shapes to build a combination rules. Compared with the rules of a certain characteristic construction, it is more in line with the semantic description of the object, so that it makes the semantic description of the object, so that it makes the semantic description of the object, so that soThe segmentation accuracy is higher; the present invention combined with the two data structures of RAG and NNG to maintain the adjacent relationship of the area, so that this algorithm can obtain higher execution efficiency, and the segmentation results can be obtained more quickly compared to the existing technology.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a region-based multi-feature fusion high-resolution remote sensing image segmentation method. Background technique [0002] While high spatial resolution remote sensing images bring opportunities for the development of remote sensing technology, they also bring new challenges to the processing of remote sensing data. The accuracy of the method is reduced. Based on this, object-based image analysis (OBIA) has become a new choice for high-resolution remote sensing image processing, and the basis of OBIA is image segmentation. Homogeneous regions, namely objects, are obtained through image segmentation technology. , and then analyze the object as a primitive, which can make full use of the characteristics of the object such as spectrum, texture, shape, etc., which has more advantages than traditional pixel-level algorithms in theory and practice. At present, re...

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): G06T7/11G06K9/62G06T7/49
CPCG06T2207/10032G06F18/22G06F18/253
Inventor 韩玲刘大伟宁晓红刘志恒
Owner CHANGAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com