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

Object-neural-network-oriented high-resolution remote-sensing image classifying method

An object-oriented, high-resolution technology, applied in the field of neural network classification, can solve the problems of ineffective use of remote sensing sensors and low classification accuracy, and achieve the effect of solving salt and pepper phenomenon, improving classification accuracy, and solving classification problems

Inactive Publication Date: 2013-01-02
HEILONGJIANG INST OF TECH
View PDF1 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problem that the traditional remote sensing image classification method has low classification accuracy and cannot effectively use the information of all bands of remote sensing sensors, the present invention proposes an object-oriented neural network classification method for high-resolution remote sensing images

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
  • Object-neural-network-oriented high-resolution remote-sensing image classifying method
  • Object-neural-network-oriented high-resolution remote-sensing image classifying method
  • Object-neural-network-oriented high-resolution remote-sensing image classifying method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0028] Specific embodiment one, combine and figure 1 Specifically illustrate the present embodiment, the high-resolution remote sensing image object-oriented neural network classification method described in the present embodiment, it comprises the following steps:

[0029] Step 1. The high-spatial-resolution sensor captures an image of the ground and sends the image to the computer;

[0030] Step 2, the computer uses the region growing algorithm to perform preliminary segmentation of the input image at the pixel level;

[0031] Step 3, performing multi-scale segmentation on the image initially segmented in step 2 according to the continuously set heterogeneity threshold, spectral characteristics and shape characteristics of the image to form segmented images of different scales;

[0032] Step 4. Establish a BP neural network based on the segmented images of different scales obtained in step 3, set training parameters, and establish training samples to classify multi-scale se...

specific Embodiment approach 2

[0052] Embodiment 2. The difference between this embodiment and the object-oriented neural network classification method for high-resolution remote sensing images described in Embodiment 1 is that the specific steps of the multi-scale segmentation described in Step 3 are:

[0053] When the calculated heterogeneity of adjacent image objects is less than or equal to the set threshold, merge adjacent image objects to generate images of different scales;

[0054] When the heterogeneity of the obtained adjacent image objects is greater than the set threshold, the adjacent image objects are not merged;

[0055] The heterogeneity f of two adjacent image objects:

[0056] f = ( w color Σ c w c ( n 1 ( ...

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 an object-neural-network-oriented high-resolution remote-sensing image classifying method, aiming at solving the problems that the conventional remote-sensing image classifying method is low in classification precision and cannot effectively utilize information of all wave bands of a remote sensor. The method comprises the following steps that: an image of the ground is shot by a high-spatial-resolution sensor and is transmitted to a computer; the computer carries out primary image element division on the input image by a region growing algorithm; the primarily-divided image is subjected to multi-size division according to continuously-set neterogeny degree thresholds and shape features and spectral signatures of the image, thus forming divided images with different sizes; and the obtained divided images with different sizes are used for establishing a BP (Back Propagation) neural network, setting training parameters and establishing training samples to classify the image which is subjected to the multi-size division, thus obtaining a high-resolution image. The method is applicable to the field of obtaining of images with high spatial resolutions.

Description

technical field [0001] The invention relates to a neural network classification method, in particular to an object-oriented neural network classification method for high-resolution remote sensing images. Background technique [0002] In the automatic identification and classification of remote sensing images, traditional classification methods are not suitable for images with high spatial resolution, because in the process of classification, a "salt and pepper phenomenon" will occur, which will reduce the accuracy of classification. For the automatic identification and classification of remote sensing images with high spatial resolution, an object-oriented classification method is mostly used at home and abroad. This method first performs multi-scale segmentation on the image, and then performs fuzzy classification or supervised classification on the basis of multi-scale segmentation. Object-oriented automatic recognition and classification, when there is a linear relationsh...

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): G06K9/62G06N3/02
Inventor 刘丹丹张玉娟王强刘江
Owner HEILONGJIANG INST OF TECH
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