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

Clonal selection-based method for detecting change of remote sensing image with optimal entropy threshold

A technology of remote sensing image and clone selection, applied in image analysis, image data processing, instrument and other directions, can solve the problem of large deviation of threshold value, and achieve the effect of reducing noise and low detection error.

Inactive Publication Date: 2012-06-20
XIDIAN UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (1) The influence of factors such as registration error and noise between images is relatively sensitive, and the problem of noise in the change detection results is more serious
[0006] (2) The method of modeling and calculating the optimal threshold value for the change class and non-change class in the difference image obtained by arithmetic operation is to calculate the probability density of the two classes under the assumption that the two classes meet a certain distribution, but in fact the difference image The two categories in the middle do not completely conform to a certain distribution, so the threshold calculated in this way has a large deviation

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
  • Clonal selection-based method for detecting change of remote sensing image with optimal entropy threshold
  • Clonal selection-based method for detecting change of remote sensing image with optimal entropy threshold
  • Clonal selection-based method for detecting change of remote sensing image with optimal entropy threshold

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] refer to figure 1 , the specific implementation steps of the present invention are as follows:

[0033] Step 1. Construct the difference image map DI of the two-temporal remote sensing images.

[0034] use I 1 and I 2 Represent the two-temporal remote sensing images respectively, firstly I 1 and I 2 Compared, then take the logarithm of its ratio to obtain the difference image map DI=log(I 1 / I 2 ).

[0035] Step 2, initialize the population and set parameters.

[0036] Since the grayscale range of the original grayscale image is between 0 and 255, the grayscale value has 2 8 Therefore, the 8-bit binary code is used to initialize the population, and the 8-bit binary code is randomly generated as the individual of the population, and the maximum number of iterations is set to 50, the current number of iterations g is 0, and the initial population size N is 10.

[0037] Step 3, calculate the affinity of the population, and sort the affinity in descending order.

...

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 discloses a clonal selection-based method for detecting change of a remote sensing image with an optimal entropy threshold. The method comprises the following implementation steps of: (1) constructing difference imagemaps of dual-time phase remote sensing images by logarithmic ratio operators; (2) initializing a population and setting parameters; (3) calculating affinities of the population by an optimal threshold algorithm, and descending the sort of the affinities; (4) performing clonal selection operation on each individual according to a clonal selection algorithm, generating a new population, and storing the individual with the maximal affinity in the population; (5) judging whether termination conditions are reached, retuning to the step (3) if the termination conditions are not reached, otherwise sorting the affinities of all the individuals in a storage result, and taking the individual corresponding to the maximum value of the affinities as an optimal threshold; (6) segmenting the threshold of the difference imagemaps by the optimal threshold to obtain an initial change detection result; and (7) processing an initial change detection result map by morphology to obtain a final change detection result. The clonal selection-based method has the advantages of stable and effective operation and fewer total detection errors.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to an image detection method, and can be used in technical fields such as image enhancement, pattern recognition, and target tracking. Background technique [0002] Change detection technology can be divided into multi-band multi-temporal remote sensing image change detection and single-band multi-temporal remote sensing image change detection according to the number of spectral bands for processing remote sensing data. Among them, the multi-band remote sensing data provides a rich source of information for change detection, and the method of data transformation is usually used to process the data of multiple bands, so that the change information can be concentrated on a few features. Image transformation techniques applied to multi-band and multi-temporal remote sensing image change detection include principal component analysis (PCA), canonical correlation analysis (MAD), spike...

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): G06T7/00G06N3/00
Inventor 公茂果焦李成张晔马晶晶马文萍石永安尚荣华王爽侯彪
Owner XIDIAN 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