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

Multi-agent and ant colony algorithm-based object-oriented remote sensing classification method

An ant colony algorithm, object-oriented technology, applied in computing, computer components, character and pattern recognition, etc., to achieve the effect of improving accuracy

Inactive Publication Date: 2016-07-06
WUHAN UNIV OF TECH
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because the ant colony algorithm needs to set many parameters, its results have a certain degree of randomness and tendency, and can only reflect the impact of a certain type of specific object on land use change.

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
  • Multi-agent and ant colony algorithm-based object-oriented remote sensing classification method
  • Multi-agent and ant colony algorithm-based object-oriented remote sensing classification method
  • Multi-agent and ant colony algorithm-based object-oriented remote sensing classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described below in conjunction with specific examples and accompanying drawings.

[0028] The invention provides an object-oriented remote sensing classification method based on multi-agent and ant colony algorithm, such as figure 1 As shown, it includes the following steps:

[0029] S1. Construction of sample data sets: collect remote sensing image data of at least two phases of the study area, and conduct data vectorization based on the remote sensing image data, produce urban land use classification data, and construct land use change sample data sets.

[0030] S2. Initialize the main agent and the sub-agent, and the main agent releases the task of mining land use change transformation rules.

[0031] S3. Several sub-agents choose whether to accept the task of the main agent according to their own capabilities, and return corresponding messages to the main agent. Among them, the main consideration of its own ability is whether ...

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 provides a multi-agent and ant colony algorithm-based object-oriented remote sensing classification method. The method comprises the steps that a sample data set is constructed; a main agent releases a task of mining land use conversion rules; a plurality of sub-agents receive the task of the main agent to become task type agents, and complete the mining of the land use conversion rules by adopting an ant colony algorithm by utilizing the land use conversion sample data set to obtain land conversion prediction types; and the main agent receives a completion message of each task type agent, performs multi-agent based negotiation and finally selects one prediction type as a final prediction type. According to the method, the multiple agents and the ant colony algorithm are combined; the randomness of a plurality of single ant colonies is subjected to weighted combination based on a method for continuously adjusting sample weights according to a sample set and a preset rule set; and a multi-agent negotiating and decision-making process is quantitatively expressed, so that the precision of final land conversion prediction is improved.

Description

technical field [0001] The invention relates to the field of remote sensing image classification, in particular to an object-oriented remote sensing classification method based on multi-agent and ant colony algorithm. Background technique [0002] In recent years, under the development trend of smart cities, the public has increasingly urgent requirements for the scientific and efficient allocation of land resources. Using spatial data mining technology to mine land resource data information. As a classic data mining algorithm, ant colony algorithm can effectively mine the rules of urban land use change based on the idea of ​​"local learning, overall integration". However, due to the need to set many parameters, the results of ant colony algorithm have certain randomness and tendency, and can only reflect the impact of a certain type of specific object on land use change. Contents of the invention [0003] The technical problem to be solved by the present invention is to ...

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): G06F17/30G06K9/62
CPCG06F16/2465G06F18/24
Inventor 崔巍郑振东周琪
Owner WUHAN UNIV 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