A multi-agent cooperative target recognition method based on msbn

A target recognition and multi-intelligence technology, applied in the field of target recognition, can solve problems such as long observation time and difficult interpretation, and achieve the effect of enhancing real-time performance, improving recognition ability, speed and accuracy

Active Publication Date: 2011-12-07
NORTHWESTERN POLYTECHNICAL UNIV
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the problems of difficult explanation or long observation time in the prior art, the present invention provides a multi-agent cooperative target recognition method based on MSBN reasoning

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 multi-agent cooperative target recognition method based on msbn
  • A multi-agent cooperative target recognition method based on msbn
  • A multi-agent cooperative target recognition method based on msbn

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Taking the environment recognition of the agricultural vehicle automatic navigation system as an example, the specific implementation steps of the present invention based on the MSBN multi-agent cooperative reasoning target recognition method are described below.

[0034] MSBN can be represented by a triplet M=(V, G, P). Where: V=∪ i V i , where V i is the variable set in the subfield, i is the number of subfields, and the present invention regards each target feature as a variable set; P=∏ i P i is the joint probability distribution, where P i is G i The product of the potentials of the relevant nodes in . Different from ordinary BN, G=∪ i G i is a multi-connected directed acyclic graph with a hypertree structure, each subgraph G i Node with V i express. In G, x is a node, and π(x) is all parents of x. For each cardinality of x, there is only one G containing {x}∪π(x) i middle assignment P(x|π(x)); other G j A potential containing x assigns a uniform dist...

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 multi-agent cooperative target identification method based on an MSBN (Multiple Sectioned Bayesian Network), which regards various agents of a multi-agent system as a BN (Bayesian Network) subnet of a multiple-section Bayesian network and used for solving the problem of accurate target identification. By taking target identification type nodes as an overlapping subdomain, the BN subnet is constructed to be the MSBN, and the multi-agent system can be cooperatively solved in terms of BN model inference. In a multi-agent cooperative target identification algorithm mainly, a reliability communication algorithm is mainly adopted to complete the reliability update of the whole MSBN, therefore, the target type hidden node probability query support of a target to be identified in the corresponding MSBN is completed, and the target identification is achieved. According to the invention, while the system identification ability is improved, the timeliness of the system is strengthened, and the target identification speed and accuracy are greatly improved.

Description

technical field [0001] The invention relates to a target recognition method, in particular to a multi-agent cooperative target recognition method based on multiple sectioned Bayesian network (Multiple sectioned Bayesian network, MSBN) cooperative reasoning. Background technique [0002] For target recognition, given some evidence, it is necessary to infer the most likely probability distribution of hidden nodes (also known as hidden variables) such as target types in the corresponding model, so that it is consistent with the mastered prior knowledge, principles, etc. Organic combination, through the fusion of multi-source information, to achieve the purpose of target recognition. [0003] Each target to be recognized has its distinctive characteristic appearance. With the development of electronic and information systems, data collection has become relatively easy, so a large amount of data can be collected in a relatively short period of time. However, utilizing signals f...

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
IPC IPC(8): G06K9/62
Inventor 高晓光郭文强陈军
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