Human body-behind-wall multi-state target detection method based on fuzzy pattern recognition and genetic algorithm

A technology of fuzzy pattern recognition and genetic algorithm, applied in the field of fuzzy pattern recognition and genetic algorithm detection technology, can solve the problems of not much research, unsuitable layout, high cost and unsuitable portability, etc., to achieve the effect of accurate target recognition algorithm

Inactive Publication Date: 2017-07-21
TIANJIN NORMAL UNIVERSITY
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Although there are many methods of target detection based on UWB radar in the current research, there are not many researches on the multi-state detection method of human body behind the wall based on UWB radar. In the civil field, the detection of indoor, outdoor and underground personnel is all used Detection methods, in the military field, wireless sensor networks usually have a large number of sensor nodes, and each sensor has a fixed position, high cost, not suitable for carrying, and not suitable for deployment in complex combat environments

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
  • Human body-behind-wall multi-state target detection method based on fuzzy pattern recognition and genetic algorithm
  • Human body-behind-wall multi-state target detection method based on fuzzy pattern recognition and genetic algorithm
  • Human body-behind-wall multi-state target detection method based on fuzzy pattern recognition and genetic algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] The basic idea of ​​human body target recognition behind the wall is to process the received signal of UWB radar equipment, and extract the characteristic parameters related to the target information from the received signal. The present invention mainly extracts the characteristic parameters of the received signal, and extracts six characteristics for each state. Parameters, including Kurtosis, Skweness, the maximum amplitude of the received signal, the variance and covariance of the received signal. The Gaussian function is selected as the sub-membership function, and each feature parameter of each scene corresponds to a sub-membership function. There are 36 sub-membership functions in 6 scenes, and the mean and variance of the sub-membership functions are obtained by genetic algorithm. The membership function set of fuzzy pattern recognition is constructed through the sub-membership function, and the state of the human target behind the wall is classified and recogniz...

Embodiment 2

[0053] We selected 6 states behind the wall for experiments, namely the state of no one behind the wall, the state of 1 person behind the wall breathing slowly, the state of 1 person waving his arms behind the wall, the state of 2 people behind the wall breathing slowly, and the state of 2 people walking back and forth behind the wall , the 3 people behind the wall breathe slowly. We choose 500 sets of pulse data for each state, and we choose 1152 data points for each set of pulse data. from figure 1 You can see the time-domain waveform diagram of each state, and the difference between various states can be seen weakly from the amplitude of the fluctuation. Therefore, the characteristic parameters are extracted for each state, and the target is identified through the characteristic parameters.

Embodiment 3

[0055] Extract the characteristic parameters of the received signal in each state, which are kurtosis, skewness, maximum amplitude of the received signal, energy, variance and covariance of the received signal. The sub-membership function is constructed through the characteristic parameters, and then the membership function set is formed. The Gaussian function is used as a sub-membership function, and its mean and variance are obtained by genetic algorithm. figure 2 It represents the mean value and variance corresponding to the 6 characteristic parameters of the 6 states behind the wall. Through the target prediction function and the principle of maximum membership degree of fuzzy pattern recognition, the test data is brought into the target prediction function to classify and judge the data category. . from image 3 Among them, the recognition effect of various states behind the wall can be clearly seen through the ROC curve.

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 human body-behind-wall multi-state target detection method based on fuzzy pattern recognition and a genetic algorithm. The human body-behind-wall multi-state target detection method comprises processing a received signal of a P410 radar, and extracting a characteristic parameter of the received signal; and forming a membership function set by means of the extracted characteristic parameter and multiple states behind a wall. A gaussian function is selected as a sub-membership function, the mean value and variance in the sub-membership function are optimized by means of the genetic algorithm, and the membership function set is constructed; a human body-behind-wall target prediction function is established in dependence on a fuzzy pattern recognition theory, and through calculation, which kind of state the detected data belongs to can be obviously recognized on the basis of a maximum membership degree principle. The human body-behind-wall multi-state target detection method based on the fuzzy pattern recognition and the genetic algorithm is mainly applied to the disaster rescue field and the anti-terrorism criminal investigation field in order to guarantee that a target under which a living body is buried is detected and rescued and the personal safety of a hostage is guaranteed when the hostage is seized in the anti-terrorism action.

Description

technical field [0001] The present invention relates to a fuzzy pattern recognition and genetic algorithm detection technology. The method is simple, practical, vivid and intuitive, excavates a new field of target recognition, overcomes the limitations of the previous UWB radar detection field, and detects various states behind the wall. Disadvantages of unclear classification. Background technique [0002] The emerging ultra-wideband radio technology (UWB-Radio Technology, UWB-RT) is a major advancement in the field of wireless communication. Its key advantages are frequency band sharing, large channel capacity, low interception and detection, anti-interference, and multi-path channel. Good performance, strong penetration, etc. Ultra-wideband radar technology is a key technology for ultra-wideband application in the field of target recognition. Its main features are high resolution, strong anti-interference ability, and strong penetration. Therefore, ultra-wideband radar ...

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): G01S13/88G01S7/41
CPCG01S7/41G01S13/888
Inventor 王为王丹
Owner TIANJIN NORMAL UNIVERSITY
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