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

Underground target detection and recognition system and method based on feature fusion

A technology of feature fusion and target detection, applied in radio wave measurement systems, electrical/magnetic exploration, geophysical measurements, etc., can solve the problems of dielectric loss dispersion, inaccuracy, and antenna characteristic loading mismatch, and achieve accurate recognition high degree of effect

Inactive Publication Date: 2015-12-09
LUDONG UNIVERSITY
View PDF2 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This inhomogeneity of the medium leads to a large difference in the propagation performance of electromagnetic waves
In actual work, it is often impossible to calibrate the detection environment quantitatively, so the prediction of GPR performance is usually empirical and far from accurate
[0005] (2) Dielectric loss and dispersion
Changes in the electromagnetic properties of the underground medium directly affect the propagation speed and amplitude attenuation of underground electromagnetic waves, which severely limits the maximum detection depth and target positioning accuracy of the GPR system
[0007] (4) Strong clutter background
From space to underground detection, strong ground jump interference and loading mismatch of antenna characteristics are caused by the existence of the ground
[0009] The above factors have caused difficulties in the realization of GPR system data processing and analysis
In particular, it is very difficult to determine the characteristic invariants of underground targets and to detect and identify targets

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
  • Underground target detection and recognition system and method based on feature fusion
  • Underground target detection and recognition system and method based on feature fusion
  • Underground target detection and recognition system and method based on feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0144] Embodiment: comparative analysis of measured data

[0145] For comparative analysis, four experiments were carried out:

[0146] (1) Used to test the recognition of objects of different shapes. The data used are the data obtained from the measurement of spherical bodies, tubular bodies, square bodies, etc. respectively. The experimental method is to preprocess the measured data first, perform parameter calculation and feature extraction, and perform target shape recognition.

[0147] (2) It is used to identify objects of different materials. The measurement data used are the data obtained from the measurement of metal (iron) pipe, plastic, cement and soil respectively. Firstly, the measurement data is preprocessed to obtain typical channel data and untargeted multi-channel soil data. Through Welch power spectrum, high-order spectrum estimation, and using wavelet neural network for training and recognition.

[0148] (3) WNN (Wavelet Neural Network), BP-NN (BackPropa...

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 underground target detection and recognition system and a method based on feature fusion. The method includes: detecting and acquiring echo signals of a ground penetrating radar; pre-processing the acquired echo signals; performing enhancement processing of the pre-processed echo signals; extracting time-domain feature and wavelet packet energy spectrum feature of the echo signals after enhancement processing, performing Welch power spectrum estimation and high-order spectral analysis of the echo signals after enhancement processing, and respectively obtaining a Welch power spectrum and a high-order spectrum; performing fusion of the time-domain feature, the wavelet packet energy spectrum feature, the Welch power spectrum, and the high-order spectrum of the echo signals; performing target recognition of the fused four kinds of signals via a wavelet neural network; and outputting a result after target recognition. According to the system and the method, comprehensive detection and recognition of the underground target can be realized based on multi-feature information fusion, the recognition of the underground target bodies in different shapes and of different materials can be effectively realized, and the recognition accuracy is high.

Description

technical field [0001] The invention relates to the technical field of earth exploration and modern information processing, in particular to an underground target detection and recognition system and method based on feature fusion. Background technique [0002] Ground Penetrating Radar (GPR) is a new non-destructive detection technology for shallow strata that uses the principle of electromagnetic wave reflection to detect underground targets and geological structures and distributions in the 1980s. It infers the structure of the medium and the position and shape of the target according to the properties of the propagation path, intensity, and waveform of the electromagnetic wave that change with the electromagnetic properties and geometric structure of the medium when the electromagnetic wave propagates in the medium. As an emerging geophysical detection method, it has many advantages such as high detection efficiency, high detection accuracy, wide frequency band, anti-inte...

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): G01V3/38
Inventor 邹海林柳婵娟周树森臧睦君殷波
Owner LUDONG UNIVERSITY
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