Unlock instant, AI-driven research and patent intelligence for your innovation.

A Feature Extraction Method of 1D Range Profile for True and False Targets

A feature extraction and distance image technology, applied in radio wave measurement systems, instruments, etc., can solve the problems of unrecognizable, target recognition rate decline, etc., achieve good recognition effect and improve classification performance

Active Publication Date: 2021-11-23
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, when the training data of each type of target is unbalanced, the distances between the feature regions obtained by the above subspace transformations show a distribution of different lengths, which will cause the recognition rate of some targets to drop significantly, and even fail to identify
Therefore, there is room for further improvement in the recognition performance of the above subspace method

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 Feature Extraction Method of 1D Range Profile for True and False Targets
  • A Feature Extraction Method of 1D Range Profile for True and False Targets
  • A Feature Extraction Method of 1D Range Profile for True and False Targets

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The actual application effect of the present invention is described below in conjunction with simulation data:

[0029] Four point targets are designed: true target, fragment, light bait, and heavy bait. The bandwidth of the radar emission pulse is 1000MHZ (the distance resolution is 0.15m, the radar radial sampling interval is 0.075m), the target is set as a uniform scattering point target, the scattering points of the real target are 7, and the scattering points of the other three targets are all 11 . In the one-dimensional range images with target attitude angles ranging from 0° to 70° at intervals of 1°, take the one-dimensional distances with target attitude angles of 0°, 2°, 4°, 6°,...,70° The one-dimensional range images of other attitude angles are used as test data, and there are 35 test samples for each type of target.

[0030] For four kinds of targets (true targets, fragments, light decoys and heavy decoys), within the range of attitude angles from 0° to 7...

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 belongs to the technical field of radar target recognition, in particular to a method for extracting one-dimensional distance image features of true and false targets. This method establishes an equidistant subspace between classes through training samples, and uses the equidistant subspace between classes for mapping, which can form an equidistant target aggregation area between classes in the feature space, thereby improving the performance of target recognition. For the data of four types of simulation targets Simulation experiments are carried out, and the experimental results verify the effectiveness of the method.

Description

technical field [0001] The invention belongs to the technical field of radar target recognition, in particular to a method for extracting one-dimensional distance image features of true and false targets. Background technique [0002] The feature subspace is composed of the principal components of the covariance matrix of the training one-dimensional range image data, which can well represent the principal energy of the target data, but does not have the optimal classification performance. The discriminant vector subspace method can increase the difference between heterogeneous target features and reduce the difference between similar target features, which has a certain improvement in classification performance compared with feature subspace method. These subspaces achieve good recognition results in radar target one-dimensional range image recognition. [0003] However, when the training data of each type of target is unbalanced, the distances between the feature regions ...

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 Patents(China)
IPC IPC(8): G01S7/41
CPCG01S7/41
Inventor 周代英冯健
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA