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

Fuzzy membership one-dimensional range profile multi-feature fusion method

A technology of multi-feature fusion and fuzzy membership, applied in radio wave measurement systems, instruments, etc., can solve the problems of recognition performance degradation and achieve the effect of improving classification performance and target recognition performance

Active Publication Date: 2019-07-12
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the differences in physical dimensions of different features, the fusion feature vector formed by concatenated fusion must be normalized before recognition, and this normalization process will lead to a decrease in the performance of recognition

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
  • Fuzzy membership one-dimensional range profile multi-feature fusion method
  • Fuzzy membership one-dimensional range profile multi-feature fusion method
  • Fuzzy membership one-dimensional range profile multi-feature fusion method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] In order to verify the effectiveness of the proposed method, the following simulation experiments are carried out.

[0029] Design four point targets: true target, fragment, light bait and heavy bait. The bandwidth of the radar emission pulse is 1000MHZ (distance resolution is 0.15m, radar radial sampling interval is 0.075m), the target is set as a uniform scattering point target, the true target scattering point is 7, and the scattering points of the other three targets are all 11. . In the one-dimensional range image with the target attitude angle of 0°~70° every 1°, take the one-dimensional distance of the target attitude angle of 0°, 2°, 4°, 6°,..., 70° For training, the one-dimensional distance profile of the remaining attitude angles is used as the test data, and there are 35 test samples for each type of target.

[0030] For four types of targets (real targets, fragments, light decoys and heavy decoys), within the range of attitude angles of 0°~70°, extract the leng...

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, and particularly relates to a fuzzy membership one-dimensional range profile multi-feature fusion method. The method comprisesthe following steps: firstly, extracting multiple types of features such as length, scattering and mode conversion from a one-dimensional range profile; the feature dimension is expanded and converted into the features with the same size; then the fuzzy membership is used for carrying out weighted fusion on the multiple types of features to form a comprehensive feature, the classification performance of the multiple types of features can be fully utilized, accordingly, the target recognition performance can be improved, and the problem that the classification performance is affected due to different physical quantities in conventional feature fusion can be solved.

Description

Technical field [0001] The invention belongs to the technical field of radar target recognition, and specifically relates to a multi-feature fusion method of fuzzy membership degree one-dimensional range profile. Background technique [0002] In radar target recognition, multiple types of features such as length, scattering and mode can be extracted from one-dimensional range profiles, and each type of feature reflects the difference in a certain aspect of different targets. For example, the length feature reflects the difference in target size. The scattering feature information contains the difference information of the target in terms of structural shape, and the feature subspace projection feature reflects the difference of the target data distribution in the direction of maximum energy. Therefore, using a single feature can only distinguish multiple types of targets that differ in one feature. In radar target recognition, especially in the recognition of true and false targ...

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): G01S7/41
CPCG01S7/41
Inventor 周代英沈晓峰冯健张瑛
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA