Radar high-resolution range profile open set target recognition method based on deep intra-class splitting
A high-resolution range image and radar technology, applied in the radar field, can solve problems such as poor closed-set recognition accuracy, unstable training, and unsatisfactory target sample generation effects, and achieve the effect of improving recognition accuracy and open-set recognition performance
Active Publication Date: 2021-06-04
XIDIAN UNIV
View PDF4 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to the problem of unstable training in the method of generative confrontation network, the generation effect of target samples is not ideal. In addition, the pseudo samples generated by generative confrontation network are indistinguishable from most of the training data, resulting in poor closed-set recognition accuracy. question
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0026] The embodiments and technical effects of the present invention will be further described below in conjunction with the accompanying drawings.
[0027] Refer to attached figure 1 , the implementation steps of the present invention are as follows:
[0028] Step 1. Obtain the radar two-dimensional high-resolution range image spectrogram data, and set label values for each target category in the radar target database.
[0029] 1.1) Extract the amplitude information of the radar echo along the range dimension on the radar line of sight as the radar high-resolution range image data;
[0030] 1.2) Perform two-norm normalization and center-of-gravity alignment processing on the radar high-resolution range image data to overcome the amplitude sensitivity and azimuth sensitivity of the radar high-resolution range image;
[0031] 1.3) Calculate the average value of the radar high-resolution range image data after the center of gravity alignment, and then subtract the mean valu...
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
Login to View More Abstract
The invention discloses a radar high-resolution range profile open set target recognition method based on deep intra-class splitting, which mainly solves the problems of low open set recognition performance and poor closed set recognition precision in the prior art. The method in the scheme comprises steps of acquiring radar two-dimensional high-resolution range profile spectrogram data, setting label values for all target categories in the radar target database, and constructing a training sample set and a test sample set, constructing an intra-class splitting model, and training the intra-class splitting model, inputting the training sample set into a trained intra-class splitting model for splitting to obtain an atypical sample subset and a typical sample subset, constructing an open set recognition model, and training the open set recognition model by using the atypical sample subset and the typical sample subset, and inputting a test sample into the trained open set recognition model to complete the open set recognition of the radar high-resolution range profile. According to the method, the open set recognition performance and the closed set recognition precision are improved, and targets in the database can be classified while targets outside the radar database are rejected.
Description
technical field [0001] The invention belongs to the technical field of radar, and in particular relates to a radar high-resolution range image open-set target recognition method, which can be used to classify targets in the database while rejecting targets outside the radar database. Background technique [0002] The high-resolution range profile HRRP represents the one-dimensional distribution of the target scattering center along the radar line of sight, and contains structural information such as the radial size of the target and the distribution of scattering points, which are very valuable for target recognition and classification. HRRP has the advantages of clean background, no clutter interference and small storage capacity, and has gradually become a research hotspot in the field of radar automatic target recognition RATR. Pattern recognition is usually divided into two categories: one is closed set recognition, that is, the target to be recognized needs to be assign...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G01S7/41
CPCG01S7/417G01S7/41Y02A90/10
Inventor 王鹏辉刘宏伟王同晶丁军陈渤
Owner XIDIAN UNIV