HRRP multi-target recognition in a beam using prior-independent DBSCAN clustering algorithm

During the operation of monopulse radar, the high-resolution range profiles (HRRPs) of multiple targets may be overlapped, which will reduce the target recognition performance. In this study, a novel multi-target recognition method is proposed based on prior-independent density-based spatial cluster...

Full description

Saved in:
Bibliographic Details
Published in:IET radar, sonar & navigation Vol. 13; no. 8; pp. 1366 - 1372
Main Authors: Guo, Peng-cheng, Liu, Zheng, Wang, Jing-jing
Format: Journal Article
Language:English
Published: The Institution of Engineering and Technology 01.08.2019
Subjects:
high‐resolution range profiles
HRRP multitarget recognition
monopulse radar
multiple targets
noise algorithm
pattern clustering
PI‐DBSCAN algorithm
prior‐independent DBSCAN clustering algorithm
radar computing
radar resolution
radar signal processing
radar target recognition
radial distance‐azimuth plane
Research Article
support vector machine classifier
support vector machines
SVM classifier
target motion
target recognition performance
test multitarget HRRP
test phase
training phase
training samples
test multitarget HRRP
PI-DBSCAN algorithm
HRRP multitarget recognition
support vector machines
support vector machine classifier
radar signal processing
monopulse radar
target motion
radar computing
prior-independent DBSCAN clustering algorithm
pattern clustering
radar resolution
radar target recognition
high-resolution range profiles
training samples
radial distance-azimuth plane
test phase
target recognition performance
training phase
multiple targets
SVM classifier
noise algorithm
ISSN:1751-8784, 1751-8792
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:During the operation of monopulse radar, the high-resolution range profiles (HRRPs) of multiple targets may be overlapped, which will reduce the target recognition performance. In this study, a novel multi-target recognition method is proposed based on prior-independent density-based spatial clustering of applications with noise (PI-DBSCAN) algorithm. In the training phase, various features of training samples are extracted, among which the distribution of strong range cells is utilised to obtain the parameters of PI-DBSCAN algorithm while the others are used to train the support vector machine (SVM) classifier. In the test phase, PI-DBSCAN algorithm is exploited at the radial distance-azimuth plane to segment the test multi-target HRRP. Afterward, the features of the segmented HRRPs are extracted and fed to the SVM classifier to be recognised. The proposed method has no constraint on the target motion and does not need to set any parameters manually, which benefits its application. The experiment results of real measured data show that the proposed method is robust against noise and the increasing target HRRP overlap ratio comparing with traditional methods.
ISSN:1751-8784
1751-8792
DOI:10.1049/iet-rsn.2018.5598