Title: A fast radar target recognition based on single Gaussian background model

Authors: Yue Fan; Zhiyuan Ma

Addresses: Department of Electronic Engineering, Naval University of Engineering, Wuhan 434400, China; School of Physics and Technology, HuaZhong Normal University, Wuhan 434400, China ' Department of Electronic Engineering, Naval University of Engineering, Wuhan 434400, China; School of Physics and Technology, HuaZhong Normal University, Wuhan 434400, China

Abstract: In order to overcome the problems of low quality factor, low recognition rate and long recognition time of radar target recognition results, a new fast recognition method of radar target based on single Gaussian background model is proposed. In this method, the radar target image is obtained by scattering point model, and the background of the target image is modelled based on the single Gaussian model to distinguish the background from the target area. Principal component analysis (PCA) and linear discriminant analysis (LDA) are used to extract the features of the target area, and the feature vectors are obtained. The SVM classifier is established. The obtained feature vectors are input into SVM classifier to realise the rapid recognition of radar targets. Experimental results show that the quality factor of the proposed method is higher than 8, the recognition rate is higher than 80%, and the recognition time is less than 0.5 s.

Keywords: single Gaussian model; background modelling; feature extraction; SVM classifier; radar target recognition.

DOI: 10.1504/IJICT.2022.124827

International Journal of Information and Communication Technology, 2022 Vol.21 No.2, pp.181 - 196

Received: 30 Sep 2020
Accepted: 06 Nov 2020
Published online: 09 Aug 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article