A three-step classification framework to handle complex data distribution for radar UAV detection

Unmanned aerial vehicles (UAVs) have been used in a wide range of applications and become an increasingly important radar target. To better model radar data and to tackle the curse of dimensionality, a three-step classification framework is proposed for UAV detection. First we propose to utilize the...

Full description

Bibliographic Details
Main Authors: Ren, Jianfeng, Jiang, Xudong
Format: Article
Language:English
Published: Elsevier Ltd 2020
Subjects:
Online Access:https://eprints.nottingham.ac.uk/63878/
_version_ 1848800068886331392
author Ren, Jianfeng
Jiang, Xudong
author_facet Ren, Jianfeng
Jiang, Xudong
author_sort Ren, Jianfeng
building Nottingham Research Data Repository
collection Online Access
description Unmanned aerial vehicles (UAVs) have been used in a wide range of applications and become an increasingly important radar target. To better model radar data and to tackle the curse of dimensionality, a three-step classification framework is proposed for UAV detection. First we propose to utilize the greedy subspace clustering to handle potential outliers and the complex sample distribution of radar data. Parameters of the resulting multi-Gaussian model, especially the covariance matrices, could not be reliably estimated due to insufficient training samples and the high dimensionality. Thus, in the second step, a multi-Gaussian subspace reliability analysis is proposed to handle the unreliable feature dimensions of these covariance matrices. To address the challenges of classifying samples using the complex multi-Gaussian model and to fuse the distances of a sample to different clusters at different dimensionalities, a subspace-fusion scheme is proposed in the third step. The proposed approach is validated on a large benchmark dataset, which significantly outperforms the state-of-the-art approaches.
first_indexed 2025-11-14T20:45:41Z
format Article
id nottingham-63878
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:45:41Z
publishDate 2020
publisher Elsevier Ltd
recordtype eprints
repository_type Digital Repository
spelling nottingham-638782020-12-03T06:05:32Z https://eprints.nottingham.ac.uk/63878/ A three-step classification framework to handle complex data distribution for radar UAV detection Ren, Jianfeng Jiang, Xudong Unmanned aerial vehicles (UAVs) have been used in a wide range of applications and become an increasingly important radar target. To better model radar data and to tackle the curse of dimensionality, a three-step classification framework is proposed for UAV detection. First we propose to utilize the greedy subspace clustering to handle potential outliers and the complex sample distribution of radar data. Parameters of the resulting multi-Gaussian model, especially the covariance matrices, could not be reliably estimated due to insufficient training samples and the high dimensionality. Thus, in the second step, a multi-Gaussian subspace reliability analysis is proposed to handle the unreliable feature dimensions of these covariance matrices. To address the challenges of classifying samples using the complex multi-Gaussian model and to fuse the distances of a sample to different clusters at different dimensionalities, a subspace-fusion scheme is proposed in the third step. The proposed approach is validated on a large benchmark dataset, which significantly outperforms the state-of-the-art approaches. Elsevier Ltd 2020-10-22 Article PeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/63878/2/A%20three-step%20classification%20framework%20to%20handle%20complex%20data%20distribution%20for%20radar%20UAV%20detection.pdf Ren, Jianfeng and Jiang, Xudong (2020) A three-step classification framework to handle complex data distribution for radar UAV detection. Pattern Recognition, 111 . p. 107709. ISSN 0031-3203 radar UAV detection; micro-Doppler signature; greedysubspace http://dx.doi.org/10.1016/j.patcog.2020.107709 doi:10.1016/j.patcog.2020.107709 doi:10.1016/j.patcog.2020.107709
spellingShingle radar UAV detection; micro-Doppler signature; greedysubspace
Ren, Jianfeng
Jiang, Xudong
A three-step classification framework to handle complex data distribution for radar UAV detection
title A three-step classification framework to handle complex data distribution for radar UAV detection
title_full A three-step classification framework to handle complex data distribution for radar UAV detection
title_fullStr A three-step classification framework to handle complex data distribution for radar UAV detection
title_full_unstemmed A three-step classification framework to handle complex data distribution for radar UAV detection
title_short A three-step classification framework to handle complex data distribution for radar UAV detection
title_sort three-step classification framework to handle complex data distribution for radar uav detection
topic radar UAV detection; micro-Doppler signature; greedysubspace
url https://eprints.nottingham.ac.uk/63878/
https://eprints.nottingham.ac.uk/63878/
https://eprints.nottingham.ac.uk/63878/