Chebychev moments based drone classification, recognition and fingerprinting

Carmine Clemente; Luca Pallotta; Christos Ilioudis; Francesco Fioranelli; Gaetano Giunta; Alfonso Farina

Chebychev moments based drone classification, recognition and fingerprinting

Carmine Clemente, Luca Pallotta, Christos Ilioudis, Francesco Fioranelli, Gaetano Giunta, Alfonso Farina

Research output: Contribution to conference › Paper › peer-review

46 Downloads (Pure)

Abstract

This paper introduces the use of a Chebychev moments' based feature for micro-Doppler based Classification, Recognition and Fingerprinting of Drones. This specific feature has been selected for its low computational cost and orthogonality property. The capability of the proposed feature extraction framework is assessed at three different levels of major classification steps, namely classification, recognition and fingerprinting, demonstrating the effectiveness of the proposed approach to discriminate drones from birds, fixed wings from multi-rotors and drones carrying different payloads on real measured radar data.

Original language	English
Number of pages	6
Publication status	Published - 22 Jun 2021
Event	International Radar Symposium - Online, Bonn, Germany Duration: 21 Jun 2021 → 22 Jun 2022 https://www.dgon-irs.org/home/

Conference

Conference	International Radar Symposium
Abbreviated title	IRS 2021
Country/Territory	Germany
City	Bonn
Period	21/06/21 → 22/06/22
Internet address	https://www.dgon-irs.org/home/

Keywords

drones
UAVs
micro-Doppler
classification
recognition
fingerprinting
ATR
image moments

Access to Document

Clemente-etal-IRS-2021-Chebychev-moments-based-drone-classification-recognition-and-fingerprintingAccepted author manuscript, 109 KB

Cite this

@conference{92ac9ad0d4784689b41c8a45a2fd54c4,

title = "Chebychev moments based drone classification, recognition and fingerprinting",

abstract = "This paper introduces the use of a Chebychev moments' based feature for micro-Doppler based Classification, Recognition and Fingerprinting of Drones. This specific feature has been selected for its low computational cost and orthogonality property. The capability of the proposed feature extraction framework is assessed at three different levels of major classification steps, namely classification, recognition and fingerprinting, demonstrating the effectiveness of the proposed approach to discriminate drones from birds, fixed wings from multi-rotors and drones carrying different payloads on real measured radar data.",

keywords = "drones, UAVs, micro-Doppler, classification, recognition, fingerprinting, ATR, image moments",

author = "Carmine Clemente and Luca Pallotta and Christos Ilioudis and Francesco Fioranelli and Gaetano Giunta and Alfonso Farina",

year = "2021",

month = jun,

day = "22",

language = "English",

note = "International Radar Symposium, IRS 2021 ; Conference date: 21-06-2021 Through 22-06-2022",

url = "https://www.dgon-irs.org/home/",

}

TY - CONF

T1 - Chebychev moments based drone classification, recognition and fingerprinting

AU - Clemente, Carmine

AU - Pallotta, Luca

AU - Ilioudis, Christos

AU - Fioranelli, Francesco

AU - Giunta, Gaetano

AU - Farina, Alfonso

PY - 2021/6/22

Y1 - 2021/6/22

N2 - This paper introduces the use of a Chebychev moments' based feature for micro-Doppler based Classification, Recognition and Fingerprinting of Drones. This specific feature has been selected for its low computational cost and orthogonality property. The capability of the proposed feature extraction framework is assessed at three different levels of major classification steps, namely classification, recognition and fingerprinting, demonstrating the effectiveness of the proposed approach to discriminate drones from birds, fixed wings from multi-rotors and drones carrying different payloads on real measured radar data.

AB - This paper introduces the use of a Chebychev moments' based feature for micro-Doppler based Classification, Recognition and Fingerprinting of Drones. This specific feature has been selected for its low computational cost and orthogonality property. The capability of the proposed feature extraction framework is assessed at three different levels of major classification steps, namely classification, recognition and fingerprinting, demonstrating the effectiveness of the proposed approach to discriminate drones from birds, fixed wings from multi-rotors and drones carrying different payloads on real measured radar data.

KW - drones

KW - UAVs

KW - micro-Doppler

KW - classification

KW - recognition

KW - fingerprinting

KW - ATR

KW - image moments

UR - https://www.dgon-irs.org/home/

M3 - Paper

T2 - International Radar Symposium

Y2 - 21 June 2021 through 22 June 2022

ER -

Chebychev moments based drone classification, recognition and fingerprinting

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this