A Low-Altitude Small Target Radar Recognition Algorithm Based on Micro-Doppler Features and Vision Transformer Network

Guangmao Chen; Haibo Liu

doi:10.1109/ICSIDP62679.2024.10868656

A Low-Altitude Small Target Radar Recognition Algorithm Based on Micro-Doppler Features and Vision Transformer Network

Guangmao Chen^*, Haibo Liu

^*Corresponding author for this work

School of Information and Electronics

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In low-altitude airspace surveillance scenarios, accurately distinguishing between birds and unmanned aerial vehicles (UAVs) is of vital importance. However, the high similarity in flight altitude and speed between birds and UAVs makes it extremely difficult to distinguish between these two types of targets. To enhance radar recognition performance for both UAVs and birds, this paper proposes a low-altitude target recognition algorithm that combines micro-Doppler features with a Vision Transformer network (ViT) under a staring radar system. Verified with real-measured data, the recognition accuracy for three types of UAVs and birds reaches 94%.

Original language	English
Title of host publication	IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798331515669
DOIs	https://doi.org/10.1109/ICSIDP62679.2024.10868656
Publication status	Published - 2024
Event	2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024 - Zhuhai, China Duration: 22 Nov 2024 → 24 Nov 2024

Publication series

Name	IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

Conference

Conference	2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024
Country/Territory	China
City	Zhuhai
Period	22/11/24 → 24/11/24

Keywords

deep learning
micro-Doppler feature
target classification

Access to Document

10.1109/ICSIDP62679.2024.10868656

Cite this

Chen, G., & Liu, H. (2024). A Low-Altitude Small Target Radar Recognition Algorithm Based on Micro-Doppler Features and Vision Transformer Network. In IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024 (IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSIDP62679.2024.10868656

Chen, Guangmao ; Liu, Haibo. / A Low-Altitude Small Target Radar Recognition Algorithm Based on Micro-Doppler Features and Vision Transformer Network. IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024. Institute of Electrical and Electronics Engineers Inc., 2024. (IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024).

@inproceedings{2416d95091764ac19a91f924b4fa67d6,

title = "A Low-Altitude Small Target Radar Recognition Algorithm Based on Micro-Doppler Features and Vision Transformer Network",

abstract = "In low-altitude airspace surveillance scenarios, accurately distinguishing between birds and unmanned aerial vehicles (UAVs) is of vital importance. However, the high similarity in flight altitude and speed between birds and UAVs makes it extremely difficult to distinguish between these two types of targets. To enhance radar recognition performance for both UAVs and birds, this paper proposes a low-altitude target recognition algorithm that combines micro-Doppler features with a Vision Transformer network (ViT) under a staring radar system. Verified with real-measured data, the recognition accuracy for three types of UAVs and birds reaches 94%.",

keywords = "deep learning, micro-Doppler feature, target classification",

author = "Guangmao Chen and Haibo Liu",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024 ; Conference date: 22-11-2024 Through 24-11-2024",

year = "2024",

doi = "10.1109/ICSIDP62679.2024.10868656",

language = "English",

series = "IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024",

address = "United States",

}

Chen, G & Liu, H 2024, A Low-Altitude Small Target Radar Recognition Algorithm Based on Micro-Doppler Features and Vision Transformer Network. in IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024. IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024, Institute of Electrical and Electronics Engineers Inc., 2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024, Zhuhai, China, 22/11/24. https://doi.org/10.1109/ICSIDP62679.2024.10868656

A Low-Altitude Small Target Radar Recognition Algorithm Based on Micro-Doppler Features and Vision Transformer Network. / Chen, Guangmao; Liu, Haibo.
IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024. Institute of Electrical and Electronics Engineers Inc., 2024. (IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Low-Altitude Small Target Radar Recognition Algorithm Based on Micro-Doppler Features and Vision Transformer Network

AU - Chen, Guangmao

AU - Liu, Haibo

PY - 2024

Y1 - 2024

N2 - In low-altitude airspace surveillance scenarios, accurately distinguishing between birds and unmanned aerial vehicles (UAVs) is of vital importance. However, the high similarity in flight altitude and speed between birds and UAVs makes it extremely difficult to distinguish between these two types of targets. To enhance radar recognition performance for both UAVs and birds, this paper proposes a low-altitude target recognition algorithm that combines micro-Doppler features with a Vision Transformer network (ViT) under a staring radar system. Verified with real-measured data, the recognition accuracy for three types of UAVs and birds reaches 94%.

AB - In low-altitude airspace surveillance scenarios, accurately distinguishing between birds and unmanned aerial vehicles (UAVs) is of vital importance. However, the high similarity in flight altitude and speed between birds and UAVs makes it extremely difficult to distinguish between these two types of targets. To enhance radar recognition performance for both UAVs and birds, this paper proposes a low-altitude target recognition algorithm that combines micro-Doppler features with a Vision Transformer network (ViT) under a staring radar system. Verified with real-measured data, the recognition accuracy for three types of UAVs and birds reaches 94%.

KW - deep learning

KW - micro-Doppler feature

KW - target classification

UR - http://www.scopus.com/inward/record.url?scp=86000028584&partnerID=8YFLogxK

U2 - 10.1109/ICSIDP62679.2024.10868656

DO - 10.1109/ICSIDP62679.2024.10868656

M3 - Conference contribution

AN - SCOPUS:86000028584

T3 - IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

BT - IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

Y2 - 22 November 2024 through 24 November 2024

ER -

Chen G, Liu H. A Low-Altitude Small Target Radar Recognition Algorithm Based on Micro-Doppler Features and Vision Transformer Network. In IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024. Institute of Electrical and Electronics Engineers Inc. 2024. (IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024). doi: 10.1109/ICSIDP62679.2024.10868656

A Low-Altitude Small Target Radar Recognition Algorithm Based on Micro-Doppler Features and Vision Transformer Network

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this