DL-CFAR: a Novel CFAR Target Detection Method Based on Deep Learning

Chia Hung Lin; Yu Chien Lin; Yue  Bai; Wei-Ho Chung; Ta-Sung Lee; Heikki Huttunen

doi:10.1109/VTCFall.2019.8891420

DL-CFAR: a Novel CFAR Target Detection Method Based on Deep Learning

Chia Hung Lin, Yu Chien Lin, Yue Bai, Wei-Ho Chung, Ta-Sung Lee, Heikki Huttunen

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

16 Scopus citations

Abstract

The well-known cell-averaging constant false alarm rate (CA-CFAR) scheme and its variants suffer from masking effect in multi-target scenarios. Although order-statistic CFAR (OS-CFAR) scheme performs well in such scenarios, it is compromised with high computational complexity. To handle masking effects with a lower computational cost, in this paper, we propose a deep-learning based CFAR (DL- CFAR) scheme. DL-CFAR is the first attempt to improve the noise estimation process in CFAR based on deep learning. Simulation results demonstrate that DL-CFAR outperforms conventional CFAR schemes in the presence of masking effects. Furthermore, it can outperform conventional CFAR schemes significantly under various signal-to-noise ratio conditions. We hope that this work will encourage other researchers to introduce advanced machine learning technique into the field of target detection.

Original language	American English
Number of pages	6
DOIs	https://doi.org/10.1109/VTCFall.2019.8891420
State	Published - 22 Sep 2019
Event	2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall) - Honolulu, United States Duration: 22 Sep 2019 → 25 Sep 2019

Conference

Conference	2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall)
Country/Territory	United States
City	Honolulu
Period	22/09/19 → 25/09/19

Keywords

constant false alarm rate (CFAR)
target detection
deep learning
neural network

Access to Document

10.1109/VTCFall.2019.8891420

Cite this

@conference{af77b482aa1a494a8d0d401ed5960f51,

title = "DL-CFAR: a Novel CFAR Target Detection Method Based on Deep Learning",

abstract = "The well-known cell-averaging constant false alarm rate (CA-CFAR) scheme and its variants suffer from masking effect in multi-target scenarios. Although order-statistic CFAR (OS-CFAR) scheme performs well in such scenarios, it is compromised with high computational complexity. To handle masking effects with a lower computational cost, in this paper, we propose a deep-learning based CFAR (DL- CFAR) scheme. DL-CFAR is the first attempt to improve the noise estimation process in CFAR based on deep learning. Simulation results demonstrate that DL-CFAR outperforms conventional CFAR schemes in the presence of masking effects. Furthermore, it can outperform conventional CFAR schemes significantly under various signal-to-noise ratio conditions. We hope that this work will encourage other researchers to introduce advanced machine learning technique into the field of target detection.",

keywords = "constant false alarm rate (CFAR), target detection, deep learning, neural network",

author = "Lin, {Chia Hung} and Lin, {Yu Chien} and Yue Bai and Wei-Ho Chung and Ta-Sung Lee and Heikki Huttunen",

year = "2019",

month = sep,

day = "22",

doi = "10.1109/VTCFall.2019.8891420",

language = "American English",

note = "2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall) ; Conference date: 22-09-2019 Through 25-09-2019",

}

TY - CONF

T1 - DL-CFAR

T2 - 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall)

AU - Lin, Chia Hung

AU - Lin, Yu Chien

AU - Bai, Yue

AU - Chung, Wei-Ho

AU - Lee, Ta-Sung

AU - Huttunen, Heikki

PY - 2019/9/22

Y1 - 2019/9/22

N2 - The well-known cell-averaging constant false alarm rate (CA-CFAR) scheme and its variants suffer from masking effect in multi-target scenarios. Although order-statistic CFAR (OS-CFAR) scheme performs well in such scenarios, it is compromised with high computational complexity. To handle masking effects with a lower computational cost, in this paper, we propose a deep-learning based CFAR (DL- CFAR) scheme. DL-CFAR is the first attempt to improve the noise estimation process in CFAR based on deep learning. Simulation results demonstrate that DL-CFAR outperforms conventional CFAR schemes in the presence of masking effects. Furthermore, it can outperform conventional CFAR schemes significantly under various signal-to-noise ratio conditions. We hope that this work will encourage other researchers to introduce advanced machine learning technique into the field of target detection.

AB - The well-known cell-averaging constant false alarm rate (CA-CFAR) scheme and its variants suffer from masking effect in multi-target scenarios. Although order-statistic CFAR (OS-CFAR) scheme performs well in such scenarios, it is compromised with high computational complexity. To handle masking effects with a lower computational cost, in this paper, we propose a deep-learning based CFAR (DL- CFAR) scheme. DL-CFAR is the first attempt to improve the noise estimation process in CFAR based on deep learning. Simulation results demonstrate that DL-CFAR outperforms conventional CFAR schemes in the presence of masking effects. Furthermore, it can outperform conventional CFAR schemes significantly under various signal-to-noise ratio conditions. We hope that this work will encourage other researchers to introduce advanced machine learning technique into the field of target detection.

KW - constant false alarm rate (CFAR)

KW - target detection

KW - deep learning

KW - neural network

U2 - 10.1109/VTCFall.2019.8891420

DO - 10.1109/VTCFall.2019.8891420

M3 - Paper

Y2 - 22 September 2019 through 25 September 2019

ER -

DL-CFAR: a Novel CFAR Target Detection Method Based on Deep Learning

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this