A novel visual attention method for target detection from SAR images

Fei Gao, Aidong Liu, Kai Liu, Erfu Yang, Amir Hussain

Research output: Contribution to journalArticle

Abstract

Synthetic Aperture Radar (SAR) imaging systems have been widely used in civil and military fields due to their all-weather and all-day abilities and various other advantages. However, due to image data exponentially increasing, there is a need for novel automatic target detection and recognition technologies. In recent years, the visual attention mechanism in the visual system has helped humans effectively deal with complex visual signals. In particular, biologically inspired top-down attention models have garnered much attention recently. This paper presents a visual attention model for SAR target detection, comprising a bottom-up stage and top-down process. In the bottom-up step, the Itti model is improved based on the difference between SAR and optical images. The top-down step fully utilizes prior information to further detect targets. Extensive detection experiments carried out on the benchmark Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that, compared with typical visual models and other popular detection methods, our model has increased ability and robustness for SAR target detection, under a range of Signal to Clutter Ratio (SCR) conditions and scenes. In addition, results obtained using only the bottom-up stage are inferior to those of the proposed method, further demonstrating the effectiveness and rationality of a top-down strategy. In summary, our proposed visual attention method can be considered a potential benchmark resource for the SAR research community.

LanguageEnglish
Pages1946-1958
Number of pages13
JournalChinese Journal of Aeronautics
Volume32
Issue number8
Early online date25 Apr 2019
DOIs
Publication statusPublished - 31 Aug 2019

Fingerprint

Synthetic aperture radar
Target tracking
Radar imaging
Imaging systems
Experiments

Keywords

  • learning strategy
  • synthetic aperture radar (SAR) images
  • target detection
  • top-down
  • visual attention mechanism

Cite this

Gao, Fei ; Liu, Aidong ; Liu, Kai ; Yang, Erfu ; Hussain, Amir. / A novel visual attention method for target detection from SAR images. In: Chinese Journal of Aeronautics. 2019 ; Vol. 32, No. 8. pp. 1946-1958.
@article{a37013444d8540d4bc0bcda327fbaafd,
title = "A novel visual attention method for target detection from SAR images",
abstract = "Synthetic Aperture Radar (SAR) imaging systems have been widely used in civil and military fields due to their all-weather and all-day abilities and various other advantages. However, due to image data exponentially increasing, there is a need for novel automatic target detection and recognition technologies. In recent years, the visual attention mechanism in the visual system has helped humans effectively deal with complex visual signals. In particular, biologically inspired top-down attention models have garnered much attention recently. This paper presents a visual attention model for SAR target detection, comprising a bottom-up stage and top-down process. In the bottom-up step, the Itti model is improved based on the difference between SAR and optical images. The top-down step fully utilizes prior information to further detect targets. Extensive detection experiments carried out on the benchmark Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that, compared with typical visual models and other popular detection methods, our model has increased ability and robustness for SAR target detection, under a range of Signal to Clutter Ratio (SCR) conditions and scenes. In addition, results obtained using only the bottom-up stage are inferior to those of the proposed method, further demonstrating the effectiveness and rationality of a top-down strategy. In summary, our proposed visual attention method can be considered a potential benchmark resource for the SAR research community.",
keywords = "learning strategy, synthetic aperture radar (SAR) images, target detection, top-down, visual attention mechanism",
author = "Fei Gao and Aidong Liu and Kai Liu and Erfu Yang and Amir Hussain",
year = "2019",
month = "8",
day = "31",
doi = "10.1016/j.cja.2019.03.021",
language = "English",
volume = "32",
pages = "1946--1958",
journal = "Chinese Journal of Aeronautics",
issn = "1000-9361",
number = "8",

}

A novel visual attention method for target detection from SAR images. / Gao, Fei; Liu, Aidong; Liu, Kai; Yang, Erfu; Hussain, Amir.

In: Chinese Journal of Aeronautics, Vol. 32, No. 8, 31.08.2019, p. 1946-1958.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A novel visual attention method for target detection from SAR images

AU - Gao, Fei

AU - Liu, Aidong

AU - Liu, Kai

AU - Yang, Erfu

AU - Hussain, Amir

PY - 2019/8/31

Y1 - 2019/8/31

N2 - Synthetic Aperture Radar (SAR) imaging systems have been widely used in civil and military fields due to their all-weather and all-day abilities and various other advantages. However, due to image data exponentially increasing, there is a need for novel automatic target detection and recognition technologies. In recent years, the visual attention mechanism in the visual system has helped humans effectively deal with complex visual signals. In particular, biologically inspired top-down attention models have garnered much attention recently. This paper presents a visual attention model for SAR target detection, comprising a bottom-up stage and top-down process. In the bottom-up step, the Itti model is improved based on the difference between SAR and optical images. The top-down step fully utilizes prior information to further detect targets. Extensive detection experiments carried out on the benchmark Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that, compared with typical visual models and other popular detection methods, our model has increased ability and robustness for SAR target detection, under a range of Signal to Clutter Ratio (SCR) conditions and scenes. In addition, results obtained using only the bottom-up stage are inferior to those of the proposed method, further demonstrating the effectiveness and rationality of a top-down strategy. In summary, our proposed visual attention method can be considered a potential benchmark resource for the SAR research community.

AB - Synthetic Aperture Radar (SAR) imaging systems have been widely used in civil and military fields due to their all-weather and all-day abilities and various other advantages. However, due to image data exponentially increasing, there is a need for novel automatic target detection and recognition technologies. In recent years, the visual attention mechanism in the visual system has helped humans effectively deal with complex visual signals. In particular, biologically inspired top-down attention models have garnered much attention recently. This paper presents a visual attention model for SAR target detection, comprising a bottom-up stage and top-down process. In the bottom-up step, the Itti model is improved based on the difference between SAR and optical images. The top-down step fully utilizes prior information to further detect targets. Extensive detection experiments carried out on the benchmark Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that, compared with typical visual models and other popular detection methods, our model has increased ability and robustness for SAR target detection, under a range of Signal to Clutter Ratio (SCR) conditions and scenes. In addition, results obtained using only the bottom-up stage are inferior to those of the proposed method, further demonstrating the effectiveness and rationality of a top-down strategy. In summary, our proposed visual attention method can be considered a potential benchmark resource for the SAR research community.

KW - learning strategy

KW - synthetic aperture radar (SAR) images

KW - target detection

KW - top-down

KW - visual attention mechanism

UR - http://www.scopus.com/inward/record.url?scp=85066292389&partnerID=8YFLogxK

U2 - 10.1016/j.cja.2019.03.021

DO - 10.1016/j.cja.2019.03.021

M3 - Article

VL - 32

SP - 1946

EP - 1958

JO - Chinese Journal of Aeronautics

T2 - Chinese Journal of Aeronautics

JF - Chinese Journal of Aeronautics

SN - 1000-9361

IS - 8

ER -