Visual attention model-based multiple target detection in synthetic aperture radar images for autonomous surveillance systems

Erfu Yang, Fei Gao, Wenguang Wang, Amir Hussain, Jun Wang, Bin Luo

Research output: Contribution to conferenceSpeech

Abstract

Visual surveillance is an attempt to detect, recognize and track certain objects from image sequences, and more generally to understand and describe object behaviors. Future’s visual surveillance systems for outdoor (including security) applications will require mission platforms that are autonomous, asynchronous, adaptive and highly sensitive in complex, time-varying and possibly hostile environments.
One fundamental problem in autonomous surveillance systems is how to detect multiple targets, sense and percept the world/environment in extreme outdoor conditions in which the presence of dust, fog, rain, changing illumination can dramatically degrade conventional stereo and laser sensing. Thus, radar-based imaging in autonomous surveillance systems has attracted extensive research attention in recent years since radar also allows for multiple targets detection within a single beam, whereas other range sensors are limited to one target return per emission. The main challenge arising from radar-based autonomous visual surveillance systems is always linked to radar image information processing and utilization, i.e., how to quickly and efficiently extract and analyse the information of interest for multiple targets from consecutive images acquired by radar imaging sensors.
In this talk, a visual attention model-based algorithm is proposed to detect multiple targets from SAR (synthetic aperture radar) images. The algorithm extends the well-known Itti model according to the requirements of multiple target detection in SAR images. It locates salient regions in SAR images and reduces false alarms significantly by using an efficient top-down process. The performance of the proposed algorithm is demonstrated by using real SAR images with 20 vehicle targets.
Acknowledgements:
This research was supported by The Royal Society of Edinburgh (RSE) and The National Natural Science Foundation of China (NNSFC) under the RSE-NNSFC joint projects (2012-2015) [grant number 61211130309 and 61211130210] with Beihang University and Anhui University, China, respectively. It was supported in part by the “Sino-UK Higher Education Research Partnership for PhD Studies” joint-project (2013-2015) funded by the British Council China and The China Scholarship Council (CSC).

Workshop

WorkshopFSD Workshop
CountryUnited Kingdom
CityOban
Period5/07/158/07/15

Fingerprint

Synthetic aperture radar
Target tracking
Radar
Natural sciences
Radar imaging
Sensors
Fog
Rain
Dust
Lighting
Education
Imaging techniques
Lasers

Keywords

  • visual attention model
  • multiple target detection
  • autonomous systems
  • cognitive computation
  • synthetic aperture radar
  • image processing

Cite this

Yang, E., Gao, F., Wang, W., Hussain, A., Wang, J., & Luo, B. (2015). Visual attention model-based multiple target detection in synthetic aperture radar images for autonomous surveillance systems. FSD Workshop , Oban, United Kingdom.
Yang, Erfu ; Gao, Fei ; Wang, Wenguang ; Hussain, Amir ; Wang, Jun ; Luo, Bin. / Visual attention model-based multiple target detection in synthetic aperture radar images for autonomous surveillance systems. FSD Workshop , Oban, United Kingdom.1 p.
@conference{aef3f49558814bc49b5ec7fbe4aa350a,
title = "Visual attention model-based multiple target detection in synthetic aperture radar images for autonomous surveillance systems",
abstract = "Visual surveillance is an attempt to detect, recognize and track certain objects from image sequences, and more generally to understand and describe object behaviors. Future’s visual surveillance systems for outdoor (including security) applications will require mission platforms that are autonomous, asynchronous, adaptive and highly sensitive in complex, time-varying and possibly hostile environments.One fundamental problem in autonomous surveillance systems is how to detect multiple targets, sense and percept the world/environment in extreme outdoor conditions in which the presence of dust, fog, rain, changing illumination can dramatically degrade conventional stereo and laser sensing. Thus, radar-based imaging in autonomous surveillance systems has attracted extensive research attention in recent years since radar also allows for multiple targets detection within a single beam, whereas other range sensors are limited to one target return per emission. The main challenge arising from radar-based autonomous visual surveillance systems is always linked to radar image information processing and utilization, i.e., how to quickly and efficiently extract and analyse the information of interest for multiple targets from consecutive images acquired by radar imaging sensors. In this talk, a visual attention model-based algorithm is proposed to detect multiple targets from SAR (synthetic aperture radar) images. The algorithm extends the well-known Itti model according to the requirements of multiple target detection in SAR images. It locates salient regions in SAR images and reduces false alarms significantly by using an efficient top-down process. The performance of the proposed algorithm is demonstrated by using real SAR images with 20 vehicle targets.Acknowledgements: This research was supported by The Royal Society of Edinburgh (RSE) and The National Natural Science Foundation of China (NNSFC) under the RSE-NNSFC joint projects (2012-2015) [grant number 61211130309 and 61211130210] with Beihang University and Anhui University, China, respectively. It was supported in part by the “Sino-UK Higher Education Research Partnership for PhD Studies” joint-project (2013-2015) funded by the British Council China and The China Scholarship Council (CSC).",
keywords = "visual attention model , multiple target detection , autonomous systems, cognitive computation, synthetic aperture radar , image processing",
author = "Erfu Yang and Fei Gao and Wenguang Wang and Amir Hussain and Jun Wang and Bin Luo",
year = "2015",
month = "7",
day = "5",
language = "English",
note = "FSD Workshop ; Conference date: 05-07-2015 Through 08-07-2015",

}

Yang, E, Gao, F, Wang, W, Hussain, A, Wang, J & Luo, B 2015, 'Visual attention model-based multiple target detection in synthetic aperture radar images for autonomous surveillance systems' FSD Workshop , Oban, United Kingdom, 5/07/15 - 8/07/15, .

Visual attention model-based multiple target detection in synthetic aperture radar images for autonomous surveillance systems. / Yang, Erfu; Gao, Fei; Wang, Wenguang; Hussain, Amir; Wang, Jun; Luo, Bin.

2015. FSD Workshop , Oban, United Kingdom.

Research output: Contribution to conferenceSpeech

TY - CONF

T1 - Visual attention model-based multiple target detection in synthetic aperture radar images for autonomous surveillance systems

AU - Yang, Erfu

AU - Gao, Fei

AU - Wang, Wenguang

AU - Hussain, Amir

AU - Wang, Jun

AU - Luo, Bin

PY - 2015/7/5

Y1 - 2015/7/5

N2 - Visual surveillance is an attempt to detect, recognize and track certain objects from image sequences, and more generally to understand and describe object behaviors. Future’s visual surveillance systems for outdoor (including security) applications will require mission platforms that are autonomous, asynchronous, adaptive and highly sensitive in complex, time-varying and possibly hostile environments.One fundamental problem in autonomous surveillance systems is how to detect multiple targets, sense and percept the world/environment in extreme outdoor conditions in which the presence of dust, fog, rain, changing illumination can dramatically degrade conventional stereo and laser sensing. Thus, radar-based imaging in autonomous surveillance systems has attracted extensive research attention in recent years since radar also allows for multiple targets detection within a single beam, whereas other range sensors are limited to one target return per emission. The main challenge arising from radar-based autonomous visual surveillance systems is always linked to radar image information processing and utilization, i.e., how to quickly and efficiently extract and analyse the information of interest for multiple targets from consecutive images acquired by radar imaging sensors. In this talk, a visual attention model-based algorithm is proposed to detect multiple targets from SAR (synthetic aperture radar) images. The algorithm extends the well-known Itti model according to the requirements of multiple target detection in SAR images. It locates salient regions in SAR images and reduces false alarms significantly by using an efficient top-down process. The performance of the proposed algorithm is demonstrated by using real SAR images with 20 vehicle targets.Acknowledgements: This research was supported by The Royal Society of Edinburgh (RSE) and The National Natural Science Foundation of China (NNSFC) under the RSE-NNSFC joint projects (2012-2015) [grant number 61211130309 and 61211130210] with Beihang University and Anhui University, China, respectively. It was supported in part by the “Sino-UK Higher Education Research Partnership for PhD Studies” joint-project (2013-2015) funded by the British Council China and The China Scholarship Council (CSC).

AB - Visual surveillance is an attempt to detect, recognize and track certain objects from image sequences, and more generally to understand and describe object behaviors. Future’s visual surveillance systems for outdoor (including security) applications will require mission platforms that are autonomous, asynchronous, adaptive and highly sensitive in complex, time-varying and possibly hostile environments.One fundamental problem in autonomous surveillance systems is how to detect multiple targets, sense and percept the world/environment in extreme outdoor conditions in which the presence of dust, fog, rain, changing illumination can dramatically degrade conventional stereo and laser sensing. Thus, radar-based imaging in autonomous surveillance systems has attracted extensive research attention in recent years since radar also allows for multiple targets detection within a single beam, whereas other range sensors are limited to one target return per emission. The main challenge arising from radar-based autonomous visual surveillance systems is always linked to radar image information processing and utilization, i.e., how to quickly and efficiently extract and analyse the information of interest for multiple targets from consecutive images acquired by radar imaging sensors. In this talk, a visual attention model-based algorithm is proposed to detect multiple targets from SAR (synthetic aperture radar) images. The algorithm extends the well-known Itti model according to the requirements of multiple target detection in SAR images. It locates salient regions in SAR images and reduces false alarms significantly by using an efficient top-down process. The performance of the proposed algorithm is demonstrated by using real SAR images with 20 vehicle targets.Acknowledgements: This research was supported by The Royal Society of Edinburgh (RSE) and The National Natural Science Foundation of China (NNSFC) under the RSE-NNSFC joint projects (2012-2015) [grant number 61211130309 and 61211130210] with Beihang University and Anhui University, China, respectively. It was supported in part by the “Sino-UK Higher Education Research Partnership for PhD Studies” joint-project (2013-2015) funded by the British Council China and The China Scholarship Council (CSC).

KW - visual attention model

KW - multiple target detection

KW - autonomous systems

KW - cognitive computation

KW - synthetic aperture radar

KW - image processing

M3 - Speech

ER -