Target detection and recognition in SAR imagery based on KFDA

Fei Gao, Jingyuan Mei, Jinping Sun, Jun Wang, Erfu Yang, Amir Hussain

Research output: Contribution to journalArticle

Abstract

Current research on target detection and recognition from synthetic aperture radar (SAR) images is usually carried out separately. It is difficult to verify the ability of a target recognition algorithm for adapting to changes in the environment. To realize the whole process of SAR automatic target recognition (ATR), especially for the detection and recognition of vehicles, an algorithm based on kernel fisher discriminant analysis (KFDA) is proposed in this paper. First, in order to make a better description of the difference between background and target, KFDA is extended to the detection part. Image samples are obtained with a dual-window approach and features of the inner and outer window samples are extracted using KFDA. The difference between the features of inner and outer window samples is compared with a threshold to determine whether a vehicle exists. Second, for the target area, we propose an improved KFDA-IMED (Image Euclidean Distance) combined with a support vector machine (SVM) to recognize the vehicles. Experimental results validate the performance of our method. On the detection task, our proposed method obtains not only a high detection rate but also a low false alarm rate without using any prior information. For the recognition task, our method overcomes the SAR image aspect angle sensitivity, reduces the requirements for image preprocessing and improves the recognition rate.
LanguageEnglish
Number of pages22
JournalJournal of Systems Engineering and Electronics
Publication statusAccepted/In press - 20 May 2015

Fingerprint

Discriminant analysis
Synthetic aperture radar
Target tracking
Automatic target recognition
Support vector machines

Keywords

  • synthetic aperture radar
  • target detection
  • kernel fisher discriminant analysis
  • target recognition
  • image Euclidean distance
  • support vector machine

Cite this

Gao, Fei ; Mei, Jingyuan ; Sun, Jinping ; Wang, Jun ; Yang, Erfu ; Hussain, Amir. / Target detection and recognition in SAR imagery based on KFDA. In: Journal of Systems Engineering and Electronics. 2015.
@article{b379958b547f43a29e9a9abf2cd46600,
title = "Target detection and recognition in SAR imagery based on KFDA",
abstract = "Current research on target detection and recognition from synthetic aperture radar (SAR) images is usually carried out separately. It is difficult to verify the ability of a target recognition algorithm for adapting to changes in the environment. To realize the whole process of SAR automatic target recognition (ATR), especially for the detection and recognition of vehicles, an algorithm based on kernel fisher discriminant analysis (KFDA) is proposed in this paper. First, in order to make a better description of the difference between background and target, KFDA is extended to the detection part. Image samples are obtained with a dual-window approach and features of the inner and outer window samples are extracted using KFDA. The difference between the features of inner and outer window samples is compared with a threshold to determine whether a vehicle exists. Second, for the target area, we propose an improved KFDA-IMED (Image Euclidean Distance) combined with a support vector machine (SVM) to recognize the vehicles. Experimental results validate the performance of our method. On the detection task, our proposed method obtains not only a high detection rate but also a low false alarm rate without using any prior information. For the recognition task, our method overcomes the SAR image aspect angle sensitivity, reduces the requirements for image preprocessing and improves the recognition rate.",
keywords = "synthetic aperture radar, target detection, kernel fisher discriminant analysis, target recognition, image Euclidean distance, support vector machine",
author = "Fei Gao and Jingyuan Mei and Jinping Sun and Jun Wang and Erfu Yang and Amir Hussain",
year = "2015",
month = "5",
day = "20",
language = "English",
journal = "Journal of Systems Engineering and Electronics",
issn = "1004-4132",

}

Target detection and recognition in SAR imagery based on KFDA. / Gao, Fei; Mei, Jingyuan; Sun, Jinping; Wang, Jun; Yang, Erfu; Hussain, Amir.

In: Journal of Systems Engineering and Electronics, 20.05.2015.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Target detection and recognition in SAR imagery based on KFDA

AU - Gao, Fei

AU - Mei, Jingyuan

AU - Sun, Jinping

AU - Wang, Jun

AU - Yang, Erfu

AU - Hussain, Amir

PY - 2015/5/20

Y1 - 2015/5/20

N2 - Current research on target detection and recognition from synthetic aperture radar (SAR) images is usually carried out separately. It is difficult to verify the ability of a target recognition algorithm for adapting to changes in the environment. To realize the whole process of SAR automatic target recognition (ATR), especially for the detection and recognition of vehicles, an algorithm based on kernel fisher discriminant analysis (KFDA) is proposed in this paper. First, in order to make a better description of the difference between background and target, KFDA is extended to the detection part. Image samples are obtained with a dual-window approach and features of the inner and outer window samples are extracted using KFDA. The difference between the features of inner and outer window samples is compared with a threshold to determine whether a vehicle exists. Second, for the target area, we propose an improved KFDA-IMED (Image Euclidean Distance) combined with a support vector machine (SVM) to recognize the vehicles. Experimental results validate the performance of our method. On the detection task, our proposed method obtains not only a high detection rate but also a low false alarm rate without using any prior information. For the recognition task, our method overcomes the SAR image aspect angle sensitivity, reduces the requirements for image preprocessing and improves the recognition rate.

AB - Current research on target detection and recognition from synthetic aperture radar (SAR) images is usually carried out separately. It is difficult to verify the ability of a target recognition algorithm for adapting to changes in the environment. To realize the whole process of SAR automatic target recognition (ATR), especially for the detection and recognition of vehicles, an algorithm based on kernel fisher discriminant analysis (KFDA) is proposed in this paper. First, in order to make a better description of the difference between background and target, KFDA is extended to the detection part. Image samples are obtained with a dual-window approach and features of the inner and outer window samples are extracted using KFDA. The difference between the features of inner and outer window samples is compared with a threshold to determine whether a vehicle exists. Second, for the target area, we propose an improved KFDA-IMED (Image Euclidean Distance) combined with a support vector machine (SVM) to recognize the vehicles. Experimental results validate the performance of our method. On the detection task, our proposed method obtains not only a high detection rate but also a low false alarm rate without using any prior information. For the recognition task, our method overcomes the SAR image aspect angle sensitivity, reduces the requirements for image preprocessing and improves the recognition rate.

KW - synthetic aperture radar

KW - target detection

KW - kernel fisher discriminant analysis

KW - target recognition

KW - image Euclidean distance

KW - support vector machine

UR - http://www.elsevier.com/journals/journal-of-systems-engineering-and-electronics/1004-4132

M3 - Article

JO - Journal of Systems Engineering and Electronics

T2 - Journal of Systems Engineering and Electronics

JF - Journal of Systems Engineering and Electronics

SN - 1004-4132

ER -