SAR automatic target recognition using discriminative graphical models

Umamahesh Srinivas, Vishal Monga, Raghu G. Raj

    Research output: Contribution to journalArticle

    82 Citations (Scopus)

    Abstract

    The problem of automatically classifying sensed imagery such as synthetic aperture radar (SAR) into a canonical set of target classes is widely known as automatic target recognition (ATR). A typical ATR algorithm comprises the extraction of a meaningful set of features from target imagery followed by a decision engine that performs class assignment. While ATR algorithms have significantly increased in sophistication over the past two decades, two outstanding challenges have been identified in the rich body of ATR literature: 1) the desire to mine complementary merits of distinct feature sets (also known as feature fusion), and 2) the ability of the classifier to excel even as training SAR images are limited. We propose to apply recent advances in probabilistic graphical models to address these challenges. In particular we develop a two-stage target recognition framework that combines the merits of distinct SAR image feature representations with discriminatively learned graphical models. The first stage projects the SAR image chip to informative feature spaces that yield multiple complementary SAR image representations. The second stage models each individual representation using graphs and combines these initially disjoint and simple graphs into a thicker probabilistic graphical model by leveraging a recent advance in discriminative graph learning. Experimental results on the benchmark moving and stationary target acquisition and recognition (MSTAR) data set confirm the benefits of our framework over existing ATR algorithms in terms of improvement in recognition rates. The proposed graphical classifiers are particularly robust when feature dimensionality is high and number of training images is small, a commonly observed constraint in SAR imagery-based target recognition.

    Original languageEnglish (US)
    Article number6809937
    Pages (from-to)591-606
    Number of pages16
    JournalIEEE Transactions on Aerospace and Electronic Systems
    Volume50
    Issue number1
    DOIs
    StatePublished - Jan 1 2014

    Fingerprint

    Automatic target recognition
    Synthetic aperture radar
    Classifiers
    Fusion reactions
    Engines

    All Science Journal Classification (ASJC) codes

    • Aerospace Engineering
    • Electrical and Electronic Engineering

    Cite this

    @article{8bd3951917eb435c89e43c5428492e3d,
    title = "SAR automatic target recognition using discriminative graphical models",
    abstract = "The problem of automatically classifying sensed imagery such as synthetic aperture radar (SAR) into a canonical set of target classes is widely known as automatic target recognition (ATR). A typical ATR algorithm comprises the extraction of a meaningful set of features from target imagery followed by a decision engine that performs class assignment. While ATR algorithms have significantly increased in sophistication over the past two decades, two outstanding challenges have been identified in the rich body of ATR literature: 1) the desire to mine complementary merits of distinct feature sets (also known as feature fusion), and 2) the ability of the classifier to excel even as training SAR images are limited. We propose to apply recent advances in probabilistic graphical models to address these challenges. In particular we develop a two-stage target recognition framework that combines the merits of distinct SAR image feature representations with discriminatively learned graphical models. The first stage projects the SAR image chip to informative feature spaces that yield multiple complementary SAR image representations. The second stage models each individual representation using graphs and combines these initially disjoint and simple graphs into a thicker probabilistic graphical model by leveraging a recent advance in discriminative graph learning. Experimental results on the benchmark moving and stationary target acquisition and recognition (MSTAR) data set confirm the benefits of our framework over existing ATR algorithms in terms of improvement in recognition rates. The proposed graphical classifiers are particularly robust when feature dimensionality is high and number of training images is small, a commonly observed constraint in SAR imagery-based target recognition.",
    author = "Umamahesh Srinivas and Vishal Monga and Raj, {Raghu G.}",
    year = "2014",
    month = "1",
    day = "1",
    doi = "10.1109/TAES.2013.120340",
    language = "English (US)",
    volume = "50",
    pages = "591--606",
    journal = "IEEE Transactions on Aerospace and Electronic Systems",
    issn = "0018-9251",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    number = "1",

    }

    SAR automatic target recognition using discriminative graphical models. / Srinivas, Umamahesh; Monga, Vishal; Raj, Raghu G.

    In: IEEE Transactions on Aerospace and Electronic Systems, Vol. 50, No. 1, 6809937, 01.01.2014, p. 591-606.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - SAR automatic target recognition using discriminative graphical models

    AU - Srinivas, Umamahesh

    AU - Monga, Vishal

    AU - Raj, Raghu G.

    PY - 2014/1/1

    Y1 - 2014/1/1

    N2 - The problem of automatically classifying sensed imagery such as synthetic aperture radar (SAR) into a canonical set of target classes is widely known as automatic target recognition (ATR). A typical ATR algorithm comprises the extraction of a meaningful set of features from target imagery followed by a decision engine that performs class assignment. While ATR algorithms have significantly increased in sophistication over the past two decades, two outstanding challenges have been identified in the rich body of ATR literature: 1) the desire to mine complementary merits of distinct feature sets (also known as feature fusion), and 2) the ability of the classifier to excel even as training SAR images are limited. We propose to apply recent advances in probabilistic graphical models to address these challenges. In particular we develop a two-stage target recognition framework that combines the merits of distinct SAR image feature representations with discriminatively learned graphical models. The first stage projects the SAR image chip to informative feature spaces that yield multiple complementary SAR image representations. The second stage models each individual representation using graphs and combines these initially disjoint and simple graphs into a thicker probabilistic graphical model by leveraging a recent advance in discriminative graph learning. Experimental results on the benchmark moving and stationary target acquisition and recognition (MSTAR) data set confirm the benefits of our framework over existing ATR algorithms in terms of improvement in recognition rates. The proposed graphical classifiers are particularly robust when feature dimensionality is high and number of training images is small, a commonly observed constraint in SAR imagery-based target recognition.

    AB - The problem of automatically classifying sensed imagery such as synthetic aperture radar (SAR) into a canonical set of target classes is widely known as automatic target recognition (ATR). A typical ATR algorithm comprises the extraction of a meaningful set of features from target imagery followed by a decision engine that performs class assignment. While ATR algorithms have significantly increased in sophistication over the past two decades, two outstanding challenges have been identified in the rich body of ATR literature: 1) the desire to mine complementary merits of distinct feature sets (also known as feature fusion), and 2) the ability of the classifier to excel even as training SAR images are limited. We propose to apply recent advances in probabilistic graphical models to address these challenges. In particular we develop a two-stage target recognition framework that combines the merits of distinct SAR image feature representations with discriminatively learned graphical models. The first stage projects the SAR image chip to informative feature spaces that yield multiple complementary SAR image representations. The second stage models each individual representation using graphs and combines these initially disjoint and simple graphs into a thicker probabilistic graphical model by leveraging a recent advance in discriminative graph learning. Experimental results on the benchmark moving and stationary target acquisition and recognition (MSTAR) data set confirm the benefits of our framework over existing ATR algorithms in terms of improvement in recognition rates. The proposed graphical classifiers are particularly robust when feature dimensionality is high and number of training images is small, a commonly observed constraint in SAR imagery-based target recognition.

    UR - http://www.scopus.com/inward/record.url?scp=84900565951&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84900565951&partnerID=8YFLogxK

    U2 - 10.1109/TAES.2013.120340

    DO - 10.1109/TAES.2013.120340

    M3 - Article

    AN - SCOPUS:84900565951

    VL - 50

    SP - 591

    EP - 606

    JO - IEEE Transactions on Aerospace and Electronic Systems

    JF - IEEE Transactions on Aerospace and Electronic Systems

    SN - 0018-9251

    IS - 1

    M1 - 6809937

    ER -