Tensor sparsity for classifying low-frequency ultra-wideband (UWB) SAR imagery

Tiep H. Vu, Lam Nguyen, Calvin Le, Vishal Monga

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    2 Citations (Scopus)

    Abstract

    Although a lot of progress has been made over the years, one critical challenge still facing low-frequency (UHF to L-band) ultra-wideband (UWB) synthetic aperture radar (SAR) technology is the discrimination of buried and obscured targets of interest from other natural and manmade clutter objects in the scene. The key issues are i) low-resolution SAR imagery for this frequency band, ii) targets of interests being typically small compared to the radar signal wavelengths, iii) targets having low radar cross sections (RCS), and iv) very noisy SAR imagery (e.g. target responses buried in responses from cluttered environment). In this paper, we consider the problem of discriminating and classifying buried targets of interest (buried metal and plastic mines, 155-mm unexploded ordinance [UXO], etc.) from other natural and manmade clutter objects (soda can, rocks, etc.) in the presence of noisy responses from the rough ground surfaces for low-frequency UWB 2-D SAR images. We generalize the traditional sparse representation-based classification (SRC) to a model with capability of using the information of the shared class, and implement multichannel classification problems by exploiting structures of sparse coefficients using various techniques. Here, we employ an electromagnetic (EM) SAR database generated using the finite-difference, time-domain (FDTD) software, which is based on a full-wave computational EM method.

    Original languageEnglish (US)
    Title of host publication2017 IEEE Radar Conference, RadarConf 2017
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages557-562
    Number of pages6
    ISBN (Electronic)9781467388238
    DOIs
    StatePublished - Jun 7 2017
    Event2017 IEEE Radar Conference, RadarConf 2017 - Seattle, United States
    Duration: May 8 2017May 12 2017

    Publication series

    Name2017 IEEE Radar Conference, RadarConf 2017

    Other

    Other2017 IEEE Radar Conference, RadarConf 2017
    CountryUnited States
    CitySeattle
    Period5/8/175/12/17

    Fingerprint

    radar imagery
    synthetic aperture radar
    Synthetic aperture radar
    classifying
    Ultra-wideband (UWB)
    Tensors
    tensors
    low frequencies
    broadband
    clutter
    computational electromagnetics
    Computational electromagnetics
    radar cross sections
    Radar cross section
    ultrahigh frequencies
    Frequency bands
    discrimination
    radar
    Radar
    plastics

    All Science Journal Classification (ASJC) codes

    • Computer Networks and Communications
    • Signal Processing
    • Instrumentation

    Cite this

    Vu, T. H., Nguyen, L., Le, C., & Monga, V. (2017). Tensor sparsity for classifying low-frequency ultra-wideband (UWB) SAR imagery. In 2017 IEEE Radar Conference, RadarConf 2017 (pp. 557-562). [7944265] (2017 IEEE Radar Conference, RadarConf 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RADAR.2017.7944265
    Vu, Tiep H. ; Nguyen, Lam ; Le, Calvin ; Monga, Vishal. / Tensor sparsity for classifying low-frequency ultra-wideband (UWB) SAR imagery. 2017 IEEE Radar Conference, RadarConf 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 557-562 (2017 IEEE Radar Conference, RadarConf 2017).
    @inproceedings{f0cf036ce9a440fcae8395e6906b8325,
    title = "Tensor sparsity for classifying low-frequency ultra-wideband (UWB) SAR imagery",
    abstract = "Although a lot of progress has been made over the years, one critical challenge still facing low-frequency (UHF to L-band) ultra-wideband (UWB) synthetic aperture radar (SAR) technology is the discrimination of buried and obscured targets of interest from other natural and manmade clutter objects in the scene. The key issues are i) low-resolution SAR imagery for this frequency band, ii) targets of interests being typically small compared to the radar signal wavelengths, iii) targets having low radar cross sections (RCS), and iv) very noisy SAR imagery (e.g. target responses buried in responses from cluttered environment). In this paper, we consider the problem of discriminating and classifying buried targets of interest (buried metal and plastic mines, 155-mm unexploded ordinance [UXO], etc.) from other natural and manmade clutter objects (soda can, rocks, etc.) in the presence of noisy responses from the rough ground surfaces for low-frequency UWB 2-D SAR images. We generalize the traditional sparse representation-based classification (SRC) to a model with capability of using the information of the shared class, and implement multichannel classification problems by exploiting structures of sparse coefficients using various techniques. Here, we employ an electromagnetic (EM) SAR database generated using the finite-difference, time-domain (FDTD) software, which is based on a full-wave computational EM method.",
    author = "Vu, {Tiep H.} and Lam Nguyen and Calvin Le and Vishal Monga",
    year = "2017",
    month = "6",
    day = "7",
    doi = "10.1109/RADAR.2017.7944265",
    language = "English (US)",
    series = "2017 IEEE Radar Conference, RadarConf 2017",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    pages = "557--562",
    booktitle = "2017 IEEE Radar Conference, RadarConf 2017",
    address = "United States",

    }

    Vu, TH, Nguyen, L, Le, C & Monga, V 2017, Tensor sparsity for classifying low-frequency ultra-wideband (UWB) SAR imagery. in 2017 IEEE Radar Conference, RadarConf 2017., 7944265, 2017 IEEE Radar Conference, RadarConf 2017, Institute of Electrical and Electronics Engineers Inc., pp. 557-562, 2017 IEEE Radar Conference, RadarConf 2017, Seattle, United States, 5/8/17. https://doi.org/10.1109/RADAR.2017.7944265

    Tensor sparsity for classifying low-frequency ultra-wideband (UWB) SAR imagery. / Vu, Tiep H.; Nguyen, Lam; Le, Calvin; Monga, Vishal.

    2017 IEEE Radar Conference, RadarConf 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 557-562 7944265 (2017 IEEE Radar Conference, RadarConf 2017).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    TY - GEN

    T1 - Tensor sparsity for classifying low-frequency ultra-wideband (UWB) SAR imagery

    AU - Vu, Tiep H.

    AU - Nguyen, Lam

    AU - Le, Calvin

    AU - Monga, Vishal

    PY - 2017/6/7

    Y1 - 2017/6/7

    N2 - Although a lot of progress has been made over the years, one critical challenge still facing low-frequency (UHF to L-band) ultra-wideband (UWB) synthetic aperture radar (SAR) technology is the discrimination of buried and obscured targets of interest from other natural and manmade clutter objects in the scene. The key issues are i) low-resolution SAR imagery for this frequency band, ii) targets of interests being typically small compared to the radar signal wavelengths, iii) targets having low radar cross sections (RCS), and iv) very noisy SAR imagery (e.g. target responses buried in responses from cluttered environment). In this paper, we consider the problem of discriminating and classifying buried targets of interest (buried metal and plastic mines, 155-mm unexploded ordinance [UXO], etc.) from other natural and manmade clutter objects (soda can, rocks, etc.) in the presence of noisy responses from the rough ground surfaces for low-frequency UWB 2-D SAR images. We generalize the traditional sparse representation-based classification (SRC) to a model with capability of using the information of the shared class, and implement multichannel classification problems by exploiting structures of sparse coefficients using various techniques. Here, we employ an electromagnetic (EM) SAR database generated using the finite-difference, time-domain (FDTD) software, which is based on a full-wave computational EM method.

    AB - Although a lot of progress has been made over the years, one critical challenge still facing low-frequency (UHF to L-band) ultra-wideband (UWB) synthetic aperture radar (SAR) technology is the discrimination of buried and obscured targets of interest from other natural and manmade clutter objects in the scene. The key issues are i) low-resolution SAR imagery for this frequency band, ii) targets of interests being typically small compared to the radar signal wavelengths, iii) targets having low radar cross sections (RCS), and iv) very noisy SAR imagery (e.g. target responses buried in responses from cluttered environment). In this paper, we consider the problem of discriminating and classifying buried targets of interest (buried metal and plastic mines, 155-mm unexploded ordinance [UXO], etc.) from other natural and manmade clutter objects (soda can, rocks, etc.) in the presence of noisy responses from the rough ground surfaces for low-frequency UWB 2-D SAR images. We generalize the traditional sparse representation-based classification (SRC) to a model with capability of using the information of the shared class, and implement multichannel classification problems by exploiting structures of sparse coefficients using various techniques. Here, we employ an electromagnetic (EM) SAR database generated using the finite-difference, time-domain (FDTD) software, which is based on a full-wave computational EM method.

    UR - http://www.scopus.com/inward/record.url?scp=85021433166&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85021433166&partnerID=8YFLogxK

    U2 - 10.1109/RADAR.2017.7944265

    DO - 10.1109/RADAR.2017.7944265

    M3 - Conference contribution

    AN - SCOPUS:85021433166

    T3 - 2017 IEEE Radar Conference, RadarConf 2017

    SP - 557

    EP - 562

    BT - 2017 IEEE Radar Conference, RadarConf 2017

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -

    Vu TH, Nguyen L, Le C, Monga V. Tensor sparsity for classifying low-frequency ultra-wideband (UWB) SAR imagery. In 2017 IEEE Radar Conference, RadarConf 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 557-562. 7944265. (2017 IEEE Radar Conference, RadarConf 2017). https://doi.org/10.1109/RADAR.2017.7944265