Efficient ATR using compression

Ulug, Batu; Ahalt, Stanley C.; Mitchell, Richard A.

doi:10.1109/7.625114

Cited by 9 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The U.S. Advanced Research Project Agency under the Wright Research and Development Center, U.S. Air Force in [13] describes a model-based SAR recognition system based on invariant histograms and deformable template matching techniques. In [14] various model-based ATR classifiers are examined to investigate the utility of model-catalog compression realized via signal vector quantization and feature extraction. The Air Force Research Labs in [4,6] are developing a next-generation SAR ATR system based on model-based vision technology.…”

Section: Literature Survey Of Target Classification Recognition Andmentioning

confidence: 99%

Automated Target Recognition Using the Karhunen–Loéve Transform with Invariance

Suvorova¹,

Schroeder²

2002

Digital Signal Processing

View full text Add to dashboard Cite

Section: Literature Survey Of Target Classification Recognition Andmentioning

confidence: 99%

Automated Target Recognition Using the Karhunen–Loéve Transform with Invariance

Suvorova¹,

Schroeder²

2002

Digital Signal Processing

View full text Add to dashboard Cite

“…Scattering center extraction (SCE) is the main concern in the field of radar signal processing because dominant scatterers on a target can provide rich description of the target's scattering mechanism even with their low‐dimensional properties. Therefore, locations and amplitudes of the scattering centers are frequently used as promising features in target recognition and classification, together with the conventional radar signatures, such as range profiles (RPs) and radar images . As a traditional approach for SCE, we can use the well‐known discrete spectral estimation (DSE) techniques , such as the Yule–Walker (YW) method based on an autoregressive moving average (ARMA) model, min‐norm method, root multiple signal classification (Root‐MUSIC), and the estimation of signal parameters via rotational invariance (ESPRIT).…”

Section: Introductionmentioning

confidence: 99%

Compressive sensing-based algorithm for one-dimensional scattering center extraction

Bae

Kang

Yang

et al. 2016

Microw. Opt. Technol. Lett.

View full text Add to dashboard Cite

This article proposes a one‐dimensional scattering center extraction (SCE) method that includes mainly two steps: coarse estimation of scattering centers using the iteratively reweighted least square (IRLS) coupled with a peak‐finding algorithm and fine estimation of scattering centers using the orthogonal matching pursuit (OMP) procedure from the adaptively sampled Fourier dictionary. Consequently, the proposed method can achieve high SCE accuracy regardless of whether data are missing in the collected radar‐cross‐section (RCS) dataset or not. © 2016 Wiley Periodicals, Inc. Microwave Opt Technol Lett 58:1408–1415, 2016

show abstract

“…These 2-D scattering centers correspond to the points radiating high-energy radar cross-section (RCS) on a target. This scattering center concept can provide a concise and physical description for scattering mechanisms of an object, and therefore it has been extensively used in SAR target feature extraction [4] and automatic target recognition (ATR) [5]- [7]. In addition, it has been applied to investigate target diagnostics [8] and to compress the RCS database for a complex target [9].…”

Section: Introductionmentioning

confidence: 99%

Two-dimensional scattering center extraction based on multiple elastic modules network

Kim

2003

IEEE Trans. Antennas Propagat.

View full text Add to dashboard Cite

The concept of scattering centers on a target is commonly used for radar signature modeling and data compression, as well as target recognition. In particular, two-dimensional (2-D) scattering centers are useful features in automatic target recognition, which uses a synthetic aperture radar system, because they are directly related to physical scattering mechanisms and also have small dimensionality. In this paper, we propose a new technique for estimating 2-D scattering centers using radar data in the frequency-aspect domain. The technique first estimates one-dimensional scattering centers at several aspects, and the multiple elastic modules network optimization is exploited to find 2-D locations and amplitudes of the target's scattering centers. Experimental results illustrate that the proposed method is efficient not only for estimating 2-D scattering centers on the target but also in computation.

show abstract

Efficient ATR using compression

Cited by 9 publications

References 8 publications

Automated Target Recognition Using the Karhunen–Loéve Transform with Invariance

Automated Target Recognition Using the Karhunen–Loéve Transform with Invariance

Compressive sensing-based algorithm for one-dimensional scattering center extraction

Two-dimensional scattering center extraction based on multiple elastic modules network

Contact Info

Product

Resources

About