&lt;title&gt;Moving and stationary target acquisition and recognition (MSTAR) model-based automatic target recognition: search technology for a robust ATR&lt;/title&gt;

Diemunsch, Joseph R.; Wissinger, John

doi:10.1117/12.321851

Cited by 90 publications

(42 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, magnitude SAR image dataset from the Moving and Stationary Target Acquisition and Recognition (MSTAR) program [28] is utilized to evaluate our proposed method. MSTAR program is to develop the next generation SAR ATR, and has conducted a significant quantity of SAR images to support the development and testing of the ATR algorithm.…”

Section: Experiments and Resultsmentioning

confidence: 99%

SAR Imagery Feature Extraction Using 2DPCA-Based Two-Dimensional Neighborhood Virtual Points Discriminant Embedding

Pei

Huang

Huo

et al. 2016

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) is an important microwave sensor that is capable of high-resolution imaging. Extracting valuable features from the SAR target imagery is one of crucial issues in SAR automatic target recognition (ATR). In this paper, we propose a new feature extraction method named 2-D principalcomponent-analysis-based 2-D neighborhood virtual points discriminant embedding (2DPCA-based 2DNVPDE) for SAR ATR. The SAR imagery is projected into the feature space by 2DPCA and 2DNVPDE in this approach. 2DPCA is able to preserve the global spatial structure of the original imagery, while 2DNVPDE establishes the spatial relationships of the neighborhoods to find the classification information from the neighborhoods of the samples. Hence, our method can extract powerful recognition information and represent the original image in low dimensions. Based on the MSTAR dataset, the experimental results show that the proposed method is able to achieve a higher recognition rate with a lower feature dimension over some existing SAR imagery feature extraction methods. Besides, it indicates that our method has a significant advantage in recognition performance and a lower sensitivity in statistical standpoint.Index Terms-Automatic target recognition (ATR), feature extraction, synthetic aperture radar (SAR).

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

SAR Imagery Feature Extraction Using 2DPCA-Based Two-Dimensional Neighborhood Virtual Points Discriminant Embedding

Pei

Huang

Huo

et al. 2016

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Then it may be a bridge between the electromagnetic simulation software and the target signature in the model-based automatic target recognition (ATR) application [17], [18]. The model-based ATR has many advantages over the templet-based methods, e.g., smaller memory space, more flexibility under extended operation conditions (EOC), and better stability [17]. A good global scattering center model extracted beforehand may replace the electromagnetic simulation software in producing the target signature in real time, which will greatly release the demand for a high speed electromagnetic simulation code or even replace it by measurements of better precision.…”

Section: Discussionmentioning

confidence: 99%

“…This model can be used to reconstruct target signatures such as 1D and 2D radar images. Then it may be a bridge between the electromagnetic simulation software and the target signature in the model-based automatic target recognition (ATR) application [17], [18]. The model-based ATR has many advantages over the templet-based methods, e.g., smaller memory space, more flexibility under extended operation conditions (EOC), and better stability [17].…”

Section: Discussionmentioning

confidence: 99%

Global Scattering Center Model Extraction of Radar Targets Based on Wideband Measurements

Zhou

Zhao

Shi

et al. 2008

IEEE Trans. Antennas Propagat.

View full text Add to dashboard Cite

The scattering center model represents the scattering characteristics of radar targets at high frequencies by a set of point scatterers. Such a model is useful in scattering analysis, data compression and target recognition. We propose a methodology to extract the scattering center model from wideband measurements at sparsely distributed aspect angles. It exploits the regular variation in the 1D projective location and the slow variation in the scattering coefficient of stable scattering centers at adjacent aspects, and greatly cuts down the original data amount compared to other methods. The extracted model contains the stable scattering centers of the target and is effective in a large angular extent. It can be used to reconstruct the target signatures such as RCS data and radar images at any aspect in this angular extent and at any frequency in or near the original measuring band. Examples using both simple and complex targets demonstrate the validity of this technique.

show abstract

“…There are also statisticalmodel-based classifiers where the features of different targets are modeled as statistical processes with different parameters [6]- [8]. The ATR system developed in the MSTAR program uses a typical model-based classifier in which scattering centers extracted from 3-D CAD models drive the prediction of SAR image features [9]- [11]. In recent years, there has been a surge of interest in model-based ATR systems [1], [9]- [17].…”

mentioning

confidence: 99%

Automatic Target Recognition of SAR Images Based on Global Scattering Center Model

Zhou

Shi

Cheng

et al. 2011

IEEE Trans. Geosci. Remote Sensing

217

View full text Add to dashboard Cite

This paper proposes a synthetic aperture radar (SAR) automatic target recognition approach based on a global scattering center model. The scattering center model is established offline using range profiles at multiple viewing angles, so the original data amount is much less than that required for establishing SAR image templates. Scattering center features at different target poses can be conveniently predicted by this model. Moreover, the model can be modified to predict features for various target configurations. For the SAR image to be classified, regional features in different levels are extracted by thresholding and morphological operations. The regional features will be matched to the predicted scattering center features of different targets to arrive at a decision. This region-to-point matching is much easier to implement and is less sensitive to nonideal factors such as noise and pose estimation error than point-to-point matching. A matching scheme going through from coarse to fine regional features in the inner cycle and going through different pose hypotheses in the outer cycle is designed to improve the efficiency and robustness of the classifier. Experiments using both data predicted by a highfrequency electromagnetic (EM) code and data measured in the MSTAR program verify the validity of the method.Index Terms-Ground target, model based, scattering center, synthetic aperture radar (SAR) automatic target recognition (ATR).

show abstract

<title>Moving and stationary target acquisition and recognition (MSTAR) model-based automatic target recognition: search technology for a robust ATR</title>

Cited by 90 publications

References 0 publications

SAR Imagery Feature Extraction Using 2DPCA-Based Two-Dimensional Neighborhood Virtual Points Discriminant Embedding

SAR Imagery Feature Extraction Using 2DPCA-Based Two-Dimensional Neighborhood Virtual Points Discriminant Embedding

Global Scattering Center Model Extraction of Radar Targets Based on Wideband Measurements

Automatic Target Recognition of SAR Images Based on Global Scattering Center Model

Contact Info

Product

Resources

About