Reliable target feature extraction and classification using potential target information

Doo, Seung Ho; Smith, Gerald Birney; Baker, Chris

doi:10.1109/radar.2015.7131073

Cited by 12 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The identification and characterization results, with 6.55% and 6.89% of improvements in performance, respectively, confirm the capability of the Krawtchouk moments to represent with higher fidelity smaller details of the targets. Analyzing the performance in the best case (190 brightest scatterers case) of the approach presented in [5] that is reported in Fig. 2(b), it is shown that the brightest-scatterer-based approach provides 96.83%, 93.81%, and 83.67% of correct target recognition, identification, and characterization, respectively.…”

Section: Performance Analysis On the Mstar Datasetmentioning

confidence: 94%

“…Moreover, different targets have different 2. Performance in terms of normalized correct number of recognition, identification, and characterization on the MSTAR dataset for (a) the proposed algorithm using the Krawtchouk moments versus the algorithm introduced in [18] using the pseudo-Zernike moments and (b) compared with the performance achievable using the approach in [5] for various number of brightest scatterers selected.…”

Section: Performance Analysis On the Mstar Datasetmentioning

confidence: 99%

“…In order to investigate the capabilities and the robustness of the proposed approach, the results of the new algorithm are compared to those obtained using the pseudo-Zernike moments [18] and the approach proposed in [5]. In the experiments, a k-NN classifier with k = 3 and p 1 = p 2 = 0.5 for the computation of the Krawtchouk polynomials have been used.…”

Section: Performance Analysis On the Mstar Datasetmentioning

confidence: 99%

“…The main drawback of the algorithm is the fact that it relies on a single metric (MSE), meaning that an accurate knowledge of the target models is required; otherwise, the algorithm would incur in misclassification. A robust algorithm has been proposed in [5], in which an increased number of scattering centres are selected while retaining low computational complexity. The approach uses a relatively large number of scatterers with a variability reduction technique.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Target Recognition of Military Vehicles With Krawtchouk Moments

Clemente

Pallotta

Gaglione

et al. 2017

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

The challenge of automatic target recognition of military targets within a synthetic aperture radar scene is addressed in this paper. The proposed approach exploits the discrete-defined Krawtchouk moments, which are able to represent a detected extended target with few features, allowing its characterization. The proposed algorithm provides robust performance for target recognition, identification, and characterization, with high reliability in the presence of noise and reduced sensitivity to discretization errors. The effectiveness of the proposed approach is demonstrated using the MSTAR dataset.

show abstract

Section: Performance Analysis On the Mstar Datasetmentioning

confidence: 94%

Section: Performance Analysis On the Mstar Datasetmentioning

confidence: 99%

Section: Performance Analysis On the Mstar Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Target Recognition of Military Vehicles With Krawtchouk Moments

Clemente

Pallotta

Gaglione

et al. 2017

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

show abstract

“…Some novel methods and systems have been proposed in recent years, which have achieved considerable classification or recognition results [3]- [5]. Generally, SAR ATR [6]- [9] has the capabilities of locating the region of interest (ROI) containing the potential targets and recognizing target signatures in SAR data by computer processing.…”

Section: Introductionmentioning

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

Data Augmentation Based on Attributed Scattering Centers to Train Robust CNN for SAR ATR

Liu

2019

IEEE Access

View full text Add to dashboard Cite

Driven by the good classification performance of the convolutional neural network (CNN), this study proposes a CNN-based synthetic aperture radar (SAR) target recognition method. In this paper, a novel data augmentation algorithm is proposed via target reconstruction based on attributed scattering centers (ASC). The ASCs reflect the electromagnetic phenomenon of SAR targets, which can be used to reconstruct the target's characteristics. The sparse representation (SR) algorithm is first employed to extract the ASCs from a single SAR image. Afterward, some of the extracted ASCs are selected to reconstruct the target's image. By repeating the process, many new images can be generated as available training samples. In the classification stage, a CNN architecture is designed and trained by the augmented samples. For the test sample, it is also reconstructed using all the extracted ASCs thus relieving the interferences caused by the clutters or noises in the background. Finally, the reconstructed image from the test sample is classified based on the trained CNN. The reconstructed image from the ASCs can reduce the clutters and noises thus enhancing the image quality. More importantly, the generated new training samples could cover more operating conditions, which may probably occur in SAR target recognition. Therefore, the trained CNN can work more robustly in different situations. In the experiments, the moving and stationary target acquisition and recognition (MSTAR) dataset is used to evaluate the performance of the proposed approach. This method could classify the 10 classes of targets with an accuracy of 99.48% under the standard operating condition (SOC). For the extended operating conditions like configuration variance, depression angle variance, noise corruption, and partial occlusion, the proposed method also displays superior performance over some baseline algorithms drawn from state-of-the-art literature. INDEX TERMS Convolutional neural network (CNN), synthetic aperture radar (SAR), target recognition, attributed scattering center (ASC), data augmentation.

show abstract

Reliable target feature extraction and classification using potential target information

Cited by 12 publications

References 8 publications

Automatic Target Recognition of Military Vehicles With Krawtchouk Moments

Automatic Target Recognition of Military Vehicles With Krawtchouk Moments

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

Data Augmentation Based on Attributed Scattering Centers to Train Robust CNN for SAR ATR

Contact Info

Product

Resources

About