A SAR dataset for ATR Development: the Synthetic and Measured Paired Labeled Experiment (SAMPLE)

Lewis, Benjamin P.; Scarnati, Theresa; Sudkamp, Elizabeth; Nehrbass, John; Rosencrantz, Stephen; Zelnio, Edmund G.

doi:10.1117/12.2523460

Cited by 96 publications

(126 citation statements)

References 19 publications

Supporting

Mentioning

125

Contrasting

Order By: Relevance

“…We calculated the MSSIM index and the PSNR value by comparing the simulated SAR images and the MSTAR images to compare the similarity between the simulated and measured images. In the simulation, we used parameters identical to those of the MSTAR measurement parameters (Table VII) [42]. The same numbers of simulated and measured SAR images obtained from the same aspect angles and depression angles were used in each case when computing the MSSIM values corresponding to each model.…”

Section: Resultsmentioning

confidence: 99%

“…This is presumably why it is occasionally adopted for the evaluation of simulated target SAR images [32] or for target recognition [36]. One study used other similarity measures such as mean absolute deviation, root mean square distance, and normalized cross correlation using the simulated and measured paired and labeled experiment dataset as a companion to the MSTAR dataset; however, the experiments were constrained and did not suggest the relevance to the recognition rate [34], [42].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

SAR Image Generation of Ground Targets for Automatic Target Recognition Using Indirect Information

Yoo

Kim

2021

IEEE Access

View full text Add to dashboard Cite

The effectiveness of using the simulated synthetic aperture radar (SAR) images of military targets in databases for automatic target recognition (ATR) is widely known. However, for simulated target images to be useful, they must be sufficiently similar to measured images; otherwise, they can degrade ATR performance. Two factors affect the quality of simulated SAR images: precision of the associated computer-aided design (CAD) model of the target and the accuracy and speed of the numerical techniques used to solve the electromagnetic problems in SAR image generation. In this study, a method for the 3D CAD modeling of the target is proposed; this method can be used when direct access to the target is not feasible and only indirect information is available. Further, a bistatic image formation concept based on the shooting-and-bouncing-ray technique is adopted; this concept helps achieve an accuracy comparable to that of the monostatic method. Moreover, it helps achieve a highly enhanced computation speed. In combination, these proposals provide an efficient and fast method to generate a database of simulated SAR images that can effectively support ATR activities. We demonstrate the effectiveness of the proposed method by comparing the simulated SAR images with the measured ones using structural similarity as a similarity measure; further, we evaluate the recognition rate obtained with the simulated images. We show that the used similarity measure bears a strong relation with the recognition rate, which is an aspect that may further contribute to considerable time savings when validating and refining simulated image databases.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

SAR Image Generation of Ground Targets for Automatic Target Recognition Using Indirect Information

Yoo

Kim

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Finally, we consider transfer learning with the Synthetic and Measured Paired and Labeled (SAMPLE) database of computer-simulated and real-world SAR images [13]. The publiclyavailable SAMPLE database consists of 1366 paired images of 10 different vehicles, each pair consisting of a real-world SAR image and a corresponding computer-simulated SAR image; see Figure 5 for an illustration.…”

Section: Transfer Learning With the Sample Datasetmentioning

confidence: 99%

“…For each technique, if test images cannot be represented in a feature space that has been determined from the training set, then classification accuracy is poor.In applications such as synthetic aperture radar (SAR) automatic target recognition (ATR), it is infeasible to collect the volume of data necessary to naively train high-accuracy classification networks. Additionally, due to varying operating conditions, the features measured in SAR imagery are different from those extracted from electro-optical (EO) imagery [13]. As such, off-the-shelf networks that have been pre-trained on the popular EObased ImageNet [3] or CIFAR-10 [8] datasets are insufficient for performing accurate ATR tasks in different imaging domains.…”

mentioning

confidence: 99%

Matching Component Analysis for Transfer Learning

Clum¹,

Mixon²,

Scarnati³

2020

SIAM Journal on Mathematics of Data Science

Self Cite

View full text Add to dashboard Cite

We introduce a new Procrustes-type method called matching component analysis to isolate components in data for transfer learning. Our theoretical results describe the sample complexity of this method, and we demonstrate through numerical experiments that our approach is indeed well suited for transfer learning. IntroductionMany state-of-the-art classification algorithms require a large training set that is statistically similar to the test set. For example, deep learning-based approaches require a large number of representative samples in order to find near-optimal network weights and biases [4,9]. Similarly, template-based approaches require large dictionaries of training images so that each test image can be represented by an element of the dictionary [21,26,17,6]. For each technique, if test images cannot be represented in a feature space that has been determined from the training set, then classification accuracy is poor.In applications such as synthetic aperture radar (SAR) automatic target recognition (ATR), it is infeasible to collect the volume of data necessary to naively train high-accuracy classification networks. Additionally, due to varying operating conditions, the features measured in SAR imagery are different from those extracted from electro-optical (EO) imagery [13]. As such, off-the-shelf networks that have been pre-trained on the popular EObased ImageNet [3] or CIFAR-10 [8] datasets are insufficient for performing accurate ATR tasks in different imaging domains. In fact, recent work has demonstrated that pre-trained networks fail to effectively generalize to random perturbations on test sets [19,18]. To build more representative training sets, additional data are often generated using modeling and simulation software. However, due to various model errors, simulated data often misrepresent the real-world scattering observed in measured imagery. Thus, even though it is possible to augment training sets with a large amount of simulated data, the inherent differences in sensor modalities and data representations make modifying classification networks a non-trivial task [20].In this paper, we introduce matching component analysis (MCA) to help remedy this situation. Given a small number of images from the training domain and matching *

show abstract

“…For the next transfer task, we consider the synthetic-to-measured transfer task where our source domain consists of 10 classes of synthetic SAR images from the SAMPLE dataset 33 and our target domain consists of corresponding measured SAR images. The results are shown in Table 7.…”

Section: Experiments 4: Synthetic To Measured Sarmentioning

confidence: 99%

Flexible deep transfer learning by separate feature embeddings and manifold alignment

Rivera

Klipfel

Weeks

2020

Automatic Target Recognition XXX

View full text Add to dashboard Cite

Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness. Unfortunately, algorithms trained on existing labeled datasets do not directly generalize to new data because the data distributions do not match. Transfer learning (TL) or domain adaptation (DA) methods have established the groundwork for transferring knowledge from existing labeled source data to new unlabeled target datasets. However, current DA approaches assume similar source and target feature spaces and suffer in the case of massive domain shifts or changes in the feature space. Existing methods assume the data are either the same modality, or can be aligned to a common feature space. Therefore, most methods are not designed to support a fundamental domain change such as visual to auditory data. We propose a novel deep learning framework that overcomes this limitation by learning separate feature extractions for each domain while minimizing the distance between the domains in a latent lower-dimensional space. The alignment is achieved by considering the data manifold along with an adversarial training procedure. We demonstrate the effectiveness of the approach versus traditional methods with several ablation experiments on synthetic, measured, and satellite image datasets. We also provide practical guidelines for training the network while overcoming vanishing gradients which inhibit learning in some adversarial training settings.

show abstract

A SAR dataset for ATR Development: the Synthetic and Measured Paired Labeled Experiment (SAMPLE)

Cited by 96 publications

References 19 publications

SAR Image Generation of Ground Targets for Automatic Target Recognition Using Indirect Information

SAR Image Generation of Ground Targets for Automatic Target Recognition Using Indirect Information

Matching Component Analysis for Transfer Learning

Flexible deep transfer learning by separate feature embeddings and manifold alignment

Contact Info

Product

Resources

About