The Generalized Gamma-DBN for High-Resolution SAR Image Classification

Zhao, Zhiqiang; Guo, Lei; Jia, Meng; Wang, Lei

doi:10.3390/rs10060878

Cited by 13 publications

(11 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, the available literature has been carried out in-depth research in the field of SAR image ATR, and made great progress [6], [7]. Moreover, SAR image is further combined with optical image in order to extract additional information and achieve better results [8], [9], [10].…”

Section: A Problem Statementmentioning

confidence: 99%

A Deformation Robust ISAR Image Satellite Target Recognition Method Based on PT-CCNN

et al. 2021

View full text Add to dashboard Cite

To tackle the inherent unknown deformation (e.g., translation, rotation and scaling) of the inverse synthetic aperture radar (ISAR) images, a deep polar transformer-circular convolutional neural network, i.e., PT-CCNN, is proposed to achieve deformation robust ISAR image automatic target recognition (ATR) in this paper. Inspired by human visual system and canonical coordinate of Lie-groups, we adopt a polar transformer module to transform the deformation ISAR images to the log-polar representations, before which a conventional convolutional neural network (CNN) is utilized to predict the origin of log-polar transformation. The above techniques make the proposed network invariant to translation, and equivariant to rotation and scaling. On this basis, for the log-polar representations with wrap-around structure, a circular convolutional neural network (CCNN) is further applied to extract more effective and highly discriminative features and improve recognition accuracy. The proposed network is end-to-end trainable with a classification loss, and could extract deformation-robust and essential features automatically. For multiple practical ISAR image datasets of six satellites, the performance testing and comparison experiments demonstrate that the techniques utilized in PT-CCNN are effective, and our proposed network achieve higher recognition accuracy than those previous common methods based on deep learning. For instance, our proposed PT-CCNN beats traditional CNN on rotation, scaling and practical deformation datasets by 24.5-49.3%, 9.0-40.8% and 22.3-26.7%. And it also outperforms the polar CNN without using the above techniques on rotation, scaling and practical deformation datasets by 9.2-53.7%, 5.2-54.6% and 9.0-49.9%. Additionally, the presented visualization results show the abilities and advantages of our method in terms of handling image deformation and extracting effective features.INDEX TERMS Automatic target recognition (ATR), inverse synthetic aperture radar (ISAR), deep convolutional neural network (DCNN), image deformation, log-polar transformation.

show abstract

Section: A Problem Statementmentioning

confidence: 99%

A Deformation Robust ISAR Image Satellite Target Recognition Method Based on PT-CCNN

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, because of the existence of speckle noise, probability distributions offer limited accuracy in describing the change information between bitemporal SAR images. Thus, utilizing the high representation learning capacity of deep neural network models, a gΓB-RBM was used to learn the statistical dependencies between the visible variables and the hidden nodes for modeling the difference images [19].…”

Section: Classification By a Generalized Gamma Deep Belief Networkmentioning

confidence: 99%

Change Detection in Synthetic Aperture Radar Images Based on a Generalized Gamma Deep Belief Networks

Jia

Zhao

2021

Sensors

Self Cite

View full text Add to dashboard Cite

Change detection from synthetic aperture radar (SAR) images is of great significance for natural environmental protection and human societal activity, which can be regarded as the process of assigning a class label (changed or unchanged) to each of the image pixels. This paper presents a novel classification technique to address the SAR change-detection task that employs a generalized Gamma deep belief network (gΓ-DBN) to learn features from difference images. We aim to develop a robust change detection method that can adapt to different types of scenarios for bitemporal co-registered Yellow River SAR image data set. This data set characterized by different looks, which means that the two images are affected by different levels of speckle. Widely used probability distributions offer limited accuracy for describing the opposite class pixels of difference images, making change detection entail greater difficulties. To address the issue, first, a gΓ-DBN can be constructed to extract the hierarchical features from raw data and fit the distribution of the difference images by means of a generalized Gamma distribution. Next, we propose learning the stacked spatial and temporal information extracted from various difference images by the gΓ-DBN. Consequently, a joint high-level representation can be effectively learned for the final change map. The visual and quantitative analysis results obtained on the Yellow River SAR image data set demonstrate the effectiveness and robustness of the proposed method.

show abstract

“…which is the gamma distribution, and hence p(x i |x j ∀j = i) = G(x i ; α i , β i ). 5 Note that a variant of gamma-Bernoulli RBM has been proposed for synthetic aperture radar image classification [33]. Its focus is not on handling data in logarithmic domain, and therefore it is essentially different from the proposed RBM that equally treats linear and logarithmic domains.…”

Section: Proposed Gamma-bernoulli Rbmmentioning

confidence: 99%

Gamma Boltzmann Machine for Audio Modeling

Nakashika

Yatabe

2021

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

This paper presents an energy-based probabilistic model that handles nonnegative data in consideration of both linear and logarithmic scales. In audio applications, magnitude of time-frequency representation, including spectrogram, is regarded as one of the most important features. Such magnitudebased features have been extensively utilized in learning-based audio processing. Since a logarithmic scale is important in terms of auditory perception, the features are usually computed with a logarithmic function. That is, a logarithmic function is applied within the computation of features so that a learning machine does not have to explicitly model the logarithmic scale. We think in a different way and propose a restricted Boltzmann machine (RBM) that simultaneously models linear-and logmagnitude spectra. RBM is a stochastic neural network that can discover data representations without supervision. To manage both linear and logarithmic scales, we define an energy function based on both scales. This energy function results in a conditional distribution (of the observable data, given hidden units) that is written as the gamma distribution, and hence the proposed RBM is termed gamma-Bernoulli RBM. The proposed gamma-Bernoulli RBM was compared to the ordinary Gaussian-Bernoulli RBM by speech representation experiments. Both objective and subjective evaluations illustrated the advantage of the proposed model.

show abstract

The Generalized Gamma-DBN for High-Resolution SAR Image Classification

Cited by 13 publications

References 57 publications

A Deformation Robust ISAR Image Satellite Target Recognition Method Based on PT-CCNN

A Deformation Robust ISAR Image Satellite Target Recognition Method Based on PT-CCNN

Change Detection in Synthetic Aperture Radar Images Based on a Generalized Gamma Deep Belief Networks

Gamma Boltzmann Machine for Audio Modeling

Contact Info

Product

Resources

About