The traditional generative adversarial network (GAN) is widely used in the field of synthetic aperture radar (SAR) ground target image generation. However, GAN has the problem of unstable gradient update, which can easily cause the loss of image feature information, resulting in a low similarity between the generated image and the real image. To solve these problems, we propose an improved Wasserstein GAN with gradient penalty (IWGAN-GP), which introduces dense connection in the generator, integrates feature information at different levels to achieve feature reuse, and alleviates the gradient disappearance problem caused by deep networks. Moreover, by introducing the squeeze-and-excitation (SE) module into the densely connected network, on the basis of considering high-level semantic information and low-level geometric texture details, the optimal fusion weights of each channel can be automatically obtained to fully explore important target information in SAR images. IWGAN-GP alleviates the gradient disappearance caused by the depth of the network, strengthens feature propagation, and realizes feature reuse. It can automatically obtain the optimal fusion weight of each channel and improve the similarity between the generated image and the real image. The superiority of IWGAN-GP is verified on the datasets of MSTAR.
We propose a polarimetric synthetic aperture radar (PolSAR) image terrain classification algorithm based on complete local binary patterns (CLBP) feature integrated convolutional neural network (CNN) (CLBP-CNN). Traditional CNN has a powerful high-level deep features extraction ability, which can effectively improve the terrain classification accuracy in PolSAR images. However, most traditional CNN-based methods only focus on the high-level deep feature extraction of the synthetic aperture radar (SAR) terrains; they ignore the low-level texture features, resulting in incomplete feature representation and poor classification accuracy. In fact, low-level texture features also play an important role in PolSAR terrain classification. To solve the problem that traditional CNN-based terrain classification methods easily lose the low-level texture features in the process of feature extraction, the proposed method uses the CLBP descriptor to extract multi-level texture features under different receptive fields, and it adaptively combines the high-level deep features and the low-level texture features for better SAR terrain feature description. CLBP-CNN greatly alleviates the shortcomings of traditional CNN in missing the low-level texture features; it improves the feature representation completeness, so it can achieve better terrain classification results. The superiority of CLBP-CNN is verified on the data sets of Flevoland, San Francisco, and Oberpfaffenhofen.
Since sea clutter samples are often contaminated by high-intensity outliers, target detection in nonhomogeneous sea clutter environments is challenging. An adaptively truncated clutter-statistics-based variability index constant false-alarm-rate (TSVI-CFAR) detector of Gaussian clutter in synthetic aperture radar (SAR) imagery is proposed. The proposed method is designed to improve the CFAR detection performance in a heterogeneous multitarget environment. TSVI-CFAR consists of three stages, i.e., clutter truncation, statistical parameter estimation, and CFAR detection. In the clutter truncation stage, the high-intensity outliers in the background window are eliminated through an adaptive threshold-based clutter truncation method. In the statistical parameter estimation stage, the parameters can be accurately estimated through the maximum-likelihood estimator. In the detection stage, the clutter background is categorized using the adaptively truncated clutter. Different types of CFAR detection methods are applied to the pixels under test of the categorized backgrounds. TSVI-CFAR has a higher detection rate and a low observed false alarm rate. The effectiveness of the proposed algorithm is demonstrated using Gaofen-3 SAR data and Envisat-ASAR data.
The mechanism of speckle noise in synthetic aperture radar (SAR) images and its characteristics are analyzed. Combining the advantages of the traditional bilateral filter (BF) and alpha-trimmed median filter, a truncated-statistics-based bilateral filter (TS-BF) in SAR imagery is proposed. The despeckling method is based on the BF methodology, where the similarities of gray levels and spatial location of the neighboring pixels are exploited. However, traditional BF is not effective to reduce the strong speckle, which is often presented as impulse noise. The proposed TS-BF filtering method designs an adaptive truncation method to properly select the samples in the local reference window, where the mean and standard deviation of all the samples are estimated, and the background types of the current pixel-for-filtering are categorized. Finally, the samples of the local reference window are truncated with different levels according to different background types, and BF is applied using the truncated samples. TS-BF can effectively preserve the edge and texture information of the image while smoothing the speckle noise; it has a great application value. The experimental results show the effectiveness of the proposed algorithm through subjective and objective analyses.
An improved bilateral filter with adaptive parameters estimation in space domain and polarimetric domain for polarimetric synthetic aperture radar (PolSAR) image despeckling, named PolSAR adaptive bilateral filtering (PABF), is proposed. On one hand, PABF sets the spatial parameter adaptively according to the local coefficient of variation. On the other hand, the polarimetric parameter is adjusted adaptively on the basis of the noise variance estimated from the convolution between the intensity image and Laplacian template. The experiments performed on simulated and real PolSAR data show that PABF effectively suppresses speckles while maintaining important details of images.
The problem of change detection in bitemporal synthetic aperture radar (SAR) images is studied. Motivated by utilizing nondense neighborhoods around pixels to detect the change level, a pointwise change detection approach is developed by employing a bilaterally weighted graph model and an irregular Markov random field (I-MRF). First, keypoints with local maximum intensity are extracted from one of the bitemporal images to describe the textural information of the images. Then, two bilaterally weighted graphs with the same topology are constructed for the bitemporal images using the keypoints, respectively. They utilize both the spatial structural and intensity information to provide good performance for feature-based change detection. Next, a change measure function is designed to evaluate the similarity between the graphs, and then the nondense difference image (NDI) is generated. Finally, an I-MRF with a generalized neighborhood system is proposed to classify the discrete keypoints on the NDI. Experiments on real SAR images show that the proposed NDI improves separability between changed and unchanged areas, and I-MRF provides high accuracy and strong noise immunity for change detection tasks with noise-contaminated SAR images. On the whole, the proposed approach is a good candidate for SAR image change detection.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.