Deep Multi-Scale Recurrent Network for Synthetic Aperture Radar Images Despeckling

Abstract

For the existence of speckles, many standard optical image processing methods, such as classification, segmentation, and registration, are restricted to synthetic aperture radar (SAR) images. In this work, an end-to-end deep multi-scale recurrent network (MSR-net) for SAR image despeckling is proposed. The multi-scale recurrent and weights sharing strategies are introduced to increase network capacity without multiplying the number of weights parameters. A convolutional long short-term memory (convLSTM) unit is embedded to capture useful information and helps with despeckling across scales. Meanwhile, the sub-pixel unit is utilized to improve the network efficiency. Besides, two criteria, edge feature keep ratio (EFKR) and feature point keep ratio (FPKR), are proposed to evaluate the performance of despeckling capacity for SAR, which can assess the retention ability of the despeckling algorithm to edge and feature information more effectively. Experimental results show that our proposed network can remove speckle noise while preserving the edge and texture information of images with low computational costs, especially in the low signal noise ratio scenarios. The peak signal to noise ratio (PSNR) of MSR-net can outperform traditional despeckling methods SAR-BM3D (Block-Matching and 3D filtering) by more than 2 dB for the simulated image. Furthermore, the adaptability of optical image processing methods to real SAR images can be enhanced after despeckling. multiple segments. The incoherent sub-views are then superimposed to obtain the high signal-to-noise ratio (SNR) images [8]. However, multi-look processing reduces the utilization of Doppler bandwidth, resulting in a decrease of the spatial resolution of the imaging results, which cannot meet the requirements of high resolution [9].The filtering methods are mainly divided into three categories: the spatial filtering method, the transform domain filtering method, and the non-local mean filtering method. Median filtering and mean filtering are the earliest spatial filtering methods of traditional digital image processing. Although these two methods can suppress speckles to a certain extent, it leads to image blurring and objects edge information loss. Afterward, Lee filter [10], Frost filter [11], and Kuan filter [12] are designed for speckles suppression of SAR images. Based on the coherent speckle multiplier model, Lee filter selects a fixed local window in the image, assuming that the prior mean and variance can be calculated by the local region [10]. This method has a small amount of computation, but the selection of local window size has a great influence on the result, and the details and edge information of the image may be lost [13]. Frost filter assumes that the SAR image is a stationary random process and coherent spot noise is multiplying noise, and uses the least mean square error criterion to estimate the real image [11]. For the reason that the actual SAR image does not fully meet the hypothesis, the SAR image processed by this method will have blurre...

Change Detection from SAR Images Based on Convolutional Neural Networks Guided by Saliency Enhancement

“…To cope with the speckle noise in SAR images, many noise reduction algorithms have been proposed in the past few years. The classical methods are probabilistic-patchbased (PPB) filter [8], speckle reducing anisotropic diffusion (SRAD) [9], non-local means filter [10,11], total variation model [12], block-matching 3D filtering [13], deep multi-scale recurrent network [14], multilook and refined Lee filtering [15], etc. Zheng et al [16] introduced a SAR change detection method based on PPB filter and k-means clustering model where the PPB filter is used to suppress the speckle noise, and the two difference images are generated by subtraction and log-ratio operators, respectively; then the k-means clustering model is performed on the combined difference image to obtain the final change map.…”

Improved Sensors Based on Scheimpflug Conditions and Multi-Focal Constraints

“…Take a series of images including three images for example. When we get plenty of feature points in three images, we can get initial matching pointpair based on generic algorithms such as multi-scale edge matching algorithm, shape based matching algorithm and so on [13], [14]. Then we can deduce initial trifocal tensor from Eq.…”

A Robust InSAR Phase Unwrapping Method via Phase Gradient Estimation Network

“…In the traditional LS method, estimating the phase gradient according to the phase continuity assumption (PGE-PCA) is an essential step. Recent studies [28][29][30][31][32] have indicated that the encoder-decoder architecture based on deep convolutional neural networks (DCNN) can learn the global features from a large number of input images with different levels of noise or other disturbances, which is useful for obtaining the robust phase gradient from noisy wrapped phase images.…”