SAR image despeckling with a multilayer perceptron neural network

Speckle noise in synthetic-aperture radar (SAR) images severely hinders remote sensing applications; therefore, the appropriate removal of speckle noise is crucial. This paper elaborates on the multilayer perceptron (MLP) neural-network model for SAR image despeckling by using a time series of SAR images. Unlike other filtering methods that use only a single radar intensity image to derive their parameters and filter that single image, this method can be trained using archived images over an area of interest to self-learn the intensity characteristics of image patches and then adaptively determine the weights and thresholds by using a neural network for image despeckling. Several hidden layers are designed for feedforward network training, and back-propagation stochastic gradient descent is adopted to reduce the error between the target output and neural-network output. The parameters in the network are automatically updated in the training process. The greatest advantage of MLP is that once the despeckling parameters are determined, they can be used to process not only new images in the same area but also images in completely different locations. Tests with images from TerraSAR-X in selected areas indicated that MLP shows satisfactory performance with respect to noise reduction and edge preservation. The overall image quality obtained using MLP was markedly higher than that obtained using numerous other filters. In comparison with other recently developed filters, this method yields a slightly higher image quality, and it demonstrates the powerful capabilities of computer learning using SAR images, which indicate the promising prospect of applying MLP to SAR image despeckling.     

衰减夹层GPR模拟的时频域全局反射误差

全局反射误差分析是深入研究探地雷达（GPR）吸收边界条件吸收效率的有力工具.基于常规完全匹配层（PML）的标准交错网格有限差分算法必须满足严格的CFL条件限制,即在单位时间步长内,不容许电磁波传播的距离超过单元网格尺寸.为了提高主区域所有网格节点的计算效率,并有效地吸收传播后期出现的低频隐失波,提出基于非分裂递归卷积完全匹配层（UCPML）的旋转交错网格（RSG）GPR正演算法.该算法采用不同的网格交错策略,并在边界条件中引入了吸收低频隐失波的自由可变因子,使得该算法允许选取较大的时间步长,提高了计算效率,并且实现了对低频隐失波的高效吸收.本文首先给出了RSG差分格式,推导了基于UCPML的RSG差分更新方程,探讨了数值色散的稳定性条件,然后以绕射现象严重的衰减夹层数值模拟为例,分别从波场快照、单道波记录、时间域反射误差（TDRE）、频率域反射误差（FDRE）四个方面分析了UCPML与常规PML的全局反射误差,说明了基于UCPML和RSG的GPR正演算法能更有效地吸收低频隐失波.

     

弱流场调制下的海面微波散射模拟研究

根据海面微波散射的多尺度模型以及波流相互作用理论,对一维弱流场调制下的海面微波散射截面进行了数值模拟。结果表明,利用数值方法直接求解波作用量方程获得的海浪调制谱并结合多尺度模型可以较好地模拟弱流场引起的雷达散射截面的变化。内波等海洋现象调制了海浪谱,使得雷达散射截面反映出这些海洋特征,整个调制过程的模拟对于分析这些海洋现象并更好地利用其雷达数据具有重要意义。     

Optimal design of two-dimensional wings in ground effect using multi-objective genetic algorithm

The shape optimization of the 2-dimensional wing in ground effect (WIG) has been performed by the integration of CFD (computational fluid dynamics) and MOGA (multi-objective genetic algorithm). Because of the trade-off between the aerodynamic forces and the height stability, it is difficult to satisfy the design requirements of efficiency and stability at the same time. In this study, the lift coefficient, the lift-drag ratio and the static height stability are chosen as the objective functions to obtain the optimal wing profiles of a WIG craft. An NACA0015 airfoil is used for the baseline model; the aerodynamic characteristics of the base model are compared with that of the optimal solutions. The profile of the airfoil is constructed by four Bezier curves with fourteen control points resulting in the eighteen coordinates, which are adopted as the design variables. The optimal solutions of the multi-objective optimization are not unique but a set of the non-dominated optima: the Pareto frontiers or a Pareto set. As the results of the multi-objective optimization, the forty Pareto optima, which include high-lift, high-efficiency, and more stable airfoils on the edge of the 3-dimensional objective space, are obtained at thirty evolutions of the generation.     

Semisupervised heterogeneous ensemble for ship target discrimination in synthetic aperture radar images

Ship detection using synthetic aperture radar (SAR) plays an important role in marine applications. The existing methods are capable of quickly obtaining many candidate targets, but numerous non-ship objects may be wrongly detected in complex backgrounds. These non-ship false alarms can be excluded by training discriminators, and the desired accuracy is obtained with enough verified samples. However, the reliable verification of targets in large-scene SAR images still inevitably requires manual interpretation, which is difficult and time consuming. To address this issue, a semisupervised heterogeneous ensemble ship target discrimination method based on a tri-training scheme is proposed to take advantage of the plentiful candidate targets. Specifically, various features commonly used in SAR image target discrimination are extracted, and several acknowledged classification models and their classic variants are investigated. Multiple discriminators are constructed by dividing these features into different groups and pairing them with each model. Then, the performance of all the discriminators is tested, and better discriminators are selected for implementing the semisupervised training process. These strategies enhance the diversity and reliability of the discriminators, and their heterogeneous ensemble makes more correct judgments on candidate targets, which facilitates further positive training. Experimental results demonstrate that the proposed method outperforms traditional tri-training.     

Efficiency analysis of open trench for impact pile driving through a single-variable method

Abstract

The ground vibrations during pile driving operation have a drastic potential to undermine the surrounding structures both in land and reclaimed land. Particularly, reclaimed land necessitates ample application of pile driving due to the weak land condition. To prevent the structural damage, attenuation of the ground vibrations to an allowable level through active isolation of circular open trench is the scope of this study. In this research, finite element simulations of continuous impact pile driving process from the ground surface was executed with particular attention to the pile-soil interaction, and thereby, the efficiency of open trench application in attenuation of the unsafe distance of different structures was surveyed using the vibration sensitivity degree. Regarding the crucial parameters of an open trench (depth, width, and location), it was concluded that a sufficient high depth can attenuate the unsafe distance up to 68%, the trench width variations are less effective, and an average pile-trench distance is the most efficient option. The excavation volume was also concluded as another crucial parameter in open trench design which takes all three parameters into account. The trench depth equal to the pile’s maximum critical depth of vibration was inferred for an optimum design.     

基于X波段雷达的表层流估计算法初步研究

对X渡段雷达记录的连续雷达图像进行分析,能够获取海浪和表层流信息.不存在海洋表层流情况下,雷达图像的谱能量分布在静水频散关系确定的平面上,而雷达相时海浪场的运动(比如表层流)使雷达图像的谱能量分布产生多普勒频移,对此频移进行最小二秉拟合.可以确定表层流的大小和方向.     

极化SAR目标相对最优极化研究

目标相对最优极化就是选取一种极化状态,使得研究目标和背景地物的接收功率对比达到最大。通过讨论了目标相对最优极化问题,提出了改进的模型和解算方法,利用实际数据对其模型和方法进行了实验,验证了其有效性和正确性。     

A synthetic aperture radar sea surface distribution estimation by n-order Bézier curve and its application in ship detection

To dates,most ship detection approaches for single-pol synthetic aperture radar(SAR) imagery try to ensure a constant false-alarm rate(CFAR).A high performance ship detector relies on two key components:an accurate estimation to a sea surface distribution and a fine designed CFAR algorithm.First,a novel nonparametric sea surface distribution estimation method is developed based on n-order Bézier curve.To estimate the sea surface distribution using n-order Bézier curve,an explicit analytical solution is derived based on a least square optimization,and the optimal selection also is presented to two essential parameters,the order n of Bézier curve and the number m of sample points.Next,to validate the ship detection performance of the estimated sea surface distribution,the estimated sea surface distribution by n-order Bézier curve is combined with a cell averaging CFAR(CA-CFAR).To eliminate the possible interfering ship targets in background window,an improved automatic censoring method is applied.Comprehensive experiments prove that in terms of sea surface estimation performance,the proposed method is as good as a traditional nonparametric Parzen window kernel method,and in most cases,outperforms two widely used parametric methods,K and G0 models.In terms of computation speed,a major advantage of the proposed estimation method is the time consuming only depended on the number m of sample points while independent of imagery size,which makes it can achieve a significant speed improvement to the Parzen window kernel method,and in some cases,it is even faster than two parametric methods.In terms of ship detection performance,the experiments show that the ship detector which constructed by the proposed sea surface distribution model and the given CA-CFAR algorithm has wide adaptability to different SAR sensors,resolutions and sea surface homogeneities and obtains a leading performance on the test dataset.     

基于浮标数据的卫星雷达高度计海浪波高数据评价与校正

卫星雷达高度计是海浪有效波高（significant wave height,SWH）观测的重要手段之一,本文利用时空匹配方法对T/P、Jason-1、Envisat、Jason-2、Cryosat-2和HY-2A共6颗卫星雷达高度计SWH数据与NDBC（National Data Buoy Center,NDBC）浮标SWH数据进行对比验证,并对雷达高度计SWH数据进行校正。全部卫星雷达高度计SWH数据时间跨度为1992年9月25日到2015年9月1日,对比验证NDBC浮标共53个,包括7个大洋浮标。精度评价发现除T/P外,各卫星雷达高度计SWH的RMSE都在0.4~0.5 m之间,经过校正后,RMSE都有显著下降,下降程度最大为13.82%;对于大洋浮标,评价结果RMSE在0.20~0.28 m之间,结果明显优于全部NDBC浮标的精度评价结果;HY-2A卫星雷达高度计SWH在经过校正后数据质量与国外其他5颗卫星雷达高度计SWH数据质量差异较小。