基于有序数据可变索引的SAR图像目标检测方法

该文提出了一种基于有序数据可变索引(Ordered Data Variability Index, ODVI)的SAR图像目标恒虚警检测算法,该算法首先对待测像素的参考窗进行基于ODVI的自适应筛选处理(Automatic Censoring, AC),以去除窗内的强杂波和干扰像素,并以窗内保留的均匀像素对背景的统计特性进行建模,估计其概率密度函数的参量,同时构建双参数恒虚警检测(CFAR)的检验统计量,计算检测的自适应阈值,实现检测的判决。论文给出了该算法的检测性能曲线,并利用实测的X波段SAR图像进行实验验证,与其它检测方法进行比较,结果显示该文算法具有较好的检测性能和较低的虚警概率。     

全卷积神经网络应用于SAR目标检测

在合成孔径雷达（SAR）图像目标检测中,由于场景杂波的复杂多变,对背景杂波统计模型估计难度增加,从而导致多数检测器容易受到背景杂波的干扰。针对如何避免场景杂波对目标检测干扰的问题,提出了一种基于全卷积神经网络的SAR目标检测模型。该模型将目标检测任务转化为像素分类问题,利用卷积神经网络对数据集中目标像素特征和背景杂波像素的先验信息进行自主学习,有效减少了虚警目标的数量;通过对目标及其阴影区域的联合检测,提高了目标的检测概率。对多个不同场景图像进行测试,实验结果表明提出的检测模型具有良好的检测性能和鲁棒性能,与传统恒虚警检测算法相比,在无需考虑背景杂波统计模型前提下有效降低了虚警概率。     

一种改进的高分辨率SAR图像超像素CFAR舰船检测算法

合成孔径雷达(SAR)图像舰船目标检测一直受到学者广泛关注,恒虚警率(CFAR)检测算法作为雷达图像经典目标检测算法被广泛应用于SAR图像舰船目标检测中。然而经典CFAR检测性能容易受到相干斑噪声影响,基于滑窗的检测结果对滑窗的尺寸选择非常敏感,难以保证杂波背景中不存在目标像素,并且计算效率较低。针对上述问题,该文提出了一种新的基于超像素无窗快速CFAR的SAR图像舰船目标检测算法。首先,利用基于密度的快速噪声空间聚类(DBSCAN)超像素生成方法生成SAR图像的超像素。在SAR数据服从混合瑞利分布的假设下,定义了超像素相异度。然后利用超像素精确估计每个像素的杂波参数,即使在多目标情况下,也可以克服传统CFAR滑动窗口的缺点。此外,基于SAR图像变异系数,提出了一种基于变异系数的局部超像素对比度来优化CFAR检测,以此消除大量杂波虚警,如陆地区域人造目标。对5幅SAR图像的实验结果表明,与其他方法相比,该文方法对不同场景SAR图像海面舰船目标检测都十分稳健。      

基于纹理特征和数学形态学的SAR图像目标检测方法

SAR图像目标检测是SAR图像解译的基础。针对含有目标的SAR图像,利用垂直方向的边缘纹理检测方法对预处理后的图像进行垂直边缘检测,再运用数学形态学中的腐蚀运算和膨胀运算对垂直方向边缘图进行虚警滤除处理,从而得到感兴趣的目标检测区域。详细地给出了SAR图像目标检测步骤,并将本方法与其他方法的检测结果进行了比较,实验结果表明,在均匀杂波背景与非均匀杂波背景下,该方法能够快速有效地实现SAR图像目标检测。     

UWB SAR非均匀区域目标检测方法

在超宽带合成孔径雷达(UWB SAR)图像目标检测中不仅会遇到均匀杂波区域，还会遇到叶簇区域、空旷区域及干扰目标等组成的非均匀杂波区域。恒虚警率(CFAR)目标检测是雷达目标检测的重要方法，而传统的CFAR检测对UWB SAR非均匀杂波区域目标检测效果较差。首先分析了叶簇区域、空旷区域及二者混合区域的杂波分布。然后针对UWB SAR的实际情况，运用智能索引变量的CFAR检测技术(VI—CFAR)，使得均匀杂波和非均匀杂波背景中目标检测都取得了较好的效果。最后，利用实际UWB SAR目标检测结果验证了VI—CFAR的有效性。     

基于CFAR级联的SAR图像舰船目标检测算法

SAR图像舰船目标检测在军事监视和海洋环境监管等方面有着重要的意义。针对SAR图像的特点,提出了一种基于全局CFAR检测与局部CFAR检测级联的舰船目标检测算法。在全局CFAR检测中,通过海杂波特性拟合优选海杂波统计模型,以较高的虚警率筛选潜在的目标点;在局部CFAR检测中,以潜在目标点的连通区域为单位,通过检测窗口的选取、背景像素的确定和海杂波拟合等步骤以后,以较低的虚警率确定目标。最后,通过条件扩张算法和目标像素聚类完善船只细节。实验结果表明,文中算法在保证良好的检测性能的同时,具有检测效率高、舰船细节完整等优点,为舰船目标鉴别和信息提取提供了良好的保障,更加符合实际应用需求。     

一种改进的恒虚警率SAR图像舰船检测算法

自动删除恒虚警率算法(AC-CFAR)作为一种自适应的CFAR检测算法被广泛应用于目标检测中,文中引入均值比对自动删除恒虚警率算法进行改进,使得其在杂波边缘处也有很好的检测效果。在检测过程中,通过分析4个不同方向的均值比来判断边缘方向,能够很好地解决边缘对检测结果的影响。采用能对高分辨率SAR图像精确建模的G0分布进行杂波区域建模,通过更加准确地对背景区域数据的拟合,进一步提高了检测精度。实验表明改进后的算法不仅在同质区域和多目标区域有很好的检测效果,在杂波边缘处也能取得比较好的检测效果。     

结合强化学习自适应候选框挑选的SAR目标检测方法

大场景合成孔径雷达(SAR)图像相对于通用光学图像,复杂背景杂波对目标特征提取影响更大,由于传统基于候选框的深度目标检测算法会在整张特征图上产生大量冗余候选框,因而在SAR图像复杂背景杂波影响下会产生大量的虚警,降低目标检测精度。针对该问题,该文基于Faster R-CNN检测模型,提出结合强化学习自适应候选框挑选的SAR目标检测方法。该方法能够通过强化学习自适应搜索特征图中可能含有目标的区域,并挑选搜索区域内的候选框继续进行分类、回归。通过准确搜索到含有目标的区域,可以减少复杂背景杂波的影响并减少传统强化学习应用于检测问题的计算量。所提方法利用强化学习序列决策的特点,能够根据图像信息通过强化学习迭代搜索自适应确定图像中可能含有目标的搜索区域的位置。同时,该方法通过在强化学习中使用距离约束,可以根据之前的搜索结果自适应调整下一次搜索区域的尺寸。基于实测数据的实验结果表明,所提方法能够提升传统深度学习目标检测方法的检测性能。     

基于灰度相关性的SAR图像联合CFAR舰船检测算法

分析了中高分辨率SAR海洋图像的目标和海杂波特点,利用了SAR海洋图像中舰船目标的灰度相关性、形状特性以及舰船目标与背景杂波的信杂比特性,提出了一种基于灰度相关性的联合CFAR舰船检测算法。算法综合利用了舰船目标内部相邻像素间的灰度强相关性和舰船目标和海杂波的信杂比,建立了海杂波区域内相邻像素间灰度值的二维对数正态分布来实现联合CFAR检测。该算法能够改善斑点噪声和背景局部不均匀对检测带来的虚警,检测效果相比于传统检测算法更加优越。     

基于卷积构型的单元平均CFAR目标检测算法

提出一种基于卷积构型的单元平均恒虚警率(convolution based cell averaging constant false alarm rate, CCA-CFAR)快速检测算法.该算法首先根据背景杂波分布模型计算待检测合成孔径雷达(synthetic aperture radar, SAR)图像统计量矩阵, 然后对单元平均恒虚警率(cell averaging constant false alarm rate, CA-CFAR)检测器构建卷积模型, 利用卷积运算实现对背景杂波的矩估计, 并求出详细的背景杂波分布函数, 最后根据分布函数计算出每个像素的判定阈值, 并对所有待检测像素是否为目标点进行判定.该检测算法复杂度低, 运算效率高, 能够快速实现SAR图像实时目标检测.仿真实验证明了该方法的有效性和工程实用价值.     

An Adaptive and Fast CFAR Algorithm Based on Automatic Censoring for Target Detection in High-Resolution SAR Images

An adaptive and fast constant false alarm rate (CFAR) algorithm based on automatic censoring (AC) is proposed for target detection in high-resolution synthetic aperture radar (SAR) images. First, an adaptive global threshold is selected to obtain an index matrix which labels whether each pixel of the image is a potential target pixel or not. Second, by using the index matrix, the clutter environment can be determined adaptively to prescreen the clutter pixels in the sliding window used for detecting. The $G^{0}$ distribution, which can model multilook SAR images within an extensive range of degree of homogeneity, is adopted as the statistical model of clutter in this paper. With the introduction of AC, the proposed algorithm gains good CFAR detection performance for homogeneous regions, clutter edge, and multitarget situations. Meanwhile, the corresponding fast algorithm greatly reduces the computational load. Finally, target clustering is implemented to obtain more accurate target regions. According to the theoretical performance analysis and the experiment results of typical real SAR images, the proposed algorithm is shown to be of good performance and strong practicability.      

Automatic censoring CFAR detector for heterogeneous environments

In radar detection, many constant false alarm rate (CFAR) processors have been proposed in the literature. It is well known that a processor is optimal only for one type of environment and that its detection performances are seriously degraded in presence of unknown irregularities. In such situations, the main difficulty resides in the estimation of the background configuration. That is, depending upon the non-homogeneity of the environment, one would choose the adequate optimal detection algorithm among a variety of known conventional ones that offer the best detection probability. Based on unknown transitions; i.e., in the presence of a priori unknown numbers of interfering targets and/or clutter edge, we propose an automatic censoring CFAR (AC-CFAR) detector for heterogeneous Gaussian clutter. The censoring technique used in this work offers a good discrimination between homogeneous and non-homogeneous environments. The proposed detector dynamically switches to the optimal conventional detector CA-, CMLD- or TM-CFAR. The performances of the proposed detector is evaluated and compared to existing detectors in various background situations. Monte Carlo simulations show that the AC-CFAR detector performs like the CA-CFAR in a homogeneous background. Moreover, the proposed detector exhibits considerable robustness in the presence of interfering targets and/or clutter-edge situations.     

CFAR edge detector for polarimetric SAR images

Finding the edges between different regions in an image is one of the fundamental steps of image analysis, and several edge detectors suitable for the special statistics of synthetic aperture radar (SAR) intensity images have previously been developed. In this paper, a new edge detector for polarimetric SAR images is presented using a newly developed test statistic in the complex Wishart distribution to test for equality of covariance matrices. The new edge detector can be applied to a wide range of SAR data from single-channel intensity data to multifrequency and/or multitemporal polarimetric SAR data. By simply changing the parameters characterizing the test statistic according to the applied SAR data, constant false-alarm rate detection is always obtained. An adaptive filtering scheme is presented, and the distributions of the detector are verified using simulated polarimetric SAR images. Using SAR data from the Danish airborne polarimetric SAR, EMISAR, it is demonstrated that superior edge detection results are obtained using polarimetric and/or multifrequency data compared to using only intensity data.     

A generalized switching CFAR processor based on test cell statistics

In this paper, a new constant false alarm rate (CFAR) thresholding algorithm which is a generalisation of the switching CFAR (S-CFAR) that takes into account the statistics of the sample in the test cell for reference sample selection is proposed. It employs a composite approach based on the switching CFAR and the order statistic CFAR (OS-CFAR). A mathematical analysis in a homogeneous environment is provided for this detector. The results obtained show that the detection performance of the generalised S-CFAR (GS-CFAR) is improved both in homogenous background and non-homogenous environment caused by interfering targets and clutter edge.     

SAR图像点目标的检测

分析了在均匀杂波回波功率服从 Gamma分布条件下 SAR点目标检测 ,推导了点目标虚警概率和检测概率与阈值系数关系 ,提出了检测点目标阈值系数选择根据和方法。在杂波均值估计方面 ,提出了以全局均值代替局部动态均值。实际测试结果表明所提出的检测方法在检测效果和计算量方面都优于双参数恒虚警检测算法     

SAR图像目标综合检测方法

基于SAR(合成孔径雷达)图像杂波结构,结合小波变换和自适应维纳滤波提出了一种新的抑制SAR图像相干斑噪声方法,该方法能够较好保留杂波边缘和点目标.分析了抑制SAR图像相干斑噪声后的多分布特性,研究了相应的SAR目标检测,提出了一种新的SAR图像目标检测方法及其实现.实际SAR图像测试结果表明了本文方法的有效性.