SAR target detection based on the optimal fractional Gabor spectrum feature

In this paper,an algorithm based on a fractional time-frequency spectrum feature is proposed to improve the accuracy of synthetic aperture radar(SAR)target detection.By extending the fractional Gabor transform(FrGT)into two dimensions,the fractional time-frequency spectrum feature of an image can be obtained.In the achievement process,we search for the optimal order and design the optimal window function to accomplish the two-dimensional optimal FrGT.Finally,the energy attenuation gradient(EAG)feature of the optimal time-frequency spectrum is extracted for high-frequency detection.The simulation results show the proposed algorithm has a good performance in SAR target detection and lays the foundation for recognition.

Point association analysis of vessel target detection with SAR, HFSWR and AIS

A space-borne synthetic aperture radar （SAR）, a high frequency surface wave radar （HFSWR）, and a ship automatic identification system （AIS） are the main remote sensors for vessel monitoring in a wide range. These three sensors have their own advantages and weaknesses, and they can complement each other in some situations. So it would improve the capability of vessel target detection to use multiple sensors including SAR, HFSWR, and A/S to identify non-cooperative vessel targets from the fusion results. During the fusion process of multiple sensors＇ detection results, point association is one of the key steps, and it can affect the accuracy of the data fusion and the efficiency of a non-cooperative target＇s recognition. This study investigated the point association analyses of vessel target detection under different conditions： space- borne SAR paired with AIS, as well as HFSWR, paired with AIS, and the characteristics of the SAR and the HFSWR and their capability of vessel target detection. Then a point association method of multiple sensors was proposed. Finally, the thresholds selection of key parameters in the points association （including range threshold, radial velocity threshold, and azimuth threshold） were investigated, and their influences on final association results were analyzed.

Target detection and recognition in SAR imagery based on KFDA

Current research on target detection and recognition from synthetic aperture radar （SAR） images is usually carried out separately. It is difficult to verify the ability of a target recognition algorithm for adapting to changes in the environment. To realize the whole process of SAR automatic target recognition （ATR）, es- pecially for the detection and recognition of vehicles, an algorithm based on kernel fisher discdminant analysis （KFDA） is proposed. First, in order to make a better description of the difference be- tween the background and the target, KFDA is extended to the detection part. Image samples are obtained with a dual-window approach and features of the inner and outer window samples are extracted by using KFDA. The difference between the features of inner and outer window samples is compared with a threshold to determine whether a vehicle exists. Second, for the target area, we propose an improved KFDA-IMED （image Euclidean distance） combined with a support vector machine （SVM） to recognize the vehicles. Experimental results validate the performance of our method. On the detection task, our proposed method obtains not only a high detection rate but also a low false alarm rate without using any prior information. For the recognition task, our method overcomes the SAR image aspect angle sensitivity, reduces the requirements for image preprocessing and improves the recogni- tion rate.

Knowledge-based detection method for SAR targets

When the classical constant false-alarm rate （CFAR） combined with fuzzy C-means （FCM） algorithm is applied to target detection in synthetic aperture radar （SAR） images with complex background, CFAR requires block-by-block estimation of clutter models and FCM clustering converges to local optimum. To address these problems, this paper pro-poses a new detection algorithm： knowledge-based combined with improved genetic algorithm-fuzzy C-means （GA-FCM） algorithm. Firstly, the algorithm takes target region＇s maximum and average intensity, area, length of long axis and long-to-short axis ratio of the external ellipse as factors which influence the target appearing probabil- ity. The knowledge-based detection algorithm can produce preprocess results without the need of estimation of clutter models as CFAR does. Afterward the GA-FCM algorithm is improved to cluster pre-process results. It has advantages of incorporating global optimizing ability of GA and local optimizing ability of FCM, which will further eliminate false alarms and get better results. The effectiveness of the proposed technique is experimentally validated with real SAR images.

MAXIMUM A POSTERIORI-BASED AUTOMATIC TARGET DETECTION IN SAR IMAGES

The paper presents an algorithm of automatic target detection in Synthetic Aperture Radar(SAR) images based on Maximum A Posteriori(MAP). The algorithm is divided into three steps. First, it employs Gaussian mixture distribution to approximate and estimate multi-modal histogram of SAR image. Then, based on the principle of MAP, when a priori probability is both unknown and learned respectively, the sample pixels are classified into different classes c = {target,shadow, background}. Last, it compares the results of two different target detections. Simulation results preferably indicate that the presented algorithm is fast and robust, with the learned a priori probability, an approach to target detection is reliable and promising.

A Novel SAR Image Ship Small Targets Detection Method

To satisfy practical requirements of high real-time accuracy and low computational complexity of synthetic aperture radar (SAR) image ship small target detection, this paper proposes a small ship target detection method based on the improved You Only Look Once Version 3 (YOLOv3). The main contributions of this study are threefold. First, the feature extraction network of the original YOLOV3 algorithm is replaced with the VGG16 network convolution layer. Second, general convolution is transformed into depthwise separable convolution, thereby reducing the computational cost of the algorithm. Third, a residual network structure is introduced into the feature extraction network to reuse the shallow target feature information, which enhances the detailed features of the target and ensures the improvement in accuracy of small target detection performance. To evaluate the performance of the proposed method, many experiments are conducted on public SAR image datasets. For ship targets with complex backgrounds and small ship targets in the SAR image, the effectiveness of the proposed algorithm is verified. Results show that the accuracy and recall rate improved by 5.31% and 2.77%, respectively, compared with the original YOLOV3. Furthermore, the proposed model not only significantly reduces the computational effort, but also improves the detection accuracy of ship small target.

Marine Target Detection Using Dual-polarimetric SAR Imagery

In this study,we provide a summary of research advances in the field of maritime target detection using DP(dualpolarimetric)SAR(Synthetic Aperture Radar)imagery,accomplished during the European and China collaboration in the framework of the Dragon-4 program ID 32235.The main innovative contribution is twofold:(1)We addressed ship detection proposing an improved GP-PNF(Geometrical Perturbation-Polarimetric Notch Filter),termed as IGP-PNF,that is characterized by a new feature vector that includes three new scattering features;(2)We addressed oil platform detection by contrasting singlepolarization SAR methods with polarimetric ones in order to quantify the extra-benefit carried on polarimetric information.The proposed theoretical framework is tested against actual multi-polarization SAR data.In particular,ship detection methods are verified against a Sentinel-1 SAR scene where a large number of ships is present;while,oil platform detection is discussed using Terra SAR-X SAR data.Experimental analysis shows that:(1)The IGP-PNF method performs best in terms of clutter-to-target ratio;(2)Coherent polarimetric information significantly outperforms single-polarization SAR measurements in highlighting targets in challenging cases.

A PARAMETER ESTIMATION FOR DETECTION AND IMAGING OF MOVING TARGETS WITH SAR BY WVD

Based on a joint time-frequency two dimensional processing, this paper proposes a method for the detection and imaging of moving targets SAR by using Wigner-Ville Distribution (WVD). It is a parameter estimation method to generate a high resolution image. The problem of WVD in dealing with multi-point targets and extended targets are also discussed. The computer simulation results illustrate its availability.

Object Detection Research of SAR Image Using Improved Faster Region-Based Convolutional Neural Network

Target detection technology of synthetic aperture radar(SAR)imageis widely used in the field of military reconnaissance and surveillance.The traditional SAR image target detection methods need to be provided a lot of empirical knowledge because the characteristics of SAR images in different configurations(attitude,pitch angle,imaging parameters,etc.)will change greatly,resulting in high generalization error.Currently,deep learning method has achieved great success in the field of image processing.Research shows that deep learning can achieve a more intrinsic description of the data,while the model has a stronger ability of modeling and generalization.In order to solve the problem of insufficient data in SAR data sets,an experimental system for acquiring SAR image data in real scenes was built.Then the transfer learning method and the improved convolution neural network algorithm(PCA+Faster R-CNN)are applied to improve the target detection precision.Finally,experimental results demonstrate the significant effectiveness of the proposed method.

A tunable adaptive detector for distributed targets when signal mismatch occurs

Aiming at the problem of detecting a distributed target when signal mismatch occurs,this paper proposes a tunable detector parameterized by an adjustable parameter.By adjusting the parameter,the tunable detector can achieve robust or selective detection of mismatched signals.Moreover,the proposed tunable detector,with a proper tunable parameter,can provide higher detection probability compared with existing detectors in the case of no signal mismatch.In addition,the proposed tunable detector possesses the constant false alarm rate property with the unknown noise covariance matrix.

改进FCOS的SAR图像舰船检测算法

针对SAR图像中舰船检测的目标尺度变化大及背景复杂等影响因素,提出一种基于FCOS的一阶段舰船目标检测算法。采用基于拆分注意力和分组卷积的ResNeSt网络作为主干网络进行提取特征,同时在特征金字塔基础上增加聚合路径和注意力机制,提升特征融合能力,实现对网络结构的优化。结果表明,改进方法相对于基线网络平均精度提升了2.15%,精准率提升了2.4%,召回率提升了3.59%。该研究在处理SAR图像中舰船检测任务时具有较好的性能。

通道剪枝与知识蒸馏相结合的轻量化SAR目标检测

轻量化SAR目标检测方法对快速检测SAR影像中的地物目标具有重要意义。针对轻量化检测方法精度不高的问题,设计了一种通道剪枝与知识蒸馏相结合的轻量化SAR目标检测方法。该方法通过对复杂网络中批归一化层的缩放因子γ进行稀疏化训练,判别对应特征通道的重要程度,进而裁剪次要通道,并在微调训练后将其作为教师网络,构造知识蒸馏框架指导轻量模型训练,提高轻量模型的检测精度。采用YOLOv5-6.1算法搭建了检测框架,并在重组的MSAR和SSDD多类目标数据集上进行了训练和检测试验,结果表明该方法能够在保持模型体积仅3.73 MB的轻量化条件下,提升SAR目标检测精度,验证了本文方法的有效性。

基于多层显著性模型的SAR图像舰船目标检测

针对合成孔径雷达图像舰船目标检测问题,提出了一种结合选择机制与轮廓信息的多层显著性目标检测方法。首先,利用非下采样剪切波和频谱残差法进行全局显著性区域提取。其次,提出了一种基于动态恒虚警率的活动轮廓显著性模型,逐步滤除候选区域的虚警,提取目标轮廓,从而实现目标的精确检测。所提方法能够由粗到细地快速捕获目标区域,从而实现高效、高分辨率合成孔径雷达图像舰船检测。最后,在真实SAR数据集进行了测试,与其他经典的舰船检测方法相比,所提算法不仅有效地抑制了海杂波的影响,而且在检测精度上有较大提高。

基于改进YOLOv5-ResNet的海上舰船SAR图像快速检测

在恶劣天气和海浪等自然因素的影响下,基于可见光数据进行舰船目标监测等手段往往难以有效开展,需要借助主动式微波成像卫星合成孔径雷达(SAR)进行图像解译。为了解决深度学习在处理数据集较小图像上无法准确提取特征及数据相似度较高的问题,基于YOLOv5-ResNet提出了一种跨尺度融合机制,重新定义损失函数。研究表明,识别SAR舰船目标的准确率有一定的提升:识别单目标舰船检测最高准确度达到93%,同比YOLOv5提升4%,比YOLOv5-ResNet50提升20%;在近岸舰船目标检测上,有效降低了由于数据集质量不佳、模型训练方法不当等造成误差率的非必要上升。

考虑海杂波特征的SAR图像海上运动小目标检测方法

鉴于海杂波是一种非平稳性雷达信号,使用传统方法容易受到海杂波特征影响,导致检测结果不精准。充分考虑海杂波特征,提出了SAR图像海上运动小目标检测方法。根据雷达观测场景等距离环,确定波浪传播方向,分析海杂波特征。构建最优自适应海杂波抑制权矢量函数,结合约束最小方差准则抑制海杂波,避免慢速目标难以被有效检测。计算节点邻域内每个像素点到节点的距离,筛选孤立像素点。充分考虑海杂波特征,使用统计平均方式获取海杂波背景下的平均干涉幅度和相位,以此为依据检测运动小目标。实验结果表明,该方法在正常、中等和复杂海况下,检测结果与实际结果一致,说明使用该方法检测结果精准。

Single Source Self-Screen Jamming Elimination and Target Detection for Distributed Dual Antennas Radar System

Detecting target echo in the existence of self-screen jamming is a challenging work for radar system, especially when digital radio frequency memory(DRFM) technique is employed that mixes the jamming and target echo both in spatial and time-frequency domain. The conventional way to solve this problem would suffer from performance degradation when physical target(PT) and false target(FT) are superposed in time. In this paper, we propose a new spatial filter according to the different correlation characteristic between PT and FT. The filter takes the ratio of expected signal power to expected jamming and noise power as the objective function under the constant filter modulus constraint. The optimal filter coefficients are derived with a generalized rayleigh quotient approach. Moreover, we analytically compute the target detection probability and demonstrate the applicability of the proposed method to the correlation coefficient. Monte Carlo simulations are provided to corroborate the proposed studies. Furthermore, the proposed method has simple architecture and low computation complexity, making it easily applied in modern radar system.

改进Faster R-CNN的视频SAR动目标检测算法

针对当前可用于深度学习的视频SAR数据稀少的现状,以及动目标检测算法中存在较多的漏检和虚警问题,基于美国桑迪亚国家实验室真实视频SAR数据制作深度学习数据集,提出一种改进Faster R-CNN的视频SAR动目标检测算法。算法以截取后的ResNet50为特征提取网络,利用K-means加遗传算法自适应计算锚框,并在数据预处理环节加入S型曲线增强方法,来增强图像的对比度信息。经实验验证,所提出方法能够显著提升动目标检测率和检测速度,其中,平均精度(AP)和F1分数提升均达到10个点以上,有效降低了虚警和漏检,整体表现优于一阶段算法SSD和RetinaNet。

基于SAR图像变化的小型目标检测

针对战场侦察的需求,结合SAR图像成像范围广、成像精度高的特性,SAR图像变化检测技术可应用于小目标检测。本文基于SAR图像尺度大而目标尺寸较小的特点,在差值法的基础上进行了改进。采用中值滤波进行图像降噪,并提出使用自适应下采样的方法进行快速图像配准,利用幂次变换增加目标信杂比提高检测率。通过实验验证改进差值法的有效性,其能够在保证检测率的同时缩短检测时间。

基于改进的YOLOv5小目标检测SAR船只方法

为了有效管理海上交通、实施海上救援和保护海洋环境,需要精确地掌握海上船只目标的位置和分布情况,但传统的检测方法(如CFAR)往往会出现船只细节丢失和小目标漏检的情况。为了解决以上问题,将YOLOv5模型进行改进。首先通过数据增强,提升数据的多样性,进而提高模型的泛化能力;之后加入SE注意力机制和小目标检测层来增强模型对船只的特征提取能力。实验结果表明,加入SE注意力机制和小目标检测层后,平均准确度mAP分别提高了2%和3.1%,可以有效改善船只密集分布、沿岸分布等不同场景下的检测准确率,实现整体准确率的提高。

用于SAR图像舰船目标检测的MAF-Net和CS损失

深度学习算法以其端到端训练和高准确率等优势被广泛应用于合成孔径雷达图像舰船检测领域。然而,SAR图像中舰船目标尺寸跨度较大,且易受到复杂背景和噪声的干扰,从而影响识别精度。为了进一步提高网络的检测精度,本文提出了一个多尺度注意力融合网络。该网络主要包含一个多尺度特征注意力融合模块,该模块使用骨干网络输出的特征图,融合多尺度的信息,在空间和通道维度对FPN输出的特征图进行增强,用于抑制噪声和背景对舰船目标的影响,提升网络的特征提取能力。此外,本文还提出了余弦相似损失,通过计算目标与非目标区域的余弦相似度,使网络更准确地区分船舶目标与背景,以进一步提高准确率。大量的实验表明,在SSDD和SAR-Ship-Dataset数据集上,本文所提的方法与现有的几种算法相比具有更高的检测精度。