首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 140 毫秒
1.
一种图斑特征引导的感知分组视觉注意模型   总被引:1,自引:0,他引:1  
肖洁  蔡超  丁明跃 《航空学报》2010,31(11):2266-2274
 结合自顶向下和自底向上的信息处理策略,提出了一种新的视觉注意模型,该模型利用图斑特征信息引导感知分组过程,使注意力关注于任务相关区域。通过引入多尺度图斑,关联图斑和底层特征,新模型利用图斑特征建立先验信息的知识表达形式。对于给定新的场景,新模型能够使用先验信息,提高和目标对象相关特征的显著性。通过视觉预注意阶段计算得到的中间数据,提取图斑特征向量作为引导,不断迭代积累对象,合并区域表征对象,由表征简单对象开始,进而表征复杂对象,迅速有效地引导视觉注意力关注任务相关区域。实验比较了新模型、显著区域提取模型及波谱残留模型,证明了所提模型的优越性。  相似文献   

2.
传统的合成孔径雷达舰船检测识别需要分两步实现,检测识别精度和效率难以满足实际应用需求。本文结合注意力机制和YOLO-V3网络提出了注意力YOLO-V3网络实现合成孔径雷达舰船检测识别一体化。同时,利用公开的AIR-SARShip-1.0数据集和OpenSARShip数据集构建了大场景舰船检测识别数据集,用于验证目标检测识别性能。实验结果表明,本文提出的注意力YOLO-V3网络可以获得较高的检测识别精度,证明了本文方法的有效性。  相似文献   

3.
Improved SAR target detection via extended fractal features   总被引:3,自引:0,他引:3  
The utility of the extended fractal (EF) feature is evaluated for the enhancement of the focus of attention (FOA) stage of a synthetic aperture radar (SAR) automatic target recognition (ATR) system. Unlike more traditional SAR detection features that distinguish target pixels from the background only on the basis of contrast, the EF feature is sensitive to both the contrast and size of objects. Furthermore, the structure for the EF feature computational algorithm lends itself to very fast implementation, and it can be shown that the new feature has a CFAR-like (constant false alarm rate) property. We demonstrate the improved performance using the new feature by testing a number of different detection approaches over two databases of SAR imagery  相似文献   

4.
We present a method for predicting a tight upper bound on performance of a vote-based approach for automatic target recognition (ATR) in synthetic aperture radar (SAR) images. In such an approach, each model target is represented by a set of SAR views, and both model and data views are represented by locations of scattering centers. The proposed method considers data distortion factors such as uncertainty, occlusion, and clutter, as well as model factors such as structural similarity. Firstly, we calculate a measure of the similarity between a given model view and each view in the model set, as a function of the relative transformation between them. Secondly we select a subset of possible erroneous hypotheses that correspond to peaks in similarity functions obtained in the first step. Thirdly, we determine an upper bound on the probability of correct recognition by computing the probability that every selected hypothesis gets less votes than those for the model view under consideration. The proposed method is validated using MSTAR public SAR data, which are obtained under different depression angles, configurations, and articulations  相似文献   

5.
We propose a model for generating low-frequency synthetic aperture radar (SAR) clutter that relates model parameters to physical characteristics of the scene. The model includes both distributed scattering and large-amplitude discrete clutter responses. The model also incorporates the SAR imaging process, which introduces correlation among image pixels. The model may be used to generate synthetic clutter for a range of environmental operating conditions for use in target detection performance evaluation of the radar and automatic target detection/recognition algorithms. We derive a statistical representation of the proposed clutter model's pixel amplitudes and compare with measured data from the CARABAS-II SAR. Simulated clutter images capture the structure and amplitude responses seen in the measured data. A statistical analysis shows an order of magnitude improvement in model fit error compared with standard maximum-likelihood (ML) density fitting methods.  相似文献   

6.
This paper deals with a new synthetic aperture radar (SAR) Processor based on a subspace detector designed for man-made target (MMT) detection. As MMTs are more accurately decribed by a set of canonical elements than with isotropic points, we develop a new algorithm which aims at using new models, instead of the isotropic point model commonly used in SAR processors. A subspace detector matched to canonical elements is included in the SAR processing. The implementation and the optimization of subspace detector SAR (SDSAR) algorithm is described. Simple examples of MMT detection in simulations and real data with a target hidden in a forest show the power of our approach. The SDSAR algorithm is shown to be the first robust and tractable algorithm relying on realistic scattering assumptions about the target.  相似文献   

7.
为了能为作战指挥系统提供清晰的局部战场信息,提高对局部战场低可观测目标的检测概率、定位精度及识别概率,迫切需要对无人机载SAR、可见光传感器、红外探测器等图像信息及其他非图像信息融合处理。提出了无人机载多传感器图像融合技术需要研究的内容,如: 图像融合新方法研究;无人机载SAR图像的非平稳性处理;基于图像融合目标检测和处理技术; 无人机载图像和非图像信息的融合问题;无人机载多传感器图像融合的实现及评估;多无人机载合成孔径雷达的协同成像;用图像融合的方法实现对运动目标检测等。分析了所提出研究内容的可行性,剖析了其中的关键技术,拟定了可能的技术路线。  相似文献   

8.
在SAR图像解译应用领域,目标的自动检测与识别一直是该领域的研究重点和热点,也是该领域的研究难点。针对SAR图像的目标检测与识别方法一般由滤波、分割、特征提取和目标识别等多个相互独立的步骤组成。复杂的流程不仅限制了SAR图像目标检测识别的效率,多步骤处理也使模型的整体优化难以进行,进而制约了目标检测识别的精度。采用近几年在计算机视觉领域表现突出的深度学习方法来处理SAR图像的目标检测识别问题,通过使用CNN、Fast RCNN以及Faster RCNN等模型对MSTAR SAR公开数据集进行目标识别及目标检测实验,验证了卷积神经网络在SAR图像目标识别领域的有效性及高效性,为后续该领域的进一步研究应用奠定了基础。  相似文献   

9.
Although Convolutional Neural Networks(CNNs) have significantly improved the development of image Super-Resolution(SR) technology in recent years, the existing SR methods for SAR image with large scale factors have rarely been studied due to technical difficulty. A more efficient method is to obtain comprehensive information to guide the SAR image reconstruction.Indeed, the co-registered High-Resolution(HR) optical image has been successfully applied to enhance the quality of SAR image due to it...  相似文献   

10.
Optimization problems are often highly constrained and evolutionary algorithms(EAs)are effective methods to tackle this kind of problems. To further improve search efficiency and convergence rate of EAs, this paper presents an adaptive double chain quantum genetic algorithm(ADCQGA) for solving constrained optimization problems. ADCQGA makes use of doubleindividuals to represent solutions that are classified as feasible and infeasible solutions. Fitness(or evaluation) functions are defined for both types of solutions. Based on the fitness function, three types of step evolution(SE) are defined and utilized for judging evolutionary individuals. An adaptive rotation is proposed and used to facilitate updating individuals in different solutions.To further improve the search capability and convergence rate, ADCQGA utilizes an adaptive evolution process(AEP), adaptive mutation and replacement techniques. ADCQGA was first tested on a widely used benchmark function to illustrate the relationship between initial parameter values and the convergence rate/search capability. Then the proposed ADCQGA is successfully applied to solve other twelve benchmark functions and five well-known constrained engineering design problems. Multi-aircraft cooperative target allocation problem is a typical constrained optimization problem and requires efficient methods to tackle. Finally, ADCQGA is successfully applied to solving the target allocation problem.  相似文献   

11.
实例分割作为计算机视觉领域极具挑战性的任务之一,要求在图像分类的基础上为每一个物体生成像素级别的分割掩码.业界主流方案可分为自上而下和自下而上两种范式,自上而下范式又可分为双阶段分割和单阶段分割.单阶段分割方案为了提高推断速度,往往使用全图卷积操作取代双阶段分割方案中先检测后分割的策略.然而,卷积网络的平移不变性使得同一种类的不同实例提取到的特征相似,仅靠全图卷积难以进行区分,从而导致单阶段分割方案精度下降.针对单阶段分割精度降低的问题,提出了一种注意力机制,该机制在特征图每个位置的特征向量上进行点积运算,并将运算结果作为新的特征图,同一位置点积结果最大化,不同位置点积结果最小化,以丰富特征图中不同实例的差异信息.通过注意力机制使得单阶段分割方案中的全图卷积操作能更好地区分同一种类的不同实例,从而生成高质量分割掩码.在公开数据集上进行实验,验证了所提方法的有效性.  相似文献   

12.
SAR image formation via semiparametric spectral estimation   总被引:1,自引:0,他引:1  
A new algorithm, referred to as the SPAR (Semiparametric) algorithm, is presented herein for target feature extraction and complex image formation via synthetic aperture radar (SAR). The algorithm is based on a flexible data model that models each target scatterer as a two-dimensional (2-D) complex sinusoid with arbitrary unknown amplitude and constant phase in cross-range and with constant amplitude and phase in range. By attempting to deal with one corner reflector, such as one dihedral or trihedral, at a time, the algorithm can be used to effectively mitigate the artifacts in the SAR images due to the flexible data model. Another advantage of SPAR is that it can be used to obtain initial conditions needed by other parametric target feature extraction methods to reduce the total amount of computations needed. Both numerical and experimental examples are provided to demonstrate the performance of the proposed algorithm  相似文献   

13.
Synthetic aperture radar(SAR)image is severely affected by multiplicative speckle noise,which greatly complicates the edge detection.In this paper,by incorporating the discontinuityadaptive Markov random feld(DAMRF)and maximum a posteriori(MAP)estimation criterion into edge detection,a Bayesian edge detector for SAR imagery is accordingly developed.In the proposed detector,the DAMRF is used as the a priori distribution of the local mean reflectivity,and a maximum a posteriori estimation of it is thus obtained by maximizing the posteriori energy using gradient-descent method.Four normalized ratios constructed in different directions are computed,based on which two edge strength maps(ESMs)are formed.The fnal edge detection result is achieved by fusing the results of two thresholded ESMs.The experimental results with synthetic and real SAR images show that the proposed detector could effciently detect edges in SAR images,and achieve better performance than two popular detectors in terms of Pratt's fgure of merit and visual evaluation in most cases.  相似文献   

14.
A likelihood ratio is proposed for moving target detection in a wideband (WB) synthetic aperture radar (SAR) system. WB is defined here as any systems having a large fractional bandwidth, i.e., an ultra wide frequency band combined with a wide antenna beam. The developed method combines time-domain fast backprojection SAR processing methods with moving target detection using space-time processing. The proposed method reduces computational load when sets of relative speeds can be tested using the same clutter-suppressed subaperture beams. The proposed method is tested on narrowband radar data.  相似文献   

15.
保持弱细结构特征的SAR图象模拟退火重构方法   总被引:2,自引:1,他引:1  
模拟退火 ( SA)算法最先由 White R G.用于合成孔径雷达 ( SAR)图象的降斑处理。该算法在重构均匀区域和强结构区效果有很大提高 ,但也有缺点 ,尤其是过分模糊弱细结构。本文提出了一种改进的方法 ,在 SA算法中融入了边沿检测和增强步骤 ,使弱细结构得以增强并在退火过程中保持。为配合此方法 ,采用平稳下降的指数温度规划取代对数形式。通过仔细调整算法过程 ,可使新方法保留 SAR图象中的很多细小结构 ,而不使其他均匀的和强结构场景性能恶化 ,同时也没有引入其他缺陷。改进的算法更加适于中、低分辨率的 SAR图象降斑处理  相似文献   

16.
利用分数阶Fourier域滤波的机载SAR多运动目标检测   总被引:5,自引:0,他引:5  
 强度相差较大的多运动目标检测是机载合成孔径雷达 ( SAR)技术的一个重点和难点,传统的频域滤波和现代的时频分布方法都无法解决这个问题。首先分析了机载 SAR运动目标回波本质上为线性调频信号,据此提出一种基于分数阶 Fourier域滤波的运动目标检测新方法,并且应用逐次消去的思想有效地解决了强度相差较大的多目标检测问题。仿真的结果验证了算法的有效性。  相似文献   

17.
Trajectory deviations in airborne SAR: analysis and compensation   总被引:3,自引:0,他引:3  
This paper concerns the analysis and compensation of trajectory deviations in airborne synthetic aperture radar (SAR) systems. Analysis of the received data spectrum is carried out with respect to the system geometry in the presence of linear, sinusoidal, and general aircraft displacements. This shows that trajectory deviations generally produce spectral replicas along the azimuth frequency that strongly impair the quality of the focused image. Based on the derived model, we explain the rationale of the motion compensation (MOCO) strategy that must be applied at the SAR processing stage in order to limit the resolution loss. To this end aberration terms are separated into range space invariant and variant components. The former can be accounted for either in a preprocessing step or efficiently at range compression stage. The latter needs a prior accommodation of range migration effect. We design the procedure for efficient inclusion of the MOCO within a high precision scaled FT based SAR processing algorithm. Finally, we present results on simulated data aimed at validating the whole analysis and the proposed procedure  相似文献   

18.
提高高分辨率SAR图像在复杂战场环境中的目标识别能力,对防御未来战争中来自地面目标的威胁具有重要意义。针对地面特定目标的大小、方位、旋转等变化以及强杂波背景给目标识别带来的严重影响,提出将目标的三维模型投影到二维平面,采用余弦傅里叶矩和瑞利分布的CFAR检测方法分别对其矩特征和峰值特征进行提取,利用级联组合分类器对目标识别进行建模分析,并通过试验验证该方法的有效性。结果表明:该方法实现了在特征维数高和姿态变化下的目标识别,而且无需额外增加对制导控制系统的开销。  相似文献   

19.
Standard radar image formation techniques waste computational resources by full resolving all areas of the scene, even regions of benign clutter. We introduce a multiscale prescreener algorithm that runs as part of the image formation processing step for ultrawideband (UWB) synthetic aperture radar (SAR) systems. The prescreener processes intermediate radar data generated by a quadtree backprojection image former. As the quadtree algorithm iterates, it is resolving increasingly finer subpatches of the scene. After each quadtree stage, the prescreener makes an estimate of the signal-to-background ratio of each subpatch and applies a constant false alarm rate (CFAR) detector to decide which ones might contain a target of interest. Whenever the prescreener determines that a subpatch is not near a detection, it cues the image former to terminate further processing of that subpatch. Using a small database of UWB radar field data, we demonstrate that the prescreener is able to decrease the overall computational load of the image formation process. We also show that the new multiscale prescreener method produces fewer false alarms than the conventional two-parameter CFAR prescreener applied to the completely formed image  相似文献   

20.
许东  安锦文 《航空学报》2006,27(4):692-696
由于图像噪声的存在,使得利用传统的极值检测算法通常会使要提取的显著极值淹没在大量的噪声极值中;同时由于先验知识的缺乏,采用普通滤波技术也往往不能很好的滤除噪声,反而会破坏图像的关键结构。本文提出了一种基于属性形态学分析的图像显著极值检测算法。该算法可以在不需要对图像进行滤波的前提下,从数学形态学的角度对图像极值的显著性进行计算和评估,从而能够较好地提取出显著的极值。在沉浸模拟算法的基础上,给出了基于属性形态学分析显著极值检测的快速算法实现,并将其成功应用在视觉注意选择和独立运动目标检测上。实践证明,该算法不仅具有较好的抗噪声特性,而且快速实用,具有广泛的应用价值。  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号