一种图斑特征引导的感知分组视觉注意模型

 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。     

基于注意力YOLO-V3的合成孔径雷达舰船检测识别一体化方法

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。     

Improved SAR target detection via extended fractal features

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     

Predicting an upper bound on SAR ATR performance

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     

A Model for Generating Synthetic VHF SAR Forest Clutter Images

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.     

New SAR Processor Based on Matched Subspace Detectors

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.     

无人机载多传感器图像融合评述

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。     

基于深度卷积网络的SAR图像目标检测识别

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。     

OGSRN: Optical-guided super-resolution network for SAR image

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...     

基于注意力机制的实例分割算法

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.