Superresolution HRR ATR with high definition vector imaging

A new 1-D template-based automatic target recognition (ATR) algorithm is developed and tested on high range resolution (HRR) profiles formed from synthetic aperture radar (SAR) images of targets taken from the Moving and Stationary Target Acquisition and Recognition (MSTAR) data set. In this work, a superresolution technique known as High Definition Vector Imaging (HDVI) is applied to the HRR profiles before the profiles are passed through ATR classification. The new I-D ATR system using HDVI demonstrates significantly improved target recognition compared with previous I-D ATR systems that use conventional image processing techniques. This improvement in target recognition is quantified by improvement in probability of correct classification (PCC). More importantly, the application of HDVI to HRR profiles helps to maintain the same ATR performance with reduced radar resource requirements     

Feature enhancement and ATR performance using nonquadratic optimization-based SAR imaging

We present an evaluation of the impact of a recently proposed synthetic aperture radar (SAR) imaging technique on feature enhancement and automatic target recognition (ATR) performance. This image formation technique is based on nonquadratic optimization, and the images it produces appear to exhibit enhanced features. We quantify such feature enhancement through a number of criteria. The findings of our analysis indicate that the new feature-enhanced SAR image formation method provides images with higher resolution of scatterers, and better separability of different regions as compared with conventional SAR images. We also provide an ATR-based evaluation. We run recognition experiments using conventional and feature-enhanced SAR images of military targets, with three different classifiers. The first classifier is template based. The second classifier makes a decision through a likelihood test, based on Gaussian models for reflectivities. The third classifier is based on extracted locations of the dominant target scatterers. The experimental results demonstrate that the new feature-enhanced SAR imaging method can improve the recognition performance, especially in scenarios involving reduced data quality or quantity.     

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     

Performance of 10- and 20-target MSE classifiers

MIT Lincoln Laboratory is responsible for developing the ATR (automatic target recognition) system for the DARPA-sponsored SAIP program; the baseline ATR system recognizes 10 GOB (ground order of battle) targets; the enhanced version of SAIP requires the ATR system to recognize 20 GOB targets. This paper presents ATR performance results for 10- and 20-target mean square error (MSE) classifiers using high-resolution SAR (synthetic aperture radar) imagery.     

Performance complexity study of several approaches to automatictarget recognition from SAR images

A framework which allows for the direct comparison of alternate approaches to automatic target recognition (ATR) from synthetic aperture radar (SAR) images is described and applied to variants of several ATR algorithms. This framework allows comparisons to be made on an even footing while minimizing the impact of implementation details and accounts for variation in image sizes, in angular resolution, and in the sizes of orientation windows used for training. Alternate approaches to ATR are characterized in terms of the best achievable performance as a function of the complexity of the model parameter database. Several approaches to ATR from SAR images are described and the performance achievable by each for a range of database complexities is studied and compared. These approaches are based on a likelihood test under a conditionally Gaussian model, log-magnitude least squared error, and quarter power least squared error. All approaches are evaluated for a wide range of parameterizations and the dependence on these parameters of both the resulting performance and the resulting database complexity is explored. Databases for all of the approaches are trained using identical sets of images and their performance is assessed under identical testing scenarios in terms of probability of correct classification, confusion matrices, and orientation estimation error. The results indicate that the conditionally Gaussian approach outperforms the other two approaches on average for both target recognition and orientation estimation, that accounting for radar power fluctuation improves performance for all three methods, and that the conditionally Gaussian approach normalized for power delivers average performance that is equal or superior to all other considered approaches     

A new approach to automatic target recognition

The fundamental problems of automatic target recognition (ATR) are discussed. A new approach to ATR is suggested that includes: a new method of scoring ATR performance, a new concept of artificial images, a new method called probing for extracting target signature knowledge from image experts, and suggestions for coping with the problem of insufficient test data and algorithm obsolescence     

一种提高SAR目标识别率的有效方法

在合成孔径雷达自动目标识别SAR ATR中，SAR像的预处理是提高识别率的关键技术之一。给出了一种简单有效的SAR图像预处理方法，该方法首先对SAR目标像进行对数变换后，再做傅立叶变换。经预处理后的SAR像用支持矢量机SVM分类器进行目标识别。实验结果表明：本方法不但有效地提高了目标识别率，而且保证了目标的平移不变性并具有良好的推广能力。     

A multiresolution approach to discrimination in SAR imagery

We develop and test a new algorithm for discriminating man-made objects from natural clutter in synthetic-aperture radar (SAR) imagery. This algorithm exploits characteristic variations in speckle pattern as image resolution is varied from course to fine. We model these variations as an autoregression in scale, and then use the autoregressive model to define a multiresolution log-likelihood ratio discriminant. We incorporate this discriminant into the existing Lincoln Laboratory SAR system for automatic target recognition (ATR), and test the augmented system by applying it to millimeter-wave SAR imagery having 0.3 m resolution and representing 56 square kilometers of terrain. At a probability of detection of 0.95, the addition of the multiresolution discriminant reduces the number of natural-clutter false alarms by a factor of six.     

Efficient ATR using compression

We examine various model-based automatic target recognition (MBATR) classifiers to investigate the utility of model-catalog compression realized via signal-vector quantization (VQ) and feature extraction. We specifically investigate the impact of various compression rates and common automatic target recognition (ATR) scenario variations such as noise and occlusion through simulations on high-range resolution (HRR) radar and synthetic aperture radar (SAR) data. For this data, we show that significant computational savings are possible for modest decreases in classification performance.     

Effects of polarization and resolution on SAR ATR

Lincoln Laboratory is investigating the detection and classification of stationary ground targets using high resolution, fully polarimetric, synthetic aperture radar (SAR) imagery. A study is summarized in which data collected by the Lincoln Laboratory 33 GHz SAR were used to perform a comprehensive comparison of automatic target recognition (ATR) performance for several polarization/resolution combinations. The Lincoln Laboratory baseline ATR algorithm suite was used, and was optimized for each polarization/resolution case. Both the HH polarization alone and the optimal combination of HH, HV, and VV were evaluated; the resolutions evaluated were 1 ft/spl times/1 ft and 1 m/spl times/1 m. The data set used for this study contained approximately 74 km/sup 2/ of clutter (56 km/sup 2/ of mixed clutter plus 18 km/sup 2/ of highly cultural clutter) and 136 tactical target images (divided equally between tanks and howitzers).     

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.     

Automatic target recognition for hyperspectral imagery using high-order statistics

Due to recent advances in hyperspectral imaging sensors many subtle unknown signal sources that cannot be resolved by multispectral sensors can be now uncovered for target detection, discrimination, and identification. Because the information about such sources is generally not available, automatic target recognition (ATR) presents a great challenge to hyperspectral image analysts. Many approaches developed for ATR are based on second-order statistics in the past years. This paper investigates ATR techniques using high order statistics. For ATR in hyperspectral imagery, most interesting targets usually occur with low probabilities and small population and they generally cannot be described by second-order statistics. Under such circumstances, using high-order statistics to perform target detection have been shown by experiments in this paper to be more effective than using second order statistics. In order to further address a challenging issue in determining the number of signal sources needed to be detected, a recently developed concept of virtual dimensionality (VD) is used to estimate this number. The experiments demonstrate that using high-order statistics-based techniques in conjunction with the VD to perform ATR are indeed very effective     

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。     

Image understanding research for automatic target recognition

Automatic target recognition (ATR) is an important capability for defense applications. Many aspects of image understanding (IU) research are traditionally used to solve ATR problems. The authors discuss ATR applications and problems in developing real-world ATR systems and present the status of technology for these systems. They identify several IU problems that need to be resolved in order to enhance the effectiveness of ATR-based weapon systems. They conclude that technological gains in developing robust ATR systems will lead to significant advances in many other areas of applications of image understanding     

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。     

Adaptive boosting for SAR automatic target recognition

The paper proposed a novel automatic target recognition (ATR) system for classification of three types of ground vehicles in the moving and stationary target acquisition and recognition (MSTAR) public release database. First MSTAR image chips are represented as fine and raw feature vectors, where raw features compensate for the target pose estimation error that corrupts fine image features. Then, the chips are classified by using the adaptive boosting (AdaBoost) algorithm with the radial basis function (RBF) network as the base learner. Since the RBF network is a binary classifier, the multiclass problem was decomposed into a set of binary ones through the error-correcting output codes (ECOC) method, specifying a dictionary of code words for the set of three possible classes. AdaBoost combines the classification results of the RBF network for each binary problem into a code word, which is then "decoded" as one of the code words (i.e., ground-vehicle classes) in the specified dictionary. Along with classification, within the AdaBoost framework, we also conduct efficient fusion of the fine and raw image-feature vectors. The results of large-scale experiments demonstrate that our ATR scheme outperforms the state-of-the-art systems reported in the literature     

Support vector machines for SAR automatic target recognition

Algorithms that produce classifiers with large margins, such as support vector machines (SVMs), AdaBoost, etc, are receiving more and more attention in the literature. A real application of SVMs for synthetic aperture radar automatic target recognition (SAR/ATR) is presented and the result is compared with conventional classifiers. The SVMs are tested for classification both in closed and open sets (recognition). Experimental results showed that SVMs outperform conventional classifiers in target classification. Moreover, SVMs with the Gaussian kernels are able to form a local “bounded” decision region around each class that presents better rejection to confusers     

High Range Resolution Profiles as Motion-Invariant Features for Moving Ground Targets Identification in SAR-Based Automatic Target Recognition

A quantitative model analysis is presented to justify the extraction of high range resolution (HRR) profiles from synthetic aperture radar (SAR) images as motion-invariant features for identifying moving ground targets. A comparative study is conducted to assess the effectiveness in the identification process between using HRR profiles and SAR images as target signatures. The results indicate that HRR profiles are just as viable as SAR image for identification. Furthermore, a score-level multi-look fusion identification method has been investigated. It is found that a correct accurate identification rate of greater than 99 percent, a low false alarm rate, and a high level of identification confidence can be achieved, providing very robust performance.     

Automatic spectral target recognition in hyperspectral imagery

Automatic target recognition (ATR) in hyperspectral imagery is a challenging problem due to recent advances of remote sensing instruments which have significantly improved sensor's spectral resolution. As a result, small and subtle targets can be uncovered and extracted from image scenes, which may not be identified by prior knowledge. In particular, when target size is smaller than pixel resolution, target recognition must be carried out at subpixel level. Under such circumstance, traditional spatial-based image processing techniques are generally not applicable and may not perform well if they are applied. The work presented here investigates this issue and develops spectral-based algorithms for automatic spectral target recognition (ASTR) in hyperspectral imagery with no required a priori knowledge, specifically, in reconnaissance and surveillance applications. The proposed ASTR consists of two stage processes, automatic target generation process (ATGP) followed by target classification process (TCP). The ATGP generates a set of targets from image data in an unsupervised manner which will subsequently be classified by the TCP. Depending upon how an initial target is selected in ATGP, two versions of the ASTR can be implemented, referred to as desired target detection and classification algorithm (DTDCA) and automatic target detection and classification algorithm (ATDCA). The former can be used to search for a specific target in unknown scenes while the latter can be used to detect anomalies in blind environments. In order to evaluate their performance, a comparative and quantitative study using real hyperspectral images is conducted for analysis.