Ship target recognition using low resolution radar and neuralnetworks

The classification of ship targets using low resolution down-range radar profiles together with preprocessing and neural networks is investigated. An implementation of the Fourier-modified discrete Mellin transform is used as a means for extracting features which are insensitive to the aspect angle of the radar. Kohonen's self-organizing map with learning vector quantization (LVQ) is used for the classification of these feature vectors. The use of a feedforward network trained with the backpropagation algorithm is also investigated. The classification system is applied to both simulated and real data sets. Classification accuracies of up to 90% are reported for the real data, provided target aspect angle information is available to within an error not exceeding 30 deg     

Automatic target recognition using sequences of high resolutionradar range-profiles

In this paper, we address the problem of joint tracking and recognition of a target using a sequence of high resolution radar (HRR) range-profiles. The likelihood function for the scene configuration combines a dynamics-based prior on the sequence of target orientations with a likelihood for range-profiles given the target orientation. A deterministic model and a conditionally Gaussian model for range-profiles are introduced, and the likelihood functions under each model are compared. Simulations are presented demonstrating recognition of mobile aircraft and ground targets, and results showing performance of the algorithm are given in terms of the expected angular estimation error and the rate of correct recognition     

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     

Automatic target recognition of time critical moving targets using1D high range resolution (HRR) radar

Synthetic Aperture Radar (SAR) imaging and Automatic Target Recognition (ATR) of moving targets pose a significant challenge due to the inherent difficulty of focusing moving targets. As a result, ATR of moving targets has recently received increased interest. High Range Resolution (HRR) radar mode offers an approach for recognizing moving targets by forming focused HRR profiles with significantly enhanced target-to-(clutter+noise) (T/(C+N)) via Doppler filtering and/or clutter cancellation. A goal of HRR ATR transition is the implementation and evaluation of algorithms exhibiting robustness under extended operating conditions (EOC). The public domain Moving and Stationary Target Acquisition and Recognition (MSTAR) data set was used to study 1D template-based ATR development and performance. Due to the unavailability of a statistically significant moving ground target data set, this approach was taken as an interim step in assessing the separability of ground targets when using range only discriminants. This report summarizes the data and algorithm methodology, simulated performance results, and recommendations     

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     

Moving target imaging algorithm for SAR data

A digital processing algorithm for fine-resolution imaging of synthetic aperture radar (SAR) moving targets is described. The targets may have any translational and rotational motion components relative to the data collection platform. The algorithm requires the presence of up to three prominent points in the image of the target; the signals from these points provide estimates of the unknown target motion parameters. Phase compensation and data formatting based on these estimates eliminate motion-induced phase errors. This algorithm has been implemented on a VAX computer and used to process both simulated and real SAR data of moving targets. Results obtained using the simulated data are presented     

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.     

A technique for enhanced slant range resolution for SAR systems inknowledge-based environment

Synthetic Aperture Radar (SAR) is an airborne (or spaceborne) radar mapping technique for generating high resolution maps of surface target areas including terrain. High resolution is achieved by coherently combining the returns from a number of radar transmissions. The resolution of the images is determined by the parameters of the emissions, with more data giving greater resolution. A requirement of the Microwave Radar Division's SAR radar is to provide classification of targets. This paper presents a technique for enhancing slant range resolution in SAR images by dithering the carrier centre frequency of the transmitted signal. The procedure controls the radar waveforms so they will optimally perform the classification function, rather than provide an image of best quality. It is shown that a Knowledge-Based engineering approach to determining the waveform of the radar gives considerably improved performance as a classifier of targets (of large radar cross-section), even though the corresponding image is degraded     

具有自动回溯的机动目标航迹精细化分段识别

机动目标航迹分段识别是判断目标行为意图的基础,然而现有航迹分段算法对模式变化检测能力弱,难以满足机动目标航迹快速精细化分段的需求。提出双层精细化航迹分段框架,预分段层检测目标运动过程中的模式切换,确定模式变化明显的预分段区,得到目标模式变化明显区域的预分段点;再分段层对模型差异小的非预分段区航迹进行回溯迭代优化再分段,得到更为精细的分段点。该框架具有从粗到精的航迹分段处理能力,实现了对于机动目标航迹的精细化分段识别。选取两个典型的目标机动仿真场景验证了所提算法的有效性,不仅减少了迭代优化时间,而且提高了分段识别精度。     

SAR data focusing using seismic migration techniques

The focusing of synthetic-aperture-radar (SAR) data using migration techniques quite similar to those used in geophysics is treated. The algorithm presented works in the ω-k_x domain. Because time delays can be easily accommodated with phase shifts that increase linearly with ω, range migration poses no problem. The algorithm is described in plane geometry first, where range migration and phase history can be exactly matched. The effects of the sphericity of the Earth, of the Earth's rotation, and of the satellite trajectory curvature are taken into account, showing that the theoretically achievable spatial resolution is well within the requirements of present day and near future SAR missions. Terrestrial swaths as wide as 100 km can be focused simultaneously with no serious degradation. The algorithm has been tested with synthetic data, with Seasat-A data, and with airplane data (NASA-AIR). The experimental results fully support the theoretical analysis     

Remote data sensing using SAR and harmonic reradiators

In sensor networks distributed over large areas, communication by means of active transmitters on sensor nodes is inherently energy expensive and poses a significant bottleneck to achieve a long battery life. We propose modulated reradiation of radar illumination as a means to transmit information from a group of sensors to an airborne radar. This puts the communications energy burden on the radar transmitter rather than on the sensor nodes, thus increasing their battery lifetimes. To distinguish the sensor return from the clutter return, the modulation on the sensors is done by switching a nonlinear load on the sensor antenna and processing the harmonic reradiation. We present techniques to transmit information from the sensors, which use stripmap mode synthetic aperture radar (SAR) ideas to decode the information and to simultaneously obtain a geographic map of the sensor locations.     

Multiple moving target detection and trajectory estimation using a single SAR sensor

A novel methodology is presented for determining the velocity and location of multiple moving targets using a single strip-map synthetic aperture radar (SAR) sensor. The so-called azimuth position uncertainty problem is therefore solved. The method exploits the structure of the amplitude and phase modulations of the returned echo from a moving target in the Fourier domain. A crucial step in the whole processing scheme is a matched filtering, depending on the moving target parameters, that simultaneously accounts for range migration and compresses two-dimensional signatures into one-dimensional ones without losing moving target information. A generalized likelihood ratio test approach is adopted to detect moving targets and derive their trajectory parameters. The effectiveness of the method is illustrated with synthetic and real data covering a wide range of targets velocities and signal-to-clutter ratios (SCRs). Even in the case of parallel to platform moving target motion, the most unfavorable scenario, the proposed method yields good results for, roughly, SCR > 10 dB.     

Improving slant-range resolution with multiple SAR surveys

Across-track resolution of a spaceborne synthetic aperture radar (SAR) system is limited by power and data rate constraints. The authors derive and discuss a new technique for increasing the across-track resolution of objects that do not change with time, using multiple surveys of the same area from different off-nadir angles. Precise information on the spaceborne trajectories are not requested since they can be derived from SAR interferometry. Simulated data show that theoretical derivations are in good agreement with practice     

基于迁移学习的SAR目标超分辨重建

针对合成孔径雷达(SAR)目标超分辨重建问题,提出了一种基于迁移学习的超分辨方法。在光学图像梯度域中联合训练超完备字典与稀疏编码映射,利用半耦合字典联系SAR图像与光学图像,寻找SAR图像在半耦合字典下的稀疏编码,并在高分辨率字典下完成重建。结合SAR图像的先验信息,使用正则化方法对SAR目标进行特征增强。所提方法在TerraSAR-X数据和MSTAR数据上进行了仿真实验,重建结果表明,相比目前的插值方法和稀疏表示方法,所提方法空间分辨率可提高0.5~1.5个像素。正则化增强结果表明,引入稀疏先验的正则化增强能够进一步提高空间分辨率并抑制杂波比,最后分析了正则化参数的选取对图像质量的影响。     

SAR resolution in the presence of phase errors

The author analyzes the effects of phase errors on synthetic aperture radar (SAR). The theory is applied to the following question: how does the achievable resolution vary with the carrier frequency when optimum quadratic focus and/or optimum processing interval (synthetic aperture length) are used? Numerous related results are given, so that much of the material is tutorial. For phase errors corresponding to uncompensated motion, the best achievable RMS resolution with any phase error spectrum satisfies the derived equation. For motion-induced phase errors it is seen that resolution improves with increasing carrier frequency when the first term in the expression applies (e.g. for phase errors concentrated at low frequencies) and resolution is independent of carrier frequency when R δ/v/v is the smaller term (e.g. with broad band or high frequency phase errors)     

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).     

Super resolution SAR imaging via parametric spectral estimationmethods

Super resolution synthetic aperture radar (SAR) image formation via sophisticated parametric spectral estimation algorithms is considered. Parametric spectral estimation methods are devised based on parametric data models and are used to estimate the model parameters. Since SAR images rather than model parameters are often used in SAR applications, we use the parameter estimates obtained with the parametric methods to simulate data matrices of large dimensions and then use the fast Fourier transform (FFT) methods on them to generate SAR images with super resolution. Experimental examples using the MSTAR and Environmental Research Institute of Michigan (ERIM) data illustrate that robust spectral estimation algorithms can generate SAR images of higher resolution than the conventional FFT methods and enhance the dominant target features     

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