Contributions to Automatic Target Recognition Systems for Underwater Mine Classification

Combining the capability of an automated target recognition (ATR) system with the expertise of human operators has the potential to improve combined human-machine target-recognition performance. The objective of this work was to develop empirically validated guidelines for the display of information provided by an ATR system. Motivated by the premise that operators will have higher trust in an ATR system that justifies its decisions, this work explored alternative ATR displays that provided different types and amounts of information in support of the system's target decisions. Operators' usage of and preference for the displays were contrasted for low- and high-accuracy simulated ATR systems representative, respectively, of current and future technologies. Performance results suggested that the amount of supporting information that is displayed must be congruent with the ATR system's accuracy. Operators expressed a clear preference for an ATR system that provides a confidence rating for its target decisions. Based on the results design guidelines are suggested for displaying ATR information to help operators balance confidence in their own judgments with trust in the ATR's decisions.

Automatic target recognition (ATR) is a challenging task for several computer vision applications. It requires efficient, accurate, and robust methods for target detection and target identification. Deep learning has shown great success in many computer vision applications involving color RGB images. However, the performance of these networks in ATR with infrared sensor data needs further investigation. In this paper, we propose a multistage automatic target detection and recognition (ATDR) system that performs both target detection and target classification on infrared (IR) imagery using deep learning. Our system processes large IR image frames where targets take <1 % of the total number of pixels. First, we train a state-of-the-art object detector you only look once (YOLO) to localize all potential targets in the input image frame. Then, we train a convolutional neural network (CNN) to identify these detections as targets or false alarms. In this second phase, we adapt and analyze the performance of three CNN architectures: a compact and fully connected CNN, VGG16 with batch normalization, and a wide residual neural network (WRN). We also explore the use of a loss function that optimizes directly the area under the receiver operating characteristic (ROC) curve (AUC), and adapt it to our ATR application. To enhance the robustness of the proposed ATR to perturbation and variations introduced during the detection stage, we train our CNN classifiers on automatically detected targets using YOLO, in addition to ground truth bounding boxes and apply selected data augmentation techniques. To simulate real testing environments, where the spatial location of the targets within the image frame is unknown, only YOLO-detected boxes are used during validation. We evaluate our ATDR on a real benchmark dataset that includes different vehicles captured at different resolutions. Our experiments have shown that YOLO can detect most of the targets at the expense of generating a high number of false alarms. We show that the VGG-16 network with batch normalization, which is the best performing model, can correctly identify the classes of the targets, as well as classify the majority of YOLO’s false detections into an additional nontarget class. We also show that the proposed training modification to optimize an AUC-based loss function for ATR proved to be advantageous mainly in identifying difficult targets.

Low altitude, small radar cross-section (RCS), and slow speed (LSS) targets, for example small unmanned aerial vehicles (UAVs), have become increasingly significant. In this paper, we propose a new automatic target recognition (ATR) system and a complete ATR chain based on multi-dimensional features and multi-layer classifier system using L-band holographic staring radar. We consider all steps of the processing required to make a classification decision out of the raw radar data, mainly including preprocessing for the raw measured Doppler data including regularization and main frequency alignment, selection, and extraction of effective features in three dimensions of RCS, micro-Doppler, and motion, and multi-layer classifier system design. We design creatively a multi-layer classifier system based on directed acyclic graph. Helicopters, small fixed-wing, and rotary-wing UAVs, as well as birds are considered for classification, and the measured data collected by L-band radar demonstrates the effectiveness of the proposed complete ATR classification system. The results show that the ATR classification system based on multi-dimensional features and k-nearest neighbors (KNN) classifier is the best, compared with support vector machine (SVM) and back propagation (BP) neural networks, providing the capability of correct classification with a probability of around 97.62%.

Proper evaluation of a pattern recognition system in the lab is paramount to its success in the field. In most commercial pattern recognition applications, such as breast cancer detection, optical character recognition, and industrial quality assurance, the boundaries and expectation of the system are well defined. This is due, at least in part, to an excellent understanding of the problem and data space for these applications. For these functions, a method for rigorous evaluation is well understood. However, the size and complexity of the data and problem spaces for automatic target recognition (ATR) systems is enormous. The consequences are that a complete understanding of how an ATR system will perform in practice is extraordinarily difficult to estimate. Thus the act of evaluating an ATR system becomes as important as its design. This paper compiles and reports the techniques used to evaluate ATR system performance. It surveys the specific difficulties associated with ATR performance estimation as well as approaches used to mitigate these obstacles.

Performance of automatic target recognition (ATR) systems depends on numerous factors including the mission description, operating conditions, sensor modality, and ATR algorithm itself. Performance prediction models sensitive to these factors could be applied to ATR algorithm design, mission planning, sensor resource management, and data collection design for algorithm verification. Ideally, such a model would return measures of performance (MOPs) such as probability of detection (Pd), correct classification (Pc), and false alarm (Pfa), all as a function of the relevant predictor variables. Here we discuss the challenges of model-based and data-based approaches to performance prediction, concentrating especially on the synthetic aperture radar (SAR) modality. Our principal conclusion for model-based performance models (predictive models derived from fundamental physics- and statistics-based considerations) is that analytical progress can be made for performance of ATR system components, but that performance prediction for an entire ATR system under realistic conditions will likely require the combined use of Monte Carlo simulations, analytical development, and careful comparison to MOPs from real experiments. The latter are valuable for their high-fidelity, but have a limited range of applicability. Our principal conclusion for data-based performance models (that fit empirically derived MOPs) offer a potentially important means for extending the utility of empirical results. However, great care must be taken in their construction due to the necessarily sparse sampling of operating conditions, the high-dimensionality of the input space, and the diverse character of the predictor variables. Also the applicability of such models for extrapolation is an open question.

The resolution capability of imaging systems is effected by a blurring effect due to the vibration and motion recorded in the image. This disturbance is often more severe than electronic and optical limitations inherent in the system. This fact must be considered when dealing with the development and analysis of automatic target recognition (ATR) systems for military applications. The aim of this research is to analyze the influence of image vibrations and motion upon the probability of acquiring the target with an ATR system. The analysis includes factors that characterize the relationship existing between the target and its background. A high level of correlation is expected between these factors and the probability of target detection, enabling efficient performance in the prediction and evaluation of any ATR system. The results of this research can be implemented in military applications as well as in developing image restoration procedures for image-blur conditions.

Biologically motivated cross-modality sensory fusion system for automatic target recognition

: This report focuses on the development of an automatic target recognition (ATR) system using high resolution synthetic aperture radar (SAR) imagery. The system achieves 95 to 100 percent recognition rates when applied to a set of MSTAR images. Typically, the system takes less than one minute to match an input image to a candidate vehicle class with Matlab programs running on a Pentium II 300 MHz machine. Experiments based on conventional recognition techniques were conducted for comparisons. Study of persistent scattering confirms the feasibility of implementing a SAR ATR system using physical image features. A new generic vehicle model, parameterized by the length, width, and orientation of a target is used in a two-phase recognition process with hypothesis generation and verification aimed at addressing the combinatorial target recognition problem. In the hypothesis generation stage, a few likely candidate target classes are identified from a target database with positive evidence. The candidates are assessed using both positive and negative evidence in the hypothesis verification stage. Leading surface estimation, image alignment, Delaunay walk, and recognition metrics are introduced to improve performance of the SAR ATR system.

The task of object classification is complicated by variations in the three-dimensional (3D) object, which translate into distortions in 2-D images. The pattern matching for invariance classification requires a large amount of data and computation time. Proposed here is an efficient distortion invariant object classification algorithm for real-time fringe-adjusted joint transform correlator (FJTC) based automatic target recognition (ATR) system. The proposed classification technique employed fragment-based recognition approach and a new type of synthetic discriminant function (SDF) filter in the generation of distortion invariant correlation filter sets. The optoelectronic FJTC is then used to provide real-time correlation of the filter sets and input under a proper arrangement. This classification method is simple and fast and hence is relevant to be in use by real-time ATR systems. As the conclusion, simulation results are provided to prove the effectiveness of the proposed system in the classification of objects invariant to various distortions.

For the Automatic Target Recognition (ATR) algorithm, the quality of the input image sequence can be a major determining factor as to the ATR algorithm's ability to recognize an object. Based on quality, an image can be easy to recognize, barely recognizable or even mangled beyond recognition. If a determination of the image quality can be made prior to entering the ATR algorithm, then a confidence factor can be applied to the probability of recognition. This confidence factor can be used to rate sensors; to improve quality through selectively preprocessing image sequences prior to applying ATR; or to limit the problem space by determining which image sequences need not be processed by the ATR algorithm. It could even determine when human intervention is needed. To get a flavor for the scope of the image quality problem, this paper reviews analog and digital forms of image degradation. It looks at traditional quality metric approaches such as peak signal-to-noise ratio. It examines a newer metric based on human vision data, a metric introduced by the Institute for Telecommunication Sciences. These objective quality metrics can be used as confidence factors primarily in ATR systems that use image sequences degraded due to transmission systems. However, to determine the quality metric, a transmission system needs the original input image sequence and the degraded output image sequence. This paper suggests a more general approach to determining quality using analysis of spatial and temporal vectors where the original input sequence is not explicitly given. This novel approach would be useful where there is no transmission system but where the ATR system is part of the sensor, on-board a mobile platform. The results of this work are demonstrated on a few standard image sequences.

Fundamental to the model-based paradigm of an Automatic Target Recognition (ATR) system is an accurate representation (a model) of the physical objects to be recognized. Detailed CAD models of targets of interest can be created using photographs, blueprints, and other intelligence sources. When created this way, the target CAD models are necessarily specific to a particular realization of the vehicle (namely, the serial number of the vehicle from which the CAD model was validated). Under realistic battlefield conditions, variations across targets of the same type (i.e. T72) may be quite drastic and may manifest themselves as significant differences in the sensor signatures. Given this variability between targets of the same type, the example CAD model, or 'exemplar' model, may not provide an adequate representation of the vehicle across the entire class. This paper discusses the development of class models for use in a model-based ATR for synthetic aperture radar (SAR). It documents the propagation of variability information into feature uncertainty, and comments on the performance of class models in the Moving and Stationary Target Acquisition and Recognition (MSTAR) model- based ATR system.

Automatic target recognition (ATR) is an important part for many computer vision applications. Despite the extensive research which has been carried out in this area for many years, there is no ATR system which performs well on all applications. Recently, different object recognition frameworks have been proposed which yield a high performance in baseline databases. However, our experiments showed that they can fail in real-world scenarios, when dealing with a limited number of data samples. In this paper, we propose a new ATR system, based on deep convolutional neural network (DCNN), to detect the targets in forward looking infrared (FLIR) scenes and recognize their classes. In our proposed ATR framework, a fully convolutional network is trained to map the input FLIR imagery data to a fixed stride correspondingly-sized target score map. The potential targets are identified by applying a threshold on the target score map. Finally, the corresponding regions centered at these target points are fed to a DCNN to classify them into different target types while at the same time rejecting the false alarms. The proposed architecture achieves a significantly better performance in comparison with that of the state-of-the-art methods on two large FLIR image databases.

Deep neural network-based synthetic aperture radar (SAR) automatic target recognition (ATR) systems are susceptible to attack by adversarial examples, which leads to misclassification by the SAR ATR system, resulting in theoretical model robustness problems and security problems in practice. Inspired by optical images, current SAR ATR adversarial example generation is performed in the image domain. However, the imaging principle of SAR images is based on the imaging of the echo signals interacting between the SAR and objects. Generating adversarial examples only in the image domain cannot change the physical world to achieve adversarial attacks. To solve these problems, this article proposes a framework for generating SAR adversarial examples in a 3D physical scene. First, adversarial attacks are implemented in the 2D image space, and the perturbation in the image space is converted into simulated rays that constitute SAR images through backpropagation optimization methods. The mapping between the simulated rays constituting SAR images and the 3D model is established through coordinate transformation, and point correspondence to triangular faces and intensity values to texture parameters are established. Thus, the simulated rays constituting SAR images are mapped to the 3D model, and the perturbation in the 2D image space is converted back to the 3D physical space to obtain the position and intensity of the perturbation in the 3D physical space, thereby achieving physical adversarial attacks. The experimental results show that our attack method can effectively perform SAR adversarial attacks in the physical world. In the digital world, we achieved an average fooling rate of up to 99.02% for three objects in six classification networks. In the physical world, we achieved an average fooling rate of up to 97.87% for these objects, with a certain degree of transferability across the six different network architectures. To the best of our knowledge, this is the first work to implement physical attacks in a full physical simulation condition. Our research establishes a theoretical foundation for the future concealment of SAR targets in practical settings and offers valuable insights for enhancing the attack and defense capabilities of subsequent DNNs in SAR ATR systems.

Deep Neural Networks (DNNs) based Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) systems have shown to be highly vulnerable to adversarial perturbations that are deliberately designed yet almost imperceptible but can bias DNN inference when added to targeted objects. This leads to serious safety concerns when applying DNNs to high-stakes SAR ATR applications. Therefore, enhancing the adversarial robustness of DNNs is essential for applying DNNs to modern real-world SAR ATR systems. Toward building more robust DNN-based SAR ATR models, this article explores the domain knowledge of SAR imaging process and proposes a novel Scattering Model Guided Adversarial Attack (SMGAA) algorithm which can generate adversarial perturbations in the form of electromagnetic scattering response (called adversarial scatterers). The proposed SMGAA consists of two parts: 1) a parametric scattering model and corresponding imaging method and 2) a customized gradient-based optimization algorithm. First, we introduce the effective Attributed Scattering Center Model (ASCM) and a general imaging method to describe the scattering behavior of typical geometric structures in the SAR imaging process. By further devising several strategies to take the domain knowledge of SAR target images into account and relax the greedy search procedure, the proposed method does not need to be prudentially finetuned, and can efficiently find the effective ASCM parameters to fool the SAR classifiers and facilitate the robust model training. Comprehensive evaluations on the MSTAR dataset show that the adversarial scatterers generated by SMGAA are more robust to perturbations and transformations in the SAR processing chain than the currently studied attacks, and are effective to construct a defensive model against the malicious scatterers.

The use of robust and representative synthetic imagery data to test and evaluate automatic target recognition (ATR) systems has long been desired but generally considered beyond the current state of the art. The use of synthetic data is investigated here to calculate upper bounds on potential ATR system performance. This paper presents the use of synthetically generated imagery templates as a means of developing upper bounds of ATR performance for laser radar based seekers. This approach employs a synthetic scene generation capability and integrates it with error models that represent decrements in performance due to resolution, noise and geometric distortion resulting from the sensing process. This paper describes the modeling approach take and presents preliminary results. The model is currently undergoing testing against real imagery and is being used to select test sets to more effectively evaluate ATR's.