Stationary Target Research Articles

Multilevel Adaptive Knowledge Distillation Network for Incremental SAR Target Recognition

The existing synthetic aperture radar (SAR) automatic target recognition (ATR) methods have shown impressive results in static scenarios, yet the performance drops sharply as new categories of targets are continuously increased. In response to this problem, this letter proposes a novel ATR method named multi-level adaptive knowledge distillation network (MLAKDN) to achieve incremental SAR target recognition. To be specific, an adaptive weighted distillation strategy is first proposed, which can alleviate the model from forgetting the knowledge of old categories by distilling multi-stage soft label information of old categories at the classification level. Then, a feature distillation method based on gradient maximum criterion is developed to filter and distill discriminative features, so as to further recall more knowledge of old categories at the feature level. Meanwhile, a model rebalancing technique is designed to effectively strike the balance of the model on new categories and old categories. Finally, a weighted incremental classification loss is presented to train the whole model. Experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset and the synthetic and measured paired labeled experiment (SAMPLE) dataset illustrate that the proposed method is superior to some state-of-the-arts for incremental SAR target recognition tasks.

Recognition of Deformation Military Targets in the Complex Scenes via MiniSAR Submeter Images With FASAR-Net

Ground armored weapons have a high detection value in military operations. Satellite synthetic aperture radar (SAR) cannot accurately detect military targets with meter-level sizes limited by resolution of sensors. Airborne SAR have strict experimental conditions and cannot be applied in actual battlefield environments. MiniSAR sensors, which combine the advantages of submeter-level ultrahigh resolutions and flexible flight, play a crucial role in recognizing military targets. In this paper, various small military targets in real complex ground scenarios are detected with the MiniSAR of NUAA. However, there are still two difficulties. First, because of a limitation in the number of flight circles, the number of obtainable military target samples is not sufficient to adapt to the traditional deep learning methods that rely on a large number of image samples. Second, due to the imaging systems and different depression angle of MiniSAR, the SAR images of MiniSAR suffer from the same deformation challenge as the moving and stationary target acquisition and recognition (Mstar) with high depression angle. To address these two challenges, we propose a FASAR-Net framework based on few-shot learning with meta learning and adversarial domain learning, combined with the inherent scattering features of the SAR targets. Furthermore, we validate the reliability and accuracy of this algorithm on Mstar and our datasets, and the result of recognizing small SAR targets is compared with our algorithm and other classical algorithms. We conclude that the proposed algorithm has high accuracy in the recognition of the deformation small targets under the few sample condition.

Zero-Shot SAR Target Recognition Based on Classification Assistance

As one of main active learning methods, zero-shot target recognition with synthetic aperture radar (SAR) data has received considerable attention in recent years. Its goal is to distinguish new targets from the known classes without requiring additional training data. Existing zero-shot learning (ZSL) methods perform well on optical targets, but they fail to recognize zero-shot SAR targets. Due to the strong similarity of SAR targets between different classes, the ZSL task usually suffers from the distribution concentration problem. To tackle this problem, a Dual Branch Auto-Encoder (DBAE) network is proposed in this letter. DBAE effectively alleviates the distribution concentration problem by adding a classification assistance net. Its dual branch structure is specially designed for further improving the intra-class similarity and inter-class dissimilarity of SAR targets in the embedding space. By training with the defined hybrid loss function, DBAE automatically builds a stable embedding space. Extensive experiments on the public data set of Moving and Stationary Target Acquisition and Recognition (MSTAR) show that DBAE is of rational design and provides better or comparable ZSL recognition results.

Contrastive Feature Disentangling for Partial Aspect Angles SAR Noncooperative Target Recognition

Deep learning algorithms have achieved state-of-the-art progress in synthetic aperture radar (SAR) automatic target recognition (ATR) tasks. They theoretically assume that training and test samples are independent and identically distributed (i.i.d.) for generalization, but it is intractable for practical ATR scenarios. In this paper, we propose a novel contrastive feature disentangling framework termed ConFeDent to learn features with improved generalization performance under a condition of a weaker distribution consistency. More specifically, ConFeDent aims to describe the semantic interactions between two arbitrary SAR training samples instead of treating them independently. It can implicitly disentangle features encoding the pose and identity knowledge from the whole samples with a semi-parametric geometric transformation model and a second-order energy model. In particular, except for the identity label, we use deductive-based geometry knowledge as supervision to teach the model to learn the concept of aspect angle variation. A progressively amortized inference scheme is constructed for efficient feature learning and recognition in an end-to-end manner. Finally, we further release a strengthened version, called ConFeDent+, which can explicitly utilize and learn more information from cross-category samples. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) benchmark demonstrate the effectiveness of our proposed models in the SAR ATR. In particular, we validate the algorithms in a more challenging scenario where the range of aspect angles for training and testing samples is permitted to be disparate. Our model can achieve much higher recognition accuracy than other SAR ATR algorithms.

Multi-Agent Exploration-Based Search for an Unknown Number of Targets

This paper presents an active sensor fusion technique for multiple mobile agents (robots) to detect an unknown number of static targets at unknown positions. To process and fuse sensor measurements from the agents, we use a random finite set formulation with an iterated-corrector probability hypothesis density filter. Our main contribution is to introduce two different multi-agent planners to quickly find the targets. The planners make greedy decisions for the next state of each agent by maximizing an objective function consisting of target refinement and exploration components. We demonstrate the performance of our approach through a series of simulations using homogeneous and heterogeneous agents. The results show that our framework works better than a lawnmower baseline, and that a centralized version of the planner works best.

Image-Based Radar Cross Section Synthesis for a Cluster of Multiple Static Targets

This study proposes a novel image-based method for radar cross-section (RCS) prediction of a cluster of multiple static targets by synthesizing replicas of an original radar image. In this approach, we first measured the near-field backscattering of a target and reconstructed a corresponding radar image. Subsequently, modified copies of this image with rotation, translation, and spatial filtering were generated according to the predefined desired arrangement, and they were coherently summed to create a single synthesized image in which all scattering contributions contained in the modified images were virtually included. Finally, the synthesized image was utilized to predict the far-field RCS of multiple targets based on the theory of image-based near-field-to-far-field transformation (NFFFT). By employing the proposed algorithm, we can avoid building multiple test targets, resulting in reduced production costs. Moreover, we can easily test several different experimental layouts for multiple targets without repeating real measurements. Numerical simulations and experiments are conducted to demonstrate the validity of the proposed image-based RCS synthesis. The measurement results show that the proposed approach is valid when the multiple scattering between targets can be ignored, and the shadowing, which refers to the effect that a target is masked by another target, is insignificant.

МОДЕЛЬ АВТОМАТИЗИРОВАННОГО РАСПРЕДЕЛЕНИЯ В ЗАДАЧЕ ГРУППОВОГО ПРЕСЛЕДОВАНИЯ С ЗАЩИТНИКАМИ

The article examines a computer model of a quasidiscrete group pursuit game with pursuers and defenders, whose aim is to reach static targets. Several pursuers may reach one target at different time periods. In order to win, at least one pursuer must reach the target, while defenders must eliminate all pursuers to succeed. A model has a unified environment that detects the pursuer as soon as he crosses it. One defender is assigned to the detected pursuer by several optimization criteria.

Trajectory Planning and Control of Autonomous Vehicles for Static Vehicle Avoidance in Dynamic Traffic Environments

This paper presents a trajectory planning and control algorithm of autonomous vehicles for static traffic agent avoidance in multi vehicle urban environments. In urban autonomous driving, the subject vehicle encounters diverse traffic scenes including lane changing, intersection driving, and illegally parked static vehicle avoidance. Among these, dealing with illegally parked static target vehicle is a major challenge to urban autonomous driving due to large velocity difference between ego and target vehicles and interactions with surrounding vehicles. In order to tackle this problem, we introduce a decision making and motion planning framework for static vehicle avoidance considering both the preceding static vehicles and surrounding vehicles. Among the surrounding vehicles, the set of objects with potential collision risk is selected based on the lane boundaries and road geometry. Then, the driving status of the selected target vehicles are classified as normal driving vehicles or parked vehicles based on their longitudinal speed, lateral position and lateral space occupancy. For the preceding parked vehicles, the motion planner generates lateral and longitudinal evasive motion, by taking side lane traffic flow and risk into account. The desired motion is executed by applying optimized control inputs computed by lateral and longitudinal model predictive controllers. The performance validation of the proposed algorithm has been conducted with actual autonomous test vehicles. The test results confirmed that the proposed algorithm can successfully perform evasive maneuvers on urban roads to ensure safety and mitigate collision risk with the surrounding traffic agents.

Functional gradation of aluminum alloy by impact of ballistics as severe plastic deformation process

In the present effort, impact of bullets fired at high speeds on a stationary target was used as a high strain-rate plastic deformation method to generate Functionally Graded Materials (FGMs). The bullet-shaped Aluminum alloy Al5052 specimens impacted the UHMWPE target at different projectile velocities ranging from 100 m/s to 750 m/s, to study the effect of the impact speed. Moreover, few of the projectiles impacted along the longitudinal axis whereas the remaining projectiles impacted with an obliquity to investigate the effect of leading-edge shape. The metallography of the projectile specimens fired at 750 m/s shows grain refinement from 70 ± 3 μm at the rear/ un-deformed point to 10 ± 1 μm at the front/ severely deformed point which is in the impact zone. Similar but of less magnitude variations were observed at other impact speeds also. The hardness variation was 45% (70 ± 3 HV at the rear surface to 102 ± 2 HV at the front face) at 750 m/s. Moreover, least variation in hardness and grain size was observed for projectile impacted at lowest velocity tested (100 m/s). Further, functionality in hardness and grain refinement was seen in graded direction due to shape of the projectile specimens, impact velocity, and target material. Depending upon the impact angles, axisymmetric (impacted normal to the longitudinal axis) or unsymmetrical (impacted at an angle) variation of grain refinement and hardness was observed.

Analysis of a Hybrid Guided Bomb Control System while Self-guided to a Ground Target

This article presents a mathematical model and an algorithm for controlling a guided bomb to a moving and a stationary ground target. The target path was determined from the kinematic relationships of the reciprocal movement of the bomb and the ground target, based on the proportional approximation method. The analysed control system used sliding control, with the PID algorithm to determine the sliding plane. Three types of sliding planes were considered. In addition, a comparative analysis was carried out for three types of controllers: classic PID, sliding and hybrid. Selected results of the computer simulation are listed.

Real-Time Cell Growth Control Using a Lactate-Based Model Predictive Controller

Providing a cost-efficient feeding strategy for cell expansion processes remains a challenging task due to, among other factors, donor variability. The current method to use a fixed medium replacement strategy for all cell batches results often in either over- or underfeeding these cells. In order to take into account the individual needs of the cells, a model predictive controller was developed in this work. Reference experiments were performed by expanding human periosteum derived progenitor cells (hPDCs) in tissue flasks to acquire reference data. With these data, a time-variant prediction model was identified to describe the relation between the accumulated medium replaced as the control input and the accumulated lactate produced as the process output. Several forecast methods to predict the cell growth process were designed using multiple collected datasets by applying transfer function models or machine learning. The first controller experiment was performed using the accumulated lactate values from the reference experiment as a static target function over time, resulting in over- or underfeeding the cells. The second controller experiment used a time-adaptive target function by combining reference data as well as current measured real-time data, without over- or underfeeding the cells.

WiCPD: Wireless Child Presence Detection System for Smart Cars

Child presence detection (CPD) is becoming a regulatory requirement for car manufacturers to save children’s lives when they are left alone in unattended vehicles. However, most of the existing solutions require dedicated devices and suffer from limited accuracy and coverage. In this article, we build WiCPD, the first-of-its-kind in-car CPD system using commodity Wi-Fi, which can cover the entire interior of a car with no blind spot. First, we introduce a statistical electromagnetic model which accounts for the impact of motion on all the multipaths inside a car, followed by a motion statistics metric indicating the ambient motion intensity and a signal-to-noise-ratio (SNR) boosting scheme to extract the minute chest movement. Then, we design a unified CPD framework consisting of three target detector modules, including a motion target detector to detect a child in motion/awake, a stationary target detector to detect a stationary/sleeping child, and a transition target detector to detect a sleeping child with sporadic motion who is missed by both the motion and stationary target detectors. We implement a real-time WiCPD system by using commercial Wi-Fi chipsets, deploy it over 20 different cars, and collect data for multiple children aging from 4 to 50 months. The results show that WiCPD can achieve 100% detection rate within 8 s when the child is awake/in-motion and 96.56% detection rate within 20 s for a static/sleeping child. Extensive experiments also demonstrate that WiCPD can be easily deployed in minutes without calibration and enjoys very low CPU and memory consumption, thus promising a practical candidate for CPD applications.

Optimal Geometries for AOA Localization in the Bayesian Sense

This paper considers the optimal sensor placement problem for angle-of-arrival (AOA) target localization in the 2D plane with a Gaussian prior. Optimal sensor locations are analytically determined for a single AOA sensor using the D- and A-optimality criteria and an approximation of the Bayesian Fisher information matrix (BFIM). Optimal sensor placement is shown to align with the minor axis of the prior covariance error ellipse for both optimality criteria. The approximate BFIM is argued to be valid for a sufficiently small prior covariance compared with the target range. Optimal sensor placement results obtained for Bayesian target localization are extended to manoeuvring target tracking. For sensor trajectory optimization subject to turn-rate constraints, numerical search methods based on the D- and A-optimality criteria as well as a new closed-form projection algorithm that aims to achieve alignment with the minor axis of the prior error ellipse are proposed. It is observed that the two optimality criteria generate significantly different optimal sensor trajectories despite having the same optimal sensor placement for the localization of a stationary target. Analysis results and the performance of the sensor trajectory optimization methods are demonstrated with simulation examples. It is observed that the new closed-form projection algorithm achieves superior tracking performance compared with the two numerical search methods.

Multisensor Estimation Fusion on Statistical Manifold.

In the paper, we characterize local estimates from multiple distributed sensors as posterior probability densities, which are assumed to belong to a common parametric family. Adopting the information-geometric viewpoint, we consider such family as a Riemannian manifold endowed with the Fisher metric, and then formulate the fused density as an informative barycenter through minimizing the sum of its geodesic distances to all local posterior densities. Under the assumption of multivariate elliptical distribution (MED), two fusion methods are developed by using the minimal Manhattan distance instead of the geodesic distance on the manifold of MEDs, which both have the same mean estimation fusion, but different covariance estimation fusions. One obtains the fused covariance estimate by a robust fixed point iterative algorithm with theoretical convergence, and the other provides an explicit expression for the fused covariance estimate. At different heavy-tailed levels, the fusion results of two local estimates for a static target display that the two methods achieve a better approximate of the informative barycenter than some existing fusion methods. An application to distributed estimation fusion for dynamic systems with heavy-tailed process and observation noises is provided to demonstrate the performance of the two proposed fusion algorithms.

New Result on Interception of Stationary Targets at Arbitrary Time-Varying Speed

This paper develops a novel approach and some main results on the varying-speed missile guided by pure proportional navigation (PPN) against a stationary target in the planar interception problem. The missile kinematic equation is established in the arc-length domain based on the differential geometry theory, which eliminates the influence of time-varying missile speed. Then, the closed-form solutions of line-of-sight (LOS) rate, leading angle, closing speed, and curvature command are derived in the arc-length domain. The performance of the varying-speed missile is analyzed, including the maximum relative distance, maximum curvature command, accurate path-to-go, and curvature increment. Additionally, the capture region is obtained considering the missile maneuvering acceleration limit. These new theoretical results could be extended to improve the performance of existing guidance laws designed under the constant-speed assumption.

High-Precision Aircraft Guidance System with Axial Acceleration Self-Tuning

Creation of aircraft control systems that provide high quality guidance is an urgent task associated with increasing efficiency of the modern missile systems. Classical autonomous guidance systems without integration with any other external correction systems are making it impossible to ensure high-precision target engagement. An approach based on the use of adaptive guidance system is proposed. Besides, an approach to synthesis and analysis of the self-tuning aircraft control system that implements terminal homing is illustrated. A technique for forming the control system structure is presented ensuring the control quality constant level in all operating modes due to self-tuning of the constituent elements variable coefficients. Structural schemes and control equations were determined to correct the aircraft flight. Implementation of the developed technique on board the aircraft is proposed determining relationship between the aircraft control system parameters and the apparent acceleration. Adaptive system operation is demonstrated on a typical model of the aircraft flying in the atmosphere with guidance at the stationary target. Results of numerical simulation are presented, and high efficiency of the developed technique is revealed

Localization and Prediction of Visual Targets' Position in Immersive Virtual Reality

Abstract Modern driver-assist and monitoring systems are severely limited by the lack of a precise understanding of how humans localize and predict the position of neighboring road users. Virtual Reality (VR) is a cost-efficient means to investigate these matters. However, human perception works differently in reality and in immersive virtual environments, with visible differences even between different VR environments. Therefore, when exploring human perception, the relevant perceptive parameters should first be characterized in the specific VR environment. In this paper, we report the results of two experiments that were designed to assess localization and prediction accuracy of static and moving visual targets in a VR setup developed using broadly available hardware and software solutions. Results of the first experiment provide a reference measure of the significant effect that distance and eccentricity have on localization error for static visual targets, while the second experiment shows the effect of time variables and contextual information on the localization accuracy of moving targets. These results provide a solid basis to test in VR the effects of different ergonomics and driver-vehicle interaction designs on perception accuracy.

Time Difference of Arrival Estimation of Stationary Targets Utilizing Deep Neural Network

Time difference of arrival (TDOA) is widely used in the field of passive location because of its flexible base station deployment and simple principle. However, when solving the solution of stationary targets position, the traditional method, such as the two-stage weighted least squares (TSWLS) algorithm, is easily affected by noise, and cannot achieve good localization results in practical situations. To solve this problem, we propose a deep neural network (DNN) for TDOA estimation of stationary targets. First, a large number of simulation samples are generated according to the TDOA model. Each sample contains the time difference from each secondary base station to the main base station, the error of time difference, and the real three-dimensional (3-D) coordinates of the targets. Next, a suitable DNN architecture is designed to solve the solution of the stationary target position. The simulation results prove that the method proposed herein outperforms TSWLS for multiple base stations based on the TDOA model.

Three-Dimensional Impact Angle and Time Control Guidance Law Based on Two-Stage Strategy

In this article, a 3-D nonlinear guidance law is developed for attacking a stationary target with desired impact angle and time. The guidance law is divided into two stages—impact angle control guidance (IACG) and proportional navigation guidance (PNG). In the IACG stage, a sliding-mode guidance law is established to guarantee the satisfaction of the impact angle constraint, and in the second stage, the 3-D PNG law is applied to ensure zero miss distance. The switch between the IACG and the PNG stages is determined by a guidance parameter related to the impact time constraint. By the virtue of Newton iteration method, an appropriate guidance parameter is obtained by solving an implicit nonlinear equality after a small number of iterations. Several numerical simulations are conducted to verify the feasibility and effectiveness of the proposed guidance law under different scenarios.

Multivariable Decoupling and Nonlinear Correction Method for Image-Based Closed-Loop Tracking of the Risley Prisms System.

Image-based closed-loop tracking (IBCLT) is an important part of the process of target tracking. The Risley prism system has a unique advantage in improving the target tracking ability because of its compact and lightweight structure. Compared with traditional target tracking equipment, the Risley prism system has two difficulties in the process of IBCLT. First, the Risley prism is a complex coupling system of double input and double output. Second, the Risley prism itself is a nonlinear system. These problems lead to decrease in dynamic response and inconsistent target tracking capabilities. Thus, this paper proposes a method to implement multivariable decoupling and reduce the nonlinear effect. First, the boresight error of IBCLT is decoupled to the azimuth and elevation directions by the rotation matrix error-decoupling (RMED) method. Second, the gains of IBCLT in azimuth and elevation directions are independent variables that comes from two functions of the target elevation angle. The experimental results show that the IBCLT error deviation of different static targets in the field of view is within 0.025 arcsec, which is 70% lower compared with the fixed gain method. Furthermore, the steady-state error deviation of moving targets is controlled within 2.5 arcsec. These experimental results prove the feasibility and effectiveness of the proposed method.