Target Tracking Applications Research Articles

Integrating deep learning in target tracking applications, as enabler of control systems

Integrating deep learning in target tracking applications, as enabler of control systems

A Robust and Efficient Cubature Kalman filter based on the Variation Bayesian Method and Its Application in Target Tracking

Abstract This paper proposes a robust cubature Kalman filter (CKF) for nonlinear state-space models with unknown state and measurement noise covariance matrix (MNCM). This paper studies situations in which sensors are independent of each other. Therefore, the unknown measurement noise variance is modeled as an unknown inverse-Gamma (IG) distribution. The Gaussian-Student-t-inverse-Wishart mixture distribution (GSTIW) is used to model the one-step prediction distribution. Modeling generates a large number of unknown parameters. Therefore, this article adopts the statistical linearization method to linearize the observation function and then estimates the state and parameters separately to reduce the computational burden of estimating unknown parameters, significantly improving the algorithm's efficiency. Finally, using the variational Bayesian (VB) method, a novel and efficient robust cubature Kalman filter based on the IG distribution and GSTIW mixture distributions (IG-GSTIW-CKF) is obtained. Simulation and experimental results show that the proposed method has better estimation accuracy than several advanced algorithms when sensors are independent. In addition, the efficiency of the proposed algorithm is significantly higher than that of other CKF-based methods.

Adaptive horizon size moving horizon estimation with unknown noise statistical properties

Abstract Moving horizon estimation (MHE) is an effective technique for state estimation. It formulates state estimation as an optimization problem over a finite time interval and is characterized by inherent robustness, flexibility, and explicit constraint handling capabilities. The horizon size is a crucial parameter influencing the estimation performance of MHE. However, the selection of the horizon size remains an open research question in the field of MHE. In this paper, we propose a novel adaptive horizon size MHE strategy that dynamically adjusts the horizon size based on the value of the objective function. This approach aims to improve the state estimation performance of MHE in real-time applications. Unlike conventional MHE methods that rely on a fixed horizon size, our adaptive strategy enhances robustness against unknown noise statistics by adjusting the horizon size. We analyze the convergence property of the estimation error and provide guidelines for parameter design to ensure optimal performance. The effectiveness and superiority of the proposed method are demonstrated through simulations involving an oscillatory system and a target tracking application under non-stationary noise conditions.

Wireless sensor localization based on distance optimization and assistance by mobile anchor nodes: a novel algorithm.

Wireless sensor networks (WSNs) have wide applications in healthcare, environmental monitoring, and target tracking, relying on sensor nodes that are joined cooperatively. The research investigates localization algorithms for both target and node in WSNs to enhance accuracy. An innovative localization algorithm characterized as an asynchronous time-of-arrival (TOA) target is proposed by implementing a differential evolution algorithm. Unlike available approaches, the proposed algorithm employs the least squares criterion to represent signal-sending time as a function of the target position. The target node's coordinates are estimated by utilizing a differential evolution algorithm with reverse learning and adaptive redirection. A hybrid received signal strength (RSS)-TOA target localization algorithm is introduced, addressing the challenge of unknown transmission parameters. This algorithm simultaneously estimates transmitted power, path loss index, and target position by employing the RSS and TOA measurements. These proposed algorithms improve the accuracy and efficiency of wireless sensor localization, boosting performance in various WSN applications.

CBCT-DRRs superior to CT-DRRs for target-tracking applications for pancreatic SBRT

Objective. In current radiograph-based intra-fraction markerless target-tracking, digitally reconstructed radiographs (DRRs) from planning CTs (CT-DRRs) are often used to train deep learning models that extract information from the intra-fraction radiographs acquired during treatment. Traditional DRR algorithms were designed for patient alignment (i.e. bone matching) and may not replicate the radiographic image quality of intra-fraction radiographs at treatment. Hypothetically, generating DRRs from pre-treatment Cone-Beam CTs (CBCT-DRRs) with DRR algorithms incorporating physical modelling of on-board-imagers (OBIs) could improve the similarity between intra-fraction radiographs and DRRs by eliminating inter-fraction variation and reducing image-quality mismatches between radiographs and DRRs. In this study, we test the two hypotheses that intra-fraction radiographs are more similar to CBCT-DRRs than CT-DRRs, and that intra-fraction radiographs are more similar to DRRs from algorithms incorporating physical models of OBI components than DRRs from algorithms omitting these models. Approach. DRRs were generated from CBCT and CT image sets collected from 20 patients undergoing pancreas stereotactic body radiotherapy. CBCT-DRRs and CT-DRRs were generated replicating the treatment position of patients and the OBI geometry during intra-fraction radiograph acquisition. To investigate whether the modelling of physical OBI components influenced radiograph-DRR similarity, four DRR algorithms were applied for the generation of CBCT-DRRs and CT-DRRs, incorporating and omitting different combinations of OBI component models. The four DRR algorithms were: a traditional DRR algorithm, a DRR algorithm with source-spectrum modelling, a DRR algorithm with source-spectrum and detector modelling, and a DRR algorithm with source-spectrum, detector and patient material modelling. Similarity between radiographs and matched DRRs was quantified using Pearson’s correlation and Czekanowski’s index, calculated on a per-image basis. Distributions of correlations and indexes were compared to test each of the hypotheses. Distribution differences were determined to be statistically significant when Wilcoxon’s signed rank test and the Kolmogorov-Smirnov two sample test returned p ≤ 0.05 for both tests. Main results. Intra-fraction radiographs were more similar to CBCT-DRRs than CT-DRRs for both metrics across all algorithms, with all p ≤ 0.007. Source-spectrum modelling improved radiograph-DRR similarity for both metrics, with all p < 10−6. OBI detector modelling and patient material modelling did not influence radiograph-DRR similarity for either metric. Significance. Generating DRRs from pre-treatment CBCT-DRRs is feasible, and incorporating CBCT-DRRs into markerless target-tracking methods may promote improved target-tracking accuracies. Incorporating source-spectrum modelling into a treatment planning system’s DRR algorithms may reinforce the safe treatment of cancer patients by aiding in patient alignment.

An Adaptive IMM Algorithm for a PD Radar with Improved Maneuvering Target Tracking Performance

A pulse-Doppler (PD) radar has the advantage of strong anti-interference ability, and it is often used as a solution for maneuvering target tracking. In the application of target monitoring and tracking in PD radars, the interacting multiple model algorithm (IMM) has become the main and preferred choice due to its flexibility and high accuracy. However, the probability transfer matrix in classical IMM algorithms generally depends on constant prior knowledge, and if a PD radar is tracking a strong maneuvering target, it is inevitable to encounter some limitations, such as the possibility of target tracking trajectory deviation, and even a loss of the target. The Markov probability transfer matrix is proposed with an adaptive modification ability in real time to overcome the above problems in this paper. Additionally, for improving the speed of switching between the models, the fuzzy control system for secondary updating of model probability is adopted. By this means, the tracking accuracy of maneuvering targets is enhanced. Compared with the classical IMM algorithm, the corresponding simulation results for the PD radar indicate that the overall tracking accuracy of the proposed adaptive IMM algorithm is improved by 19.6%. In conclusion, the continuity and accuracy of the target trajectory can be effectively improved with the proposed adaptive IMM algorithm in PD radar cases.

Iterated Orthogonal Simplex Cubature Kalman Filter and Its Applications in Target Tracking

In order to increase a nonlinear system’s state estimate precision, an iterated orthogonal simplex cubature Kalman filter (IOSCKF) is presented in this study for target tracking. The Gaussian-weighted integral is decomposed into a spherical integral and a radial integral, which are approximated using the spherical simplex-radial rule and second-order Gauss–Laguerre quadrature rule, respectively, and result in the novel simplex cubature rule. To decrease the high-order error terms, cubature points with appropriate weights are taken from the cubature rule and processed using the provided orthogonal matrix. The structure supporting the nonlinear Kalman filter incorporates the altered points and weights and the calculation steps; from this, the updated time and measurement can be inferred. The Gauss–Newton iteration is employed repeatedly to adjust the measurement update until the termination condition is met and the IOSCKF is attained. The proposed algorithms are applied in target tracking, including CV target tracking and spacecraft orbit tracking, and the simulation results reveal that the IOSCKF can achieve higher accuracy compared to the CKF, SCKF, and OSCKF. In spacecraft orbit tracking simulation, compared with the SCKF, the position tracking accuracy and velocity tracking accuracy of the OSCKF are increased by 2.21% and 1.94%, respectively, which indicates that the orthogonal transformation can improve the tracking accuracy. Furthermore, compared with the OSCKF, the position tracking accuracy and velocity tracking accuracy of the IOSCKF are increased by 2.71% and 2.97%, respectively, which indicates that the tracking accuracy can be effectively improved by introducing iterative calculation into the measurement equation, thus verifying the effectiveness of the method presented in this paper.

Arithmetic average density fusion - Part I: Some statistic and information-theoretic results

Finite mixture such as the Gaussian mixture is a flexible and powerful probabilistic modeling tool for representing the multimodal distribution widely involved in many estimation and learning problems. The core of it is representing the target distribution by the arithmetic average (AA) of a finite number of sub-distributions which constitute a mixture. While the mixture has been widely used for single sensor filter design, it is only recent that the AA fusion demonstrates compelling performance for multi-sensor filter design. In this paper, some statistic and information-theoretic results are given on the covariance consistency, mean square error, mode-preservation capacity, and the information divergence of the AA fusion approach. In particular, based on the concept of conservative fusion, the relationship of the AA fusion with the existing conservative fusion approaches such as covariance union and covariance intersection is exposed. A suboptimal weighting approach has been proposed, which jointly with the best mixture-fit property of the AA fusion leads to a max–min optimization problem. Linear Gaussian models are considered for algorithm illustration and simulation comparison, resulting in the first-ever AA fusion-based multi-sensor Kalman filter. This is the first part of a series of papers that provide a comprehensive and thorough study of the AA fusion methodology and its application for target tracking. Extension and derivation of the AA fusion in the context of random finite set filters are provided in the consequent papers.

TRACE: Transformer-based continuous tracking framework using IoT and MCS

Target tracking, a critical application in the Internet of Things (IoT) and Mobile Crowd Sensing (MCS) domains, is a complex task that involves the continuous estimation of the positions of an object by using efficient and accurate algorithms. Some potential applications of target tracking include surveillance systems, asset tracking, wildlife monitoring, and cross-border security. The existing target tracking solutions are either energy-inefficient or are only effective for fixed-length trajectories, making them impractical for real-world applications. For robust predictive tracking, with irregular trajectory lengths, energy efficiency and accuracy are vital to ensure system’s longevity and reliability. In this work, using a combination of trajectory prediction and path correction techniques, a novel approach, TRACE, is proposed for continuously tracking a target in an environment. TRACE uses locations offered by IoT/MCS localization systems to make predictions about the target’s future movement. A transformer neural network is implemented to learn mobility patterns to predict the target’s future trajectory. To ensure accurate predictions, a path correction mechanism is devised, by updating the predicted trajectory using polynomial regression. Experiments are conducted using a real-world GeoLife dataset to evaluate the performance of the proposed approach. The results demonstrate that TRACE performs better than existing tracking techniques with an improvement in accuracy of about 50% while using 85% less energy, supporting the potential of the proposed approach for enhancing target tracking in IoT/MCS applications.

An Improved Genetic Algorithm for Scheduling Sensor Nodes in WSN

The extended lifetime of Wireless Sensor Networks (WSN) is an attractive goal for various types of research. This can be achieved if not all sensor nodes in the network consume their energy; this is because the energy consumption of every sensor node is a vital resource for a WSN. The scheduling techniques have recently enticed the interest of the researchers’ community, as they provide the ability to adjust a set of nodes in sleep mode instead of activating all sensor nodes. However, we consider the sensors that were selected to be in sleep mode, which will not affect network coverage for any target or full connectivity. In this paper, the genetic algorithm has been used to build efficient scheduling for the sensor nodes, which were based on multiple objectives in the fitness function, and we have proposed improved mutation and crossover operations. Then, we evaluate our approaches in a target tracking application compared with previous GA approaches. Our simulations show that we have an optimal chromosome that contains a minimum number of active sensor nodes for scheduling within 3-5 iterations.

Real-time tracking and berthing aid system with occlusion handling based on LiDAR

In smart ports, accurate perception of the state of a berthing ship relative to the berth is critical for the safety and efficiency of ships and ports. A real-time tracking and berthing system with occlusion handling based on Light Detection and Ranging (LiDAR) is proposed. First, the data is pre-processed, including fast filtering and clustering, and then a real-time tracking framework is proposed to solve the occlusion problem. This framework adapts to different berthing scenarios through accurate determination of dynamic and static targets and efficient retracking of berthing ships. To verify the effectiveness of the method, an on-site monitoring experiment of the “Yukun” training ship in Dalian Port is conducted, and a simulated berthing scene under occlusion is constructed to test the algorithm. The practical results prove that our method shows feasibility and effectiveness in the application of ship dynamic target tracking and safe ship berthing.

Self-Tuning Process Noise in Variational Bayesian Adaptive Kalman Filter for Target Tracking

Many practical systems, such as target tracking, navigation systems, autonomous vehicles, and other applications, are usually applied in dynamic conditions. Thus, the actual noise statistics characteristics of these systems are generally time varying and unknown, which will deteriorate the state estimation accuracy of the Kalman filter (KF) and even cause filter diverging. To address this issue, this paper proposes an adaptive process noise covariance (Qk)-based variational Bayesian adaptive Kalman filter (AQ-VBAKF) algorithm. Firstly, the adaptive factor is introduced to self-tune the process noise covariance; the adaptive factor is obtained based on the innovation sequences, which can adapt to the input measurement values. Then, the VB solution is applied to approximate the time variant and unknown measurement noise covariance. Therefore, this proposed algorithm can adjust the process noise covariance and the measurement noise covariance simultaneously based on the variable input signals, which can improve the self-adaptive ability of the state estimation filter in dynamic conditions. According to the dynamic target tracking test results, the proposed AQ-VBAKF outperforms several other existing filtering methods in estimation accuracy, robustness, and computational efficiency.

Pareto-based bi-objective optimization for robust power allocation in hybrid MIMO phased-array radar system under air defense maneuvering tracking

Recently, Hybrid MIMO phased-array (H-MIMO-PA) radar systems have been demonstrated to offer enhanced target tracking capabilities. In practice, an effective radar resource allocation (RA) strategy can ensure the quality of service (QoS) of subtasks and improve the system resource utilization in multiple target tracking (MTT) applications. In this paper, a robust power allocation strategy is developed with the objectives of enhancing target tracking accuracy (TTA) and low probability of intercept (LPI) performance in H-MIMO-PA radar. Firstly, in order to accurately grasp the air defense battlefield situation and improve the QoS for MTT, we propose a threat assessment model based on the intuitionistic fuzzy entropy (IFE) to calculate the comprehensive threat degree of each target in real time. Next, since the predicted conditional Cramér-Rao lower bound (PC-CRLB) is based on the most recently realized measurement and provides an accurate lower bound, the PC-CRLB in clutter is derived and utilized to formulate the task utility function for TTA. In addition, the probability of intercept is derived and adopted as the performance metric for LPI. Due to power allocation process may become conflicting for achieving better TTA and LPI performance at the same time, the Pareto-based bi-objective optimization scheme is adopted, which formulates a non-convex optimization problem. Finally, to solve the formulated model, we propose the modified bi-objective particle swarm optimization (MBOPSO) algorithm. Simulation results are provided to verify the effectiveness of the proposed power allocation algorithm.

Hesitant hierarchical T–S fuzzy system with fuzzily weighted recursive least square

Hierarchical fuzzy systems have been an increasingly prevalent research topic, however, most of them are with fixed structures. This could reduce the flexibility of the method in applications and make it difficult to build an elastic multilayer structure for different input information. Hesitant fuzzy set (HFS) consists of rich and flexible hesitant fuzzy elements, which have been widely developed and applied in recent years, and related basic concepts and theories have been constantly developed and improved. By using the flexible expressing capabilities of HFS, we constructively construct a new serial-based hierarchical fuzzy system with flexible and adaptive rules in each layer, named after hesitant hierarchical T–S fuzzy system (HHFS). In the general HHFS, lengths of HFS elements play an important role generating constructions of each layer and consequent parameters of rules are adjusted by fuzzily weighted recursive least square method. It is the first time to build a multilayer fuzzy system using HFS. To adapt HHFS into the application of maneuvering target tracking, another newly adapted one, time-sequential hesitant fuzzy set (TSHFS) is utilized. The function of the conventional HFS is still generating structures of subsystems, and the TSHFS is utilized to optimize parameters of consequent parts with the new proposed approach for fluctuated hesitant information under TSHFS environment. In HHFS, the rules of subsystems are adaptively changeable according to different inputs, namely subsystems of each layer are with variant structures. Compared with state-of-the-art algorithms, the effectiveness and advantage of HHFS are exhibited in various experiments.

Tracking of Manoeuvring Target Using Fuzzy Logic Augmented H-Infinity Filter

Conventionally for target tracking, Kalman filter and closely related algorithms are used. These filters inherently are as such not robust. In this paper, fuzzy logic augmented H-infinity filters are proposed for target tracking application. Initially, fuzzy logic is used at filter level to eliminate or reduce local estimation errors and then, an additional fuzzy system is used to minimize effects of outliers and estimation errors during data fusion process. An adaptive H-Infinity filter using fuzzy degree of matching is also proposed for target tracking. The performance of these algorithms is evaluated using MATLAB and its fuzzy logic tool box. Very encouraging results have been obtained with the newly proposed algorithms for target tracking.

Application of Target Recognition and Tracking in Agricultural Picking Robots

Target tracking in agricultural picking robots has a huge impact in the field of computer vision, and high-quality picking recognition and tracking algorithms are the basis for solving many problems such as inaccurate localization in agricultural picking. The problem of target recognition and tracking research is to identify and track the trajectories of different targets in video sequences. This paper mainly summarizes and analyzes the latest proposed algorithmic models about deep learning on target recognition and tracking and its application in agricultural picking robots. By analyzing various problems of current target recognition, the improvement of algorithms for different problems is summarized, and finally some possible future research directions are also proposed.

Study on Maneuvering Target Trajectory Simulation and Tracking Based on IMM algorithm

On the background of air defense missile which use radar command guidance, this article focuses on the maneuvering target trajectory simulation and tracking problem by considering possible maneuvering modes and target overload. Taking Serpentine maneuvering (S maneuvering) as an example, the target trajectory is simulated based on overload using stepwise design method, and data are measured through sensor models. Since single model cannot model the maneuvering target motion exactly, the estimation is addressed by combining the interacting multiple model algorithm and unscented Kalman filter algorithm, so as to study the applications of maneuvering target trajectory simulation and tracking in air defense missile systems. The effectiveness of the algorithm is demonstrated with simulated data.

TAN: A Transferable Adversarial Network for DNN-Based UAV SAR Automatic Target Recognition Models

Recently, the unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) has become a highly sought-after topic for its wide applications in target recognition, detection, and tracking. However, SAR automatic target recognition (ATR) models based on deep neural networks (DNN) are suffering from adversarial examples. Generally, non-cooperators rarely disclose any SAR-ATR model information, making adversarial attacks challenging. To tackle this issue, we propose a novel attack method called Transferable Adversarial Network (TAN). It can craft highly transferable adversarial examples in real time and attack SAR-ATR models without any prior knowledge, which is of great significance for real-world black-box attacks. The proposed method improves the transferability via a two-player game, in which we simultaneously train two encoder–decoder models: a generator that crafts malicious samples through a one-step forward mapping from original data, and an attenuator that weakens the effectiveness of malicious samples by capturing the most harmful deformations. Particularly, compared to traditional iterative methods, the encoder–decoder model can one-step map original samples to adversarial examples, thus enabling real-time attacks. Experimental results indicate that our approach achieves state-of-the-art transferability with acceptable adversarial perturbations and minimum time costs compared to existing attack methods, making real-time black-box attacks without any prior knowledge a reality.

PSO-Based Target Localization and Tracking in Wireless Sensor Networks

Research of target localization and tracking is always a remarkable problem in the application of wireless sensor networks (WSNs) technology. There are many kinds of research and applications of target localization and tracking, such as Angle of Arrival (AOA), Time of Arrival (TOA), and Time Difference of Arrival (TDOA). The target localization accuracy for TOA, TDOA, and AOA is better than RSS. However, the required devices in the TOA, TDOA, and AOA are more expensive than RSS. In addition, the computational complexity of TOA, TDOA, and AOA is also more complicated than RSS. This paper uses a particle swarm optimization (PSO) algorithm with the received signal strength index (RSSI) channel model for indoor target localization and tracking. The performance of eight different method combinations of random or regular points, fixed or adaptive weights, and the region segmentation method (RSM) proposed in this paper for target localization and tracking is investigated for the number of particles in the PSO algorithm with 12, 24, 52, 72, and 100. The simulation results show that the proposed RSM method can reduce the number of particles used in the PSO algorithm and improve the speed of positioning and tracking without affecting the accuracy of target localization and tracking. The total average localization time for target localization and tracking with the RSM method can be reduced by 48.95% and 34.14%, respectively, and the average accuracy of target tracking reaches up to 93.09%.

Application of Recurrent Neural-Network based Kalman Filter for Uncertain Target Models

For various target tracking applications, it is well known that the Kalman filter is the optimal estimator(in the minimum mean-square sense) to predict and estimate the state(position and/or velocity) of linear dynamical systems driven by Gaussian stochastic noise. In the case of nonlinear systems, Extended Kalman filter(EKF) and/or Unscented Kalman filter(UKF) are widely used, which can be viewed as approximations of the(linear) Kalman filter in the sense of the conditional expectation. However, to implement EKF and UKF, the exact dynamical model information and the statistical information of noise are still required. In this paper, we propose the recurrent neural-network based Kalman filter, where its Kalman gain is obtained via the proposed GRU-LSTM based neural-network framework that does not need the precise model information as well as the noise covariance information. By the proposed neural-network based Kalman filter, the state estimation performance is enhanced in terms of the tracking error, which is verified through various linear and nonlinear tracking problems with incomplete model and statistical covariance information.