Accuracy Of Target Tracking Research Articles

Tracking of Multiple Static and Dynamic Targets for 4D Automotive Millimeter-Wave Radar Point Cloud in Urban Environments

This paper presents a target tracking algorithm based on 4D millimeter-wave radar point cloud information for autonomous driving applications, which addresses the limitations of traditional 2 + 1D radar systems by using higher resolution target point cloud information that enables more accurate motion state estimation and target contour information. The proposed algorithm includes several steps, starting with the estimation of the ego vehicle’s velocity information using the radial velocity information of the millimeter-wave radar point cloud. Different clustering suggestions are then obtained using a density-based clustering method, and correlation regions of the targets are obtained based on these clustering suggestions. The binary Bayesian filtering method is then used to determine whether the targets are dynamic or static targets based on their distribution characteristics. For dynamic targets, Kalman filtering is used to estimate and update the state of the target using trajectory and velocity information, while for static targets, the rolling ball method is used to estimate and update the shape contour boundary of the target. Unassociated measurements are estimated for the contour and initialized for the trajectory, and unassociated trajectory targets are selectively retained and deleted. The effectiveness of the proposed method is verified using real data. Overall, the proposed target tracking algorithm based on 4D millimeter-wave radar point cloud information has the potential to improve the accuracy and reliability of target tracking in autonomous driving applications, providing more comprehensive motion state and target contour information for better decision making.

A Multimodal Data Harness Approach of Mobile Sensors Trajectory Planning for Target Tracking

The future Internet comprising multimodal mobile wireless sensors (MMWSs) dramatically increases the data dimension and complexity compared to the traditional homogeneous networks. It consists of various types of nodes that can be deployed in different spatial domains to form the space, air, ground, and ocean integrated network (SAGOI-Net). A key challenge to IoT with SAGOI-Net is harnessing the real-time data from these sensors to obtain target characteristics and realize target tracking, especially in rough environment with obstacles and enemy threats. In this paper, we propose an approach -fuzzy logic and flocking control under extended kalman filter (EKFFL) to provide sensor nodes trajectory formation. With the tools from control systems and signal processing, this approach improves the commonly-adopted flocking control algorithm and fully employs multi modality of data. Compared with the modified kalman consistency filter (KCF) approach, the proposed EKFFL achieves higher target tracking accuracy with a shorter time period of trajectory formation. The trade-off between the data delay and tracking accuracy is also analysed. Based on its advantages, the EKFFL approach can be applied in broad scenarios, such as unmanned border awareness systems, environmental monitoring and intelligent transportation.

Research on the association algorithm of space-target track segments

In order to improve the tracking continuity and stability of space targets, the track segments association algorithms are studied. The extrapolation prediction based on the C-W motion model in the main spacecraft orbital coordinates is carried out. The model of space target is used to forecast and extrapolate the trajectory of the interrupted target. Based on the extrapolation of the terminated track, the track segments are associated by using the extrapolation results and the state update values at the first few moments of each track segment after the interruption. In this way, the association and fusion of the orbit of the space target interruption is completed. The results can improve the tracking accuracy of space targets and the trajectory association.

Distributed Maximum Correntropy Cubature Information Filtering for Tracking Unmanned Aerial Vehicle

Aiming at improving the performance of tracking unmanned aerial vehicle in the battlefield, this paper focuses on the algorithm involving tracking the maneuvering target with a distributed sensor network under non-Gaussian measurement noise. A novel distributed maximum correntropy cubature information filtering based on interactive multiple model is proposed. Taking advantage of the correntropy, we design a maximum correntropy cubature information filtering for each node to estimate the target state under non-Gaussian measurement noise. Then, distributed information fusion based on weighted average consensus is conducted to improve the stability of the sensor network. After that, the information pair is changed, so that a distributed state estimation algorithm based on interactive multiple model is developed to increase the accuracy of maneuvering target tracking. Simulation results and comparison with other algorithms in three typical non-Gaussian measurement noise scenarios are given to evaluate the effectiveness of the proposed algorithm.

Correlation Filtering Algorithm of Infrared Spectral Data for Dim Target Tracking

The correlation filtering algorithm of infrared spectral data for dim and small target tracking is studied to improve the tracking accuracy of small and weak targets and to track small and weak targets in real time. After the image noise reduction processing by the mean shift filtering algorithm, the infrared small and weak target image data model is constructed by using the denoised infrared small and weak target image. And the brightness value and position of unknown small and weak targets are obtained. The tracking and measurement model of small and weak targets is built. The joint probabilistic data association algorithm is used to calculate the probability that each measurement is associated with its possible source targets, and the particle filter is used to update the tracking status of small and weak targets to achieve real-time tracking of small and weak targets. The experimental results show that the algorithm can enhance the edge contour information of small and weak images, so as to accurately track small and weak targets moving in any track, and has good real-time tracking and accuracy. There is a small deviation between the tracking track of weak and small targets tracked by the algorithm and the actual track, and the root mean square difference of tracking weak and small targets is within 2 pixels. In addition, the detection probability of detecting weak and small targets is less affected by SNR environmental factors.

Maneuvering target tracking based on an adaptive variable structure interactive multiple model filtering and smoothing algorithm

For maneuvering target tracking, the interactive multiple model (IMM) algorithm and its variants have shown good performance, among which the variable structure IMM (VSIMM) algorithm is the most widely studied one. The approximation degree of the algorithm and the matching degree of the model subset will affect the performance of the VSIMM. In addition, considering that smoothing can provide better estimation of the target state, a new adaptive VSIMM filtering and smoothing (AVSIMMFS) algorithm is proposed in this paper. First, an accurate model of the VSIMM algorithm is established, in which the IMM is run in parallel with and independently from the different model subsets, and the state estimation of the model subset with the highest probability is selected as the final estimation result. Then, an adaptive VSIMM (AVSIMM) algorithm was designed based on the VSIMM algorithm. The adaptation is reflected in the construction of a new model subset from the original model subsets, which improves the matching degree between the model subset and the actual maneuvering model of the target. Finally, by smoothing the filtering data of the AVSIMM algorithm, the AVSIMMFS algorithm is obtained. Because of the combination of forward filtering and backward smoothing, the target tracking accuracy is further improved. Simulation results show that the tracking performance of the AVSIMMFS algorithm is better than that of other methods.

Optimized Deep Learning for Congestion-Aware Continuous Target Tracking and Boundary Detection in IoT-Assisted WSN

Target tracking (TT) is an important application of Internet of Things (IoT)-assisted wireless sensor networks (WSNs) in which sensor nodes monitor and report the positions of continuously moving objects. However, continuous tracking of multiple objects causes network congestion. To solve this challenge and provide congestion-aware continuous TT and boundary detection, we propose a novel energy-aware radial clustering based piecewise regressive multiobjective golden eagle optimized deep convolutive learning (EARC-ODCL) algorithm. In particular, EARC-ODCL incorporates a multiobjective stochastic sampled golden eagle optimization to select the optimal cluster heads (CHs) for sending the target information. Also, a fully connected deep convolutive neural learning is used to identify the boundary of sensor nodes. Furthermore, a piecewise linear regression approach is used for network congestion prediction and minimize data loss. Thereby, the proposed EARC-ODCL is able to perform continuous TT and boundary detection with higher accuracy in IoT-assisted WSN. Extensive simulations are conducted to assess the performance of EARC-ODCL in terms of various metrics, such as TT accuracy and time, boundary detection accuracy (BDA), and data loss.

Temporal contexts for motion tracking in ultrasound sequences with information bottleneck.

Recently, deep convolutional neural networks (CNNs) have been widely adopted for ultrasound sequence tracking and shown to perform satisfactorily. However, existing trackers ignore the rich temporal contexts that exists between consecutive frames, making it difficult for these trackers to perceive information about the motion of thetarget. In this paper, we propose a sophisticated method to fully utilize temporal contexts for ultrasound sequences tracking with information bottleneck. This method determines the temporal contexts between consecutive frames to perform both feature extraction and similarity graph refinement, and information bottleneck is integrated into the feature refinementprocess. The proposed tracker combined three models. First, online temporal adaptive convolutional neural network (TAdaCNN) is proposed to focus on feature extraction and enhance spatial features using temporal information. Second, information bottleneck (IB) is incorporated to achieve more accurate target tracking by maximally limiting the amount of information in the network and discarding irrelevant information. Finally, we propose temporal adaptive transformer (TA-Trans) that efficiently encodes temporal knowledge by decoding it for similarity graph refinement. The tracker was trained on 2015 MICCAI Challenge on Liver Ultrasound Tracking (CLUST) dataset to evaluate the performance of the proposed method by calculating the tracking error (TE) between the predicted landmarks and the ground truth landmarks for each frame. The experimental results are compared with 13 state-of-the-art methods, and ablation studies areconducted. On CLUST 2015 dataset, our proposed model achieves a mean TE of 0.81 ± 0.74 mm and a maximum TE of 1.93 mm for 85 point-landmarks across 39 ultrasound sequences in the 2D sequences. Tracking speed ranged from 41 to 63 frames per second (fps). This study demonstrates a new integrated workflow for ultrasound sequences motion tracking. The results show that the model has excellent accuracy and robustness. Reliable and accurate motion estimation is provided for applications requiring real-time motion estimation in the context of ultrasound-guided radiationtherapy.

An innovative method for scene recognition and target tracking for adaptive cruise control in complex traffic environment

The adaptive cruise control (ACC) system as a typical advanced driver assistant system (ADAS) has been commercially application in automotive industry for decades. An innovative method is proposed in this paper for scene recognition and target tracking for ACC application in some complex traffic environment. Firstly, a multi-sensor fusion method is established to estimate the curvature integrated by the quadratic programing (QP)-based lane boundaries detection, vehicle dynamics of lateral motion, and an improved Kalman filter (IKF) to introduce more measurement information into the feedback correction process. Then, the closet in-path vehicle (CIPV) can be selected according to the statistical distance between the tracked targets and the predicted driving path of ego vehicle. To distinguish the lane changing and curve driving behaviors, the trajectory models of obstacles are established as an ellipsoid domain equation and transformed into a regression model, which is recast as a standardized QP problem. Hence, the behaviors and scenes can be recognized effectively. To restrain the disturbance and improve the accuracy and robustness of target tracking, an [Formula: see text]-based switched tracking method is proposed by combining of the low pass filter (LPF) and [Formula: see text] theory. Finally, an accurate and robust tracker is provided for the CIPV by incorporating with four steps: IKF-based curvature fusion estimation, CIPV selection, QP-based scene recognition, and the [Formula: see text]-based observer. Moreover, two real car experiments are adopted and the results verify the effectiveness and real-time performance of the proposed method.

Research on the angular velocity estimation method based on the state augmentation method

In the maneuvering target tracking research due to the unpredictability of the target’s maneuvering, it makes it difficult to establish an accurate target motion model to reflect the real motion trajectory of the target. Based on the determination of the parametric maneuver model and the radar measurement conditions of the target, the joint estimation method of the motion state and the maneuver parameters is designed to obtain the optimal estimation of the motion state and the maneuver parameters based on the optimal evaluation criteria. Currently, in the descriptive category of the state space model, the state augmentation method is obtained to solve the joint estimation of the motion state and maneuver parameters based on the estimation criterion [1]. Therefore, the angular velocity estimation method of the state augmentation method is used to consider the estimated value of the target angular velocity and the estimated variance comprehensively to improve the convergence speed of target tracking, minimize the error between the filtered angular velocity and the real angular velocity of the maneuvering target, and finally achieve the purpose of improving the target tracking accuracy.

Fusion of Inverse Synthetic Aperture Radar and Camera Images for Automotive Target Tracking

Automotive targets undergoing turns in road junctions offer large synthetic apertures over short dwell times to automotive radars that can be exploited for obtaining fine cross-range resolution. Likewise, the wide bandwidths of the automotive radar signal yield high-range resolution profiles. Together, they are exploited for generating inverse synthetic aperture radar (ISAR) images that offer rich information regarding the target vehicle's size, shape, and trajectory which is useful for object recognition and classification. However, a key requirement for ISAR is translation motion compensation and estimation of the turning velocity of the target. State-of-the-art algorithms for motion compensation trade-off between computational complexity and accuracy. An alternative low complexity method is to use an additional sensor for tracking the target motion. In this work, we propose to exploit computer vision algorithms to identify the radar target object in the sensor field-of-view (FoV) with high accuracy. Further, we propose to track the target vehicle's motion through fusion of vision and radar data. Vision data facilitates the accurate estimation of the lateral position of the target and its lateral velocity which complements the radar's capability of accurate estimation of range and radial velocity. Through simulations and experimental evaluations with a monocular camera and Texas Instrument's millimeter wave radar, we demonstrate the effectiveness of sensor fusion for accurate target tracking for translational motion compensation and generation of high quality ISAR images.

A Video Target Tracking and Correction Model with Blockchain and Robust Feature Location

In this paper, a cutting-edge video target tracking system is proposed, combining feature location and blockchain technology. The location method makes full use of feature registration and received trajectory correction signals to achieve high accuracy in tracking targets. The system leverages the power of blockchain technology to address the challenge of insufficient accuracy in tracking occluded targets, by organizing the video target tracking tasks in a secure and decentralized manner. To further enhance the accuracy of small target tracking, the system uses adaptive clustering to guide the target location process across different nodes. In addition, the paper also presents an unmentioned trajectory optimization post-processing approach, which is based on result stabilization, effectively reducing inter-frame jitter. This post-processing step plays a crucial role in maintaining a smooth and stable track of the target, even in challenging scenarios such as fast movements or significant occlusions. Experimental results on CarChase2 (TLP) and basketball stand advertisements (BSA) datasets show that the proposed feature location method is better than the existing methods, achieving a recall of 51% (27.96+) and a precision of 66.5% (40.04+) in the CarChase2 dataset and recall of 85.52 (11.75+)% and precision of 47.48 (39.2+)% in the BSA dataset. Moreover, the proposed video target tracking and correction model performs better than the existing tracking model, showing a recall of 97.1% and a precision of 92.6% in the CarChase2 dataset and an average recall of 75.9% and mAP of 82.87% in the BSA dataset, respectively. The proposed system presents a comprehensive solution for video target tracking, offering high accuracy, robustness, and stability. The combination of robust feature location, blockchain technology, and trajectory optimization post-processing makes it a promising approach for a wide range of video analytics applications, such as surveillance, autonomous driving, and sports analysis.

Joint allocation of transmit power and signal bandwidth for distributed cognitive tracking radar network using cooperative game

The radar network can achieve high target tracking accuracy by felicitously distributing the transmitting resources of each node. However, the influence of multiple transmitting resources of each radar node on target tracking accuracy is coupled with each other. We propose a joint allocation strategy of transmit power and signal bandwidth based on the cooperative game for the distributed cognitive tracking radar network. We employ the determinant of the Fisher information matrix to evaluate the target tracking accuracy and analyze the influence of each radar node's transmit power and signal bandwidth on target tracking accuracy. The joint allocation problem of transmit power and signal bandwidth is modeled as a cooperative game. We use the algorithm combining the cyclic minimization with the Shapley value to solve the cooperative game model. The weighted graph is used to simplify the calculation of the Shapley value. Simulation experiments are carried out in single-target tracking and multi-target tracking scenes. The results demonstrate that the proposed method can approach the centralized resource allocation method on the target tracking performance with a lower computational load.

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%.

An Improved IMM-GPDA Tracking Algorithm

To improve the accuracy and efficiency of multi-maneuvering target tracking in dense clutter environments, an improved interactive multi-model generalized probabilistic data association (IMM-GPDA) algorithm is proposed in this paper. The algorithm introduces Doppler information into the measurement data. Firstly, the measurement data is pre-processed by double-threshold regional density clutter elimination, and then the pre-processed data is put into the improved IMM-GPDA algorithm with square-root cubature Kalman filter (SRCKF) and model transition probability adaptation for interaction, association, and filtering. Simulation results show that the algorithm has advanced accuracy, instantaneity, and robustness in tracking environments with multi-maneuvering targets and dense clutters.

Cognitive Conformal Subaperturing FDA-MIMO Radar for Power Allocation Strategy

Recently, the conformal array radar has attracted wide attention compared with the conventional array radar due to its flexible element configuration and more diverse signal processing methods. During the development of the jamming equipment, the electromagnetic environment becomes more complex, which brings more challenges to the radar system. To overcome the variable interference environment's negative influence on moving target tracking, we propose two adaptive power allocation methods based on two criteria to improve target tracking accuracy. Firstly, we build the data model of the conformal subaperturing frequency diverse array multi-input and multi-output (CSFDA-MIMO) radar and the interference signal. Moreover, the Bayesian Cramer-Rao bound (BCRB), signal-to-interference-plus-noise ratio (SINR) are derived and taken as the objective functions in proposed optimization problems. Based on it, we build two different power allocation optimization problems under BCRB minimization criteria and SINR maximization criteria, respectively, and two different power constraints are considered. Finally, simulation results verify the effectiveness of the proposed adaptive power allocation methods. The power allocation strategies under two criteria can obtain better tracking accuracy compared with uniform allocation, and the tracking accuracy of the adaptive power allocation method can be influenced by different power constraint conditions.

LPI-Based Transmit Resource Scheduling for Target Tracking with Distributed MIMO Radar Systems

This paper explores the effect of the low probability of intercept (LPI) performance optimization on target tracking in distributed MIMO (D-MIMO) radar systems, where an intercept receiver is equipped on the target. The aim of the proposed LPI-based transmit resource scheduling (LPI-TRS) strategy is to optimize the LPI performance of the D-MIMO systems meanwhile satisfy the target tracking accuracy requirement by the proper transmit resource management design. Different from the existing research, we introduce a cascading mathematical model to describe the intercept process with the specific intercept receiver. A cascading product of the probabilities of interception and detection deduces the probability of report <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ P_{R}$</tex-math></inline-formula> for the interceptor, to evaluate the LPI performance of one transmit radar node. Accordingly, the maximum <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$ P_{R}$</tex-math></inline-formula> is employed, for the overall D-MIMO radar systems, to perform as the global LPI performance metric. Based on the min-max criterion, by minimizing the global LPI metric, a novel non-convex optimization problem is formulated wherein the requirements for target tracking performance and the system resource limitation are considered as the constraints. Wherein the tracking task is fulfilled by the two-tier hybrid processing framework. Meanwhile, we introduce a convex relaxation-based approach, so the sub-optimal results are acquired via a two-step fast computational search algorithm. Subsequently, the closed-loop scheme is set up to achieve LPI-based resource awareness in D-MIMO radar systems. Several numerical results demonstrate the theoretical analysis and show that the proposed LPI-TRS leads to significant LPI performance improvements.

Maneuvering Resource Allocation for Coordinated Target Tracking in Airborne Radar Network

In this paper, a performance driven maneuvering resource allocation (MRA) scheme is developed for target tracking in airborne radar network (ARN). To exploit the degree of freedom of ARN mobility for target tracking, we formulate a MRA scheme for maximizing the target tracking performance, under the practical constraints on the airborne radar's speed and attitude variation rate, as well as threat zone and collision avoidance. We adopt the Bayesian Cramér-Rao lower bound as a metric function to gauge the target tracking performance, and build the MRA scheme as a non-convex optimization problem. Instead of using the heuristic based methods to solve the resulting non-convex optimization problem, we design an efficient three-step solution technique, which incorporates inactive constraints elimination and active constraints linearization procedure. In such a case, the resulting relaxed problem can be solved with guaranteed convergence through the proximal alternating direction method of multipliers. Simulation results demonstrate that the proposed MRA scheme can greatly increase the target tracking accuracy, and is computationally more efficient than the heuristic algorithms.

Geometric Arithmetic Mean Method for Low Altitude Target Elevation Angle Tracking

In tracking operation, the signal reflected from the target comes to the antenna in two paths. The first is the direct path, from the target to the antenna, and the second is the indirect path, due to the multipath phenomenon, from the target to the surface then to the antenna. In a low altitude situation, the indirect path can cause severe errors in tracking operation as it enters the antenna main beam and combines with the direct path signal. In such a scenario, the antenna fails to track the elevation angle by the target's image located under the ground. A significant challenge in tracking systems is to mitigate the multipath effect. To do so, we extended the elevation geometric mean method and presented the target and image elevation angles separation method. Two monopulse equations are proposed to calculate the target elevation angle. The proposed method offers low computational load and can be implemented on monopulse system. The complete noise analysis is derived for the method. It is shown that the error of the proposed method reaches the Carmer Rao Lower Bound by proper selection of frequencies. Simulation results show accurate target tracking in a multipath environment.

Consensus-Based Distributed Batch Estimation in Asynchronous Wireless Sensor Networks

In this paper, to address the distributed estimation problem over an asynchronous wireless sensor network (aWSN), an average consensus-based distributed batch estimation (DBE) method is proposed. The DBE seeks to update the global posterior with a predefined global update period (GUP) and is implemented with a local filter (LF) and a fusion filter (FF). For LF, we develop two different asynchronous batch estimation approaches to align and compute the asynchronous local posteriors of multiple nodes in an aWSN. At FF, an average consensus filter is adopted to compute the global posterior via a proposed DBE fusion rule. Numerical results show that the proposed DBE method has high target-tracking accuracy and is robust to strong asynchronism. Besides, the optimality of DBE fusion can be approximately achieved with a sufficiently large number of particles and consensus iterations.