Target Tracking Framework Research Articles

S4-KD: A single step spiking SiamFC+ + for object tracking with knowledge distillation.

S4-KD: A single step spiking SiamFC+ + for object tracking with knowledge distillation.

The TEDDY Framework: An Efficient Framework for Target Tracking Using Edge-Based Distributed Smart Cameras with Dynamic Camera Selection

The TEDDY Framework: An Efficient Framework for Target Tracking Using Edge-Based Distributed Smart Cameras with Dynamic Camera Selection

Visual target tracking based on fractional – order bidirectional hybrid attentional feature fusion

This paper mainly designs and implements target tracking based on fractional – order feature fusion to solve tracking drift and tracking box jumping in complex scenes. Firstly, the starting point and overall structure of the model design were introduced. Secondly, in response to the low information utilization of the feature extraction network in the target tracking framework at the local scale of the target, a fractional – order node function based attention CNN hybrid attention extraction module was proposed to improve the robustness of target tracking. Finally, overall performance was quantitatively and qualitatively evaluated on multiple evaluation datasets with various advanced trackers. The results showed that the algorithm proposed in this paper had a high tracking advantage under severe changes in scale morphology, dynamic blurring, and similar interference attributes.

Robust underwater object tracking with image enhancement and two-step feature compression

Developing a robust algorithm for underwater object tracking (UOT) is crucial to support the sustainable development and utilization of marine resources. In addition to open-air tracking challenges, the visual object tracking (VOT) task presents further difficulties in underwater environments due to visual distortions, color cast issues, and low-visibility conditions. To address these challenges, this study introduces a novel underwater target tracking framework based on correlation filter (CF) with image enhancement and a two-step feature compression mechanism. Underwater image enhancement mitigates the impact of visual distortions and color cast issues on target appearance modeling, while the two-step feature compression strategy addresses low-visibility conditions by compressing redundant features and combining multiple compressed features based on the peak-to-sidelobe ratio (PSR) indicator for accurate target localization. The excellent performance of the proposed method is demonstrated through evaluation on two public UOT datasets.

Enhancing Target Tracking Capability in Weapon Systems Using Target Detection and Sensor Network Mechanisms

Abstract The ability to track targets in weapon systems profoundly impacts the precision and potency of target engagement. Stable and accurate target tracking is pivotal for bolstering military capabilities. This study proposes a framework that integrates a target detection probability model with a wireless sensor network mechanism to address challenges in enhancing the reliability of multi-target tracking in weapon systems. We introduce a closed-loop target tracking framework called MTT-SNM, which integrates multiple-source target tracking modules to improve the system’s capability to capture crucial information for target acquisition. Additionally, we devise a position estimation module and a node collaboration module to achieve smooth, continuous future position estimation with higher precision and reduced uncertainty based on current position estimates. This capability aids in guiding coordinated target tracking within the system and enhancing collaborative tracking capabilities. Furthermore, a target recovery module with a four-phase recovery strategy is introduced to swiftly locate targets after loss, thereby enhancing the stability of target tracking in the system. Extensive experimentation validates the outstanding performance of the MTT-SNM framework in system target tracking.

A Vision-Based End-to-End Reinforcement Learning Framework for Drone Target Tracking

Drone target tracking, which involves instructing drone movement to follow a moving target, encounters several challenges: (1) traditional methods need accurate state estimation of both the drone and target; (2) conventional Proportional–Derivative (PD) controllers require tedious parameter tuning and struggle with nonlinear properties; and (3) reinforcement learning methods, though promising, rely on the drone’s self-state estimation, adding complexity and computational load and reducing reliability. To address these challenges, this study proposes an innovative model-free end-to-end reinforcement learning framework, the VTD3 (Vision-Based Twin Delayed Deep Deterministic Policy Gradient), for drone target tracking tasks. This framework focuses on controlling the drone to follow a moving target while maintaining a specific distance. VTD3 is a pure vision-based tracking algorithm which integrates the YOLOv8 detector, the BoT-SORT tracking algorithm, and the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. It diminishes reliance on GPS and other sensors while simultaneously enhancing the tracking capability for complex target motion trajectories. In a simulated environment, we assess the tracking performance of VTD3 across four complex target motion trajectories (triangular, square, sawtooth, and square wave, including scenarios with occlusions). The experimental results indicate that our proposed VTD3 reinforcement learning algorithm substantially outperforms conventional PD controllers in drone target tracking applications. Across various target trajectories, the VTD3 algorithm demonstrates a significant reduction in average tracking errors along the X-axis and Y-axis of up to 34.35% and 45.36%, respectively. Additionally, it achieves a notable improvement of up to 66.10% in altitude control precision. In terms of motion smoothness, the VTD3 algorithm markedly enhances performance metrics, with improvements of up to 37.70% in jitter and 60.64% in Jerk RMS. Empirical results verify the superiority and feasibility of our proposed VTD3 framework for drone target tracking.

FedTrack: A Collaborative Target Tracking Framework Based on Adaptive Federated Learning

FedTrack: A Collaborative Target Tracking Framework Based on Adaptive Federated Learning

Application of fuzzy logic control theory combined with target tracking algorithm in unmanned aerial vehicle target tracking

This paper aims to increase the Unmanned Aerial Vehicle's (UAV) capacity for target tracking. First, a control model based on fuzzy logic is created, which modifies the UAV's flight attitude in response to the target's motion status and changes in the surrounding environment. Then, an edge computing-based target tracking framework is created. By deploying edge devices around the UAV, the calculation of target recognition and position prediction is transferred from the central processing unit to the edge nodes. Finally, the latest Vision Transformer model is adopted for target recognition, the image is divided into uniform blocks, and then the attention mechanism is used to capture the relationship between different blocks to realize real-time image analysis. To anticipate the position, the particle filter algorithm is used with historical data and sensor inputs to produce a high-precision estimate of the target position. The experimental results in different scenes show that the average target capture time of the algorithm based on fuzzy logic control is shortened by 20% compared with the traditional proportional-integral-derivative (PID) method, from 5.2 s of the traditional PID to 4.2 s. The average tracking error is reduced by 15%, from 0.8 m of traditional PID to 0.68 m. Meanwhile, in the case of environmental change and target motion change, this algorithm shows better robustness, and the fluctuation range of tracking error is only half of that of traditional PID. This shows that the fuzzy logic control theory is successfully applied to the UAV target tracking field, which proves the effectiveness of this method in improving the target tracking performance.

A dynamic target tracking framework of UGV for UAV recovery under random disturbances

PurposeDynamically tracking the target by unmanned ground vehicles (UGVs) plays a critical role in mobile drone recovery. This study aims to solve this challenge under diverse random disturbances, proposing a dynamic target tracking framework for UGVs based on target state estimation, trajectory prediction, and UGV control.Design/methodology/approachTo mitigate the adverse effects of noise contamination in target detection, the authors use the extended Kalman filter (EKF) to improve the accuracy of locating unmanned aerial vehicles (UAVs). Furthermore, a robust motion prediction algorithm based on polynomial fitting is developed to reduce the impact of trajectory jitter caused by crosswinds, enhancing the stability of drone trajectory prediction. Regarding UGV control, a dynamic vehicle model featuring independent front and rear wheel steering is derived. Additionally, a linear time-varying model predictive control algorithm is proposed to minimize tracking errors for the UGV.FindingsTo validate the feasibility of the framework, the algorithms were deployed on the designed UGV. Experimental results demonstrate the effectiveness of the proposed dynamic tracking algorithm of UGV under random disturbances.Originality/valueThis paper proposes a tracking framework of UGV based on target state estimation, trajectory prediction and UGV predictive control, enabling the system to achieve dynamic tracking to the UAV under multiple disturbance conditions.

A Sequential Game Framework for Target Tracking

A Sequential Game Framework for Target Tracking

Domain-knowledge-aided airborne ground moving targets tracking

Domain-knowledge-aided airborne ground moving targets tracking

Probabilistic indoor tracking of Bluetooth Low-Energy beacons

Probabilistic indoor tracking of Bluetooth Low-Energy beacons

Siamese Network Tracker Based on Multi-Scale Feature Fusion

The main task in visual object tracking is to track a moving object in an image sequence. In this process, the object’s trajectory and behavior can be described by calculating the object’s position, velocity, acceleration, and other parameters or by memorizing the position of the object in each frame of the corresponding video. Therefore, visual object tracking can complete many more advanced tasks, has great performance in relation to real scenes, and is widely used in automated driving, traffic monitoring, human–computer interaction, and so on. Siamese-network-based trackers have been receiving a great deal of attention from the tracking community, but they have many drawbacks. This paper analyzes the shortcomings of the Siamese network tracker in detail, uses the method of feature multi-scale fusion to improve the Siamese network tracker, and proposes a new target-tracking framework to address its shortcomings. In this paper, a feature map with low-resolution but strong semantic information and a feature map with high-resolution and rich spatial information are integrated to improve the model’s ability to depict an object, and the problem of scale change is solved by fusing features at different scales. Furthermore, we utilize the 3D Max Filtering module to suppress repeated predictions of features at different scales. Finally, our experiments conducted on the four tracking benchmarks OTB2015, VOT2016, VOT2018, and GOT10K show that the proposed algorithm effectively improves the tracking accuracy and robustness of the system.

A Re-detection Target Tracking Framework after Loss for Unmanned Aerial Vehicle

Currently, the target tracking algorithm based on discriminative correlation filter (DCF) and deep learning (DL) plays an increasingly important role in UAV (unmanned aerial vehicle). However, existing algorithms have limitations such as limited search region, difficulty in re-capturing targets when tracking is lost, and high computational complexity, which makes them difficult to apply to the UAV platform. In this paper, a target re-detection tracking algorithm (RDT) after tracking loss is designed for mobile platforms. RDT uses DCF in simple scenes to track targets and establish a target model between different frames. To ensure the algorithm when tracking is lost due to occlusion or moving out of view, an efficient switching criterion is designed to indirectly invoke the detection algorithm to re-capture the target and guide online learning of DCF. And the experiment results on the OTB benchmark show that RDT can re-capture the target after tracking is lost, and the speed of operation on the CPU is 85fps.

Multirobot Fully Distributed Active Joint Localization and Target Tracking

In this article, we study the problem of multirobot active joint localization and target tracking (AJLATT), where a team of robots mounted with sensors of limited field of view actively estimate their own and the target’s states cooperatively. Each robot designs its motion strategy to gain better estimation performance while avoiding collisions by using only the information from itself and its one-hop communicating neighbors. By leveraging the framework of joint localization and target tracking (JLATT) presented in our previous work, we propose two fully distributed algorithms that help each robot design motion strategies to achieve better localization and target tracking performance. These two algorithms are designed from, respectively, the control and optimization perspectives. The control-based algorithm is designed by incorporating the estimated target’s and robots’ states and their uncertainties as well as collision avoidance in the control policy. The optimization-based algorithm minimizes an objective function involving both the target’s and robots’ estimation uncertainties and a potential function that helps each robot avoid collision and maintain communication connectivity when the robot is planning its motion. Monte Carlo simulations demonstrate our algorithms’ feasibility to solve the AJLATT problem, and performance comparison between these two algorithms is given.

A predictive target tracking framework for IoT using CNN–LSTM

A predictive target tracking framework for IoT using CNN–LSTM

Autonomous landing algorithm of UAV based on Target tracking

The target tracking technology in the UAV autonomous landing process is studied. Based on the analysis of the occlusion, background change, and variable scale problems in the target tracking process, a scale adaptive method for UAV target tracking based on KCF (Kernelized Correlation Filter) algorithm is proposed. The original KCF target tracking framework is adopted to achieve the target position prediction function. Secondly, to address the variable scale problem of moving targets and the target loss problem caused by scale changes, the scale filter of the DSST target tracking algorithm is used. The algorithm is for estimating the scale of moving targets and generating a small-scale filter estimate to improve the tracking efficiency of the UAV for moving targets and reduce the target loss rate. The final test on the OTB dataset showed a 4% improvement in variable scale accuracy and a 2.9% improvement in variable scale success rate. A Gazebo 3D environment scene was set up under the Linux system, and UAV autonomous landing simulation experiments were conducted to verify the improved algorithm’s real-time effectiveness in the UAV autonomous landing application. The simulation results show that the improved KCF target tracking algorithm has real-time performance in the UAV autonomous landing trajectory tracking process.

A Moving Target Tracking Framework Based on a Set and Its Topological Space

Moving target tracking is a technology that matches frames and images based on target characteristics. This technology is widely utilized in intelligent transportation, logistics transportation, public security, sports event broadcasting, and other fields. Existing research focuses primarily on improving target detection and tracking algorithms to improve target retrieval and tracking efficiency. However, the majority of studies focus on global and full-range retrieval. More importantly, in large video scenes with multiple camera collaborations, these methods rarely consider the efficiency of target retrieval and tracking. Based on relevant theories and methods of video GIS, set theory, and topology, in this paper, a set and its topology space covering road networks, cameras, videos, and key frames were constructed. Additionally, the positioning, tracking, and track representation of a moving target based on the set and its topology space were solved. Compared to the feature vector algorithm, video summarization and Meanshift algorithm, the experimental findings reveal that the target retrieval performance, algorithm stability, and robustness are improved.

Trustworthy Target Tracking With Collaborative Deep Reinforcement Learning in EdgeAI-Aided IoT

Mobile target tracking with artificial intelligence (AI) approaches such as deep reinforcement learning (DRL) in edge-assisted Internet of Things (Edge-IoT) platform can be promising. In this article, we propose <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DRLTrack</monospace> , a framework for target tracking with a collaborative DRL called C-DRL in Edge-IoT with the aim to obtain two major objectives: high quality of tracking (QoT) and resource-efficient network performance. In <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DRLTrack</monospace> , a huge number of IoT devices are employed to collect data about a target of interest. One or two edge devices in the network coordinate with a group of IoT devices and collaboratively detect the target by using the C-DRL approach and form an area around the target by the group of IoT devices. To maintain such an area during the tracking time, we employ a deep Q-network to track the target from one group to another. An EdgeAI sitting on the top of the edge devices has the control of the C-DRL approach during tracking and can identify a sequence of tracks. <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DRLTrack</monospace> is said to be <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">trustworthy</i> as it shows trustworthy performance in terms of QoT, dynamic environments, and even under certain cyberattacks. We validate the performance of <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DRLTrack</monospace> considering the objectives through simulations and it demonstrates superior performance compared with existing work.

A General Framework for Slow and Weak Range-Spread Ground Moving Target Indication Using Airborne Multichannel High-Resolution Radar

Airborne multichannel high-resolution radar (HRR)-ground moving target indication (GMTI) is of great significance to wide-area surveillance, traffic monitoring and target recognition. The Aerospace Information Research Institute, Chinese Academy of Sciences, produced an advanced airborne digital array radar with high resolution and conducted an experiment with slow and weak cooperative moving targets in 2021. In this paper, an overall processing framework for target detection, parameter estimation and target tracking using this system is introduced. For HRR detection, the echo energy of targets is spread into multiple range units, so-called range-spread targets; thus, using detectors designed for point-like targets will severely degrade the detection performance, especially for slow and weak targets. To address the adaptive detection of such range-spread targets embedded in Gaussian clutter with an unknown covariance matrix, a novel two-step generalized space-time adaptive processing (GSTAP) algorithm is proposed, which offers an enhanced clutter suppression capability compared with natural competitors. Moreover, a tracking method is implemented in the range-Doppler domain to avoid track loss caused by azimuth relocation error and reject discrete false alarms. Both simulation and experimental results are presented to demonstrate the effectiveness of the proposed method and provide a paradigm for further research.