Target Tracking Research Articles

Critical band-to-band-tunnelling based optoelectronic memory

Neuromorphic vision hardware, embedded with multiple functions, has recently emerged as a potent platform for machine vision. To realize memory in sensor functions, reconfigurable and non-volatile manipulation of photocarriers is highly desirable. However, previous technologies bear mechanism challenges, such as the ambiguous optoelectronic memory mechanism and high potential barrier, resulting in a limited response speed and a high operating voltage. Here, for the first time, we propose a critical band-to-band tunnelling (BTBT) based device that combines sensing, integration and memory functions. The nearly infinitesimal barrier facilitates the tunnelling process, resulting in a broadband application range (940 nm). Furthermore, the observation of dual negative differential resistance (NDR) points confirms that the critical BTBT of photocarriers contributes to the sub-microsecond photomemory speed. Since the photomemory speed, with no motion blur, is important for motion detection, the critical BTBT memory is expected to enable moving target tracking and recognition, underscoring its superiority in intelligent perception.

Salience-dependent disruption of sustained auditory attention can be inferred from evoked pupil responses and neural tracking of task-irrelevant sounds.

Stimulus-driven attention allows us to react to relevant stimuli (and imminent danger!) outside our current focus of attention. But irrelevant stimuli can also disrupt attention; for example, during listening to speech. The degree to which sound captures attention is called salience, which can be estimated by existing, behaviorally validated, computational models (Huang & Elhilali, 2017). Here we examined whether neurophysiological responses to task-irrelevant sounds indicate the degree of distraction during a sustained-listening task and how much this depends on individual hearing thresholds. N = 47 Danish-speaking adults (28/19 female/male; mean age: 60.1, SD: 15.9 years) with heterogenous hearing thresholds (PTA; mean: 25.5, SD: 18.0 dbHL) listened to continuous speech while one-second-long, task-irrelevant natural sounds (distractors) of varying computed salience were presented at unpredictable times and locations. Eye tracking and electroencephalography were used to estimate pupil response and neural tracking, respectively. The task-irrelevant sounds evoked a consistent pupil response (PR), distractor-tracking (DT) and a drop of target-tracking (ΔTT), and statistical modelling of these three measures within subjects showed that all three are enhanced for sounds with higher computed salience. Participants with larger PR showed a stronger drop in target tracking (ΔTT) and performed worse in target speech comprehension. We conclude that distraction can be inferred from neurophysiological responses to task-irrelevant stimuli. These results are a first step towards neurophysiological assessment of attention dynamics during continuous listening, with potential applications in hearing-care diagnostics.Significance statement Successful speech-in-noise comprehension in daily life does not only depend on the acuity of the auditory input, but also cognitive factors like attentional control. Being able to measure distraction-dependent neurophysiological responses to peripheral, task-irrelevant stimuli would enable monitoring the extent to which the attentional focus is instantaneously captured away from a target under sustained attention. Here we show that especially pupil response and neural tracking of distractor sounds reflect the degree to which people with both normal and elevated hearing thresholds are distracted. Such a measure could be used to non-invasively track the focus of attention and thus could find application in hearing care diagnostics, where cognitive factors like attentional control are being increasingly recognized as important.

Efficient and accurate feature-aided active tracking for underwater small targets in highly cluttered harbor environments using a full motion acoustic flow field solution.

To address the issue of tracking highly maneuverable small underwater intruders in the dynamic and heavily interfered environment of harbors, a local sparse motion acoustic flow (LSMAF) computation method constrained by robust high-order flux tensor (RHO-FT) feature has been proposed, along with a LSMAF feature-aided active tracking method. First, potential targets are localized from the dense dynamic clutter background of active sonar echographs using RHO-FT feature maps. Subsequently, on the basis of a dense motion acoustic flow calculation method, a local motion consistency criterion is introduced to the potential target area, establishing a method for calculating LSMAF, which updates the precise motion vectors of potential targets in real time. Finally, all measurements obtained from the RHO-FT feature map are iteratively filtered together with their corresponding motion vectors to maintain the kinematic consistency of the potential target's trajectory. Experiments conducted on a series of cooperative targets in real-world harbor environments show that LSMAF-aided tracking method outperforms the latest developments of tracking for underwater targets in terms of both tracking efficiency and trajectory accuracy.

Multivariate Fuzzy Density-Based Temporospatial Clustering of Applications With Noise (MF-DBTSCAN) Algorithm for Detection and Tracking of Multiple Targets by 77-GHz Millimeter Wave Radar Sensor

Multivariate Fuzzy Density-Based Temporospatial Clustering of Applications With Noise (MF-DBTSCAN) Algorithm for Detection and Tracking of Multiple Targets by 77-GHz Millimeter Wave Radar Sensor

Trajectory tracking of QUAV based on cascade DRL with feedforward control

The adoption of advanced control strategies has become increasingly critical for the quadrotor unmanned aerial vehicle (QUAV). Deep reinforcement learning (DRL) stands at the forefront of these developments, showcasing significant utility, particularly in the realm of static target tracking for QUAVs. However, existing DRL methodologies encounter substantial challenges with latency issues when applied to trajectory tracking scenarios. This paper tackles this challenge by incorporating a feedforward technique, which empowers agents to analyze high order trajectory information. Initially, a cascade DRL controller for fixed point tracking is trained, where multiple agents are separately responsible for translation and rotation movement along each axis. Then, the controller is implemented for trajectory tracking by incorporating the feedforward information from the trajectory, which significantly solves the latency issue. Through extensive tracking demonstrations and quantitative analysis, the proposed integrated scheme demonstrates a significant enhancement in the trajectory tracking performance of QUAVs.

Target tracking control for Unmanned Surface Vehicles: An end-to-end deep reinforcement learning approach

Target tracking control for Unmanned Surface Vehicles: An end-to-end deep reinforcement learning approach

Particle Filter Tracking System Based on Digital Zoom and Regional Image Measure

To address the challenges of low accuracy and the difficulty in balancing a large field of view and long distance when tracking high-speed moving targets with a single sensor, an ROI adaptive digital zoom tracking method is proposed. In this paper, we discuss the impact of ROI on image processing and describe the design of the ROI adaptive digital zoom tracking system. Additionally, we construct an adaptive ROI update model based on normalized target information. To capture target changes effectively, we introduce the multi-scale regional measure and propose an improved particle filter algorithm, referred to as the improved multi-scale regional measure resampling particle filter (IMR-PF). This method enables high temporal resolution processing efficiency within a high-resolution large field of view, which is particularly beneficial for high-resolution videos. The IMR-PF can maintain high temporal resolution within a wide field of view with high resolution. Simulation results demonstrate that the improved target tracking method effectively improves tracking robustness to target motion changes and reduces the tracking center error by 20%, as compared to other state-of-the-art methods. The IMR-PF still maintains good performance even when confronted with various interference factors and in real-world scenario applications.

Improving Tracking of Selective Attention in Hearing Aid Users: The Role of Noise Reduction and Nonlinearity Compensation.

Hearing impairment (HI) disrupts social interaction by hindering the ability to follow conversations in noisy environments. While hearing aids (HAs) with noise reduction (NR) partially address this, the "cocktailparty problem" persists, where individuals struggle to attend to specific voices amidst background noise. This study investigated how NR and an advanced signal processing method for compensating for nonlinearities in EEG signals can improve neural speech processing in HI listeners. Participants wore hearing aids with NR, either activated or deactivated, while focusing on target speech amidst competing masker speech and background noise. Analysis focused on temporal response functions to assess neural tracking of relevant target and masker speech. Results revealed enhanced neural responses (N1 and P2) to target speech, particularly in frontal and central scalp regions, when NR was activated. Additionally, a novel method compensated for nonlinearities in EEG data, leading to improved signal-to-noise ratio (SNR) and potentially revealing more precise neural tracking of relevant speech. This effect was most prominent in the left-frontal scalp region. Importantly, NR activation significantly improved the effectiveness of this method, leading to stronger responses and reduced variance in EEG data and potentially revealing more precise neural tracking of relevant speech. This study provides valuable insights into the neural mechanisms underlying NR benefits and introduces a promising EEG analysis approach sensitive to NR effects, paving the way for potential improvements in HAs.Significance Statement Understanding how hearing aids (HAs) with noise reduction (NR) improve selective auditory attention in noisy environments is crucial for future advancements. This study investigated the neural effects of NR in hearing-impaired listeners using EEG. We observed significantly enhanced neural responses (N1 and P2 peaks) to target speech with NR activated, suggesting improved speech tracking in frontal and central scalp regions. The advanced signal processing method also compensated for nonlinearities in EEG data, improving the signal-to-noise ratio (SNR) and revealing more precise neural tracking, particularly in the left-frontal scalp region. This study sheds light on the neural mechanisms behind NR benefits and introduces a promising EEG analysis method sensitive to NR effects, paving the way for optimizing future HAs.

Node Selection and Path Optimization for Passive Target Localization via UAVs

The performance of passive target localization is affected by the positions of unmanned aerial vehicles (UAVs) at a large scale. In this paper, to improve resource utilization efficiency and localization accuracy, the node selection problem and the path optimization problem are jointly investigated. Firstly, the target passive localization model is established and the Chan-based time difference of arrival (TDOA) localization method is introduced. Then, the Cramer–Rao lower bound (CRLB) for Chan-TDOA localization is derived, and the problems of node selection and path optimization are formulated. Secondly, a CRLB-based node selection method is proposed to properly divide the UAVs into several groups, localizing different targets, and a CRLB-based path optimization method is proposed to search for the optimal UAV position configuration at each time step. The proposed path optimization method also effectively handles no-fly-zone (NFZ) constraints, ensuring operational safety while maintaining optimal target tracking performance. Also, to improve the efficiency of path optimization, particle swarm algorithm (PSO) is applied to accelerate the searching process. Finally, numerical simulations are performed to verify the validity and effectiveness of the proposed methods in this paper.

Dual-prompt complementary fusion network for RGBT tracking

RGBT target tracking is a significant downstream task in the field of object tracking. However, compared to visible light target tracking, RGBT target tracking faces the challenge of smaller datasets, making it difficult to achieve performance levels comparable to those achieved in visible light target tracking. To address how to effectively combine the complementary characteristics of visible and thermal modalities, as well as how to fully leverage the superior performance of models trained on visible light target tracking tasks, while also aiming for lower computational costs and higher tracking effectiveness, a dual-prompt complementary fusion strategy for an RGBT tracking network is proposed. Drawing on the concept of prompt learning, this network aims to extend the efficient performance of visible light target tracking to the RGBT target tracking domain. In its implementation, the prompt module inputs both visible and thermal modality information as dual prompts into the backbone network, where the network utilizes these prompts to generate new, enriched prompt information at each layer. Subsequently, an information enhancement fusion module enhances the acquired prompt information and refeeds it into the backbone network, aiming to improve the tracking accuracy and robustness. Experimental results on GTOT, RGBT234 and LasHeR datasets show that the tracking accuracy (PR) and success rate (SR) of the network reach 93.1%/76.8%, 84.4%/62.4% and 66.8%/53.8%, respectively, which is improved compared with the current mainstream RGBT target tracking network, which verifies the effectiveness of the network.

A Double Extended Kalman Filter Algorithm for Weakening Non-Line-of-Sight Errors in Complex Indoor Environments Based on Ultra-Wideband Technology

In complex indoor environments, target tracking performance is impacted by non-line-of sight (NLOS) noises and other measurement errors. In order to fix NLOS errors, a double extended Kalman filter (DEKF) algorithm is proposed, which refers to a kind of cascaded structure composed of two Kalman filters. In the proposed algorithm, the first filter is a classic Kalman filter (KF) and the second is an extended Kalman filter (EKF). Time of arrival (TOA) measurements collected by multiple stationary ultra-wideband (UWB) sensors are used. The residual errors between the measured TOA and that of the first KF are predicted, and the covariance of the first KF is adjusted correspondingly. Then, we use the estimated distance state of the first KF as a measurement vector for the second EKF in order to obtain a smoother observation. One of the advantages of the proposed algorithm is that it is able to perform target tracking with good accuracy even without or with only one LOS TOA measurement for a period of time without prior information about the NLOS noise, which may be difficult to obtain in practical applications. Another advantage is that the accuracy does not greatly decrease when NLOS noises exist for a long period of time. Finally, the proposed DEKF can maintain the high-precision positioning characteristics in both the constant velocity (CV) model and the constant acceleration (CA) model in the LOS/NLOS environment. Our simulation and experimental results show that the proposed algorithm performs much better than other algorithms in SOTA, particularly in severe mixed LOS/NLOS environments.

On-Satellite Implementation of Real-Time Multi-Object Moving Vehicle Tracking with Complex Moving Backgrounds

On-satellite information processing enables all-weather target tracking. The background of videos from satellite sensors exhibits an affine transformation due to their motion relative to the Earth. In complex moving backgrounds, moving vehicles have a small number of pixels and weak texture features. At the same time, the resources and performance of on-satellite equipment are limited. To address these issues, we propose a multi-object tracking (MOT) algorithm with a detection–association framework for moving vehicles in complex moving backgrounds and implement the algorithm on a satellite to achieve real-time MOT. We use feature matching to effectively eliminate the effects of background motion and use the neighborhood pixel difference method to extract moving vehicle targets in the detection stage. The accurate extraction of motion targets ensures the effectiveness of target association to achieve MOT of moving vehicles in complex moving backgrounds. Additionally, we use a Field-Programmable Gate Array (FPGA) to implement the algorithm completely on a satellite. We propose a pixel-level stream processing mode and a cache access processing mode, given the characteristics of on-satellite equipment and sensors. According to the experimental results, the prototype on-satellite implementation method proposed in this paper can achieve real-time processing at 1024 × 1024 px@47 fps.

A Novel Non-Line-of-Sight Error Mitigation Algorithm Using Double Extended Kalman Filter for Ultra-Wide Band Ranging Technology

In complex indoor environments, target tracking performance is impacted by non-line-of-sight (NLOS) noises and other measurement errors. In order to fix NLOS errors, a Double Extended Kalman filter (DEKF) algorithm is proposed, which refers to a kind of cascaded structure composed of two Kalman filters. In the proposed algorithm, the first filter is a classic Kalman filter (KF) and the second is an Extended Kalman filter (EKF). The time of arrival (TOA) measurements collected by multiple stationary ultra-wide band (UWB) sensors are used. Residual errors between the measured TOA and the prediction from the first KF are used to adjust the covariance of the first KF accordingly. Then, we use the estimated distance state of the first KF as a measurement vector of the second EKF in order to obtain a smoother observation. One of the advantages of the proposed algorithm is that it is able to perform target tracking with a good accuracy even without or with only one line-of-sight(LOS) TOA measurement for a period of time without prior information of the NLOS noise, which may be difficult to obtain in practical applications. Another advantage is that the accuracy does not significantly decrease when NLOS noises persist for a long period of time. Finally, the proposed DEKF can maintain high-precision positioning characteristics in both the constant velocity (CV) model and the constant acceleration (CA) model for LOS/NLOS environments. In the case of mixed LOS/NLOS environments, the RMSE of the proposed algorithm can be kept within 5 cm, while the RMSEs of other compared algorithms are easily beyond tens of centimeters. At the same time, when the confidence of RMSE is set to 95% for 1000 MC simulations, the confidence interval of the proposed algorithm is the smallest, and the mean value is 3–5 times closer to the true value compared to other algorithms. Simulation and experimental results show that the proposed algorithm performs much better than other state-of-the-art algorithms, particularly in severe mixed LOS/NLOS environments.

Multicooperation of Turtle-inspired amphibious spherical robots

It is challenging to achieve high-speed and accurate multicooperation of turtle-inspired amphibious spherical robots (ASRs) in turbid water and confined spaces when the robots are underwater movement with multiple degrees of freedom (MDOF). This paper innovatively proposes a control strategy for modelling and experimental platforms that can communicate and cooperate between multiple robots. First, a novel underwater kinematic model using the unit quaternion (UQ) algorithm is proposed based on attitude interpolation to realize MDOF movement. Then, the ASRs use a camera acquisition compartment to realize underwater target recognition and tracking by adjusting their motion trajectory. Finally, multirobot cooperation and three-dimensional (3-D) movement experiments using ASRs verifies the effectiveness of the proposed cooperation mode and 3-D underwater movement according to the control strategy implemented. The control strategy and experimental results presented in this paper can inspire the efficient communication and cooperation of multiple bionic robots, which are currently popular research topics.

Ultraviolet target tracking using mask-based four-pixel parallel detection

Ultraviolet target tracking using mask-based four-pixel parallel detection

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.

Remote Sensing Target Tracking Method Based on Super-Resolution Reconstruction and Hybrid Networks

Remote Sensing Target Tracking Method Based on Super-Resolution Reconstruction and Hybrid Networks

An Ultrasound-Guided Miniature Hand-Eye Integrated Robot for Percutaneous Needle Placement

Abstract Ultrasound-guided percutaneous puncture technology has advantages such as intra-operative real-time imaging, noninvasive operation, high targeting accuracy, nonionizing radiation, and low cost. However, traditional percutaneous puncture surgery requires doctors to hold ultrasound probes or puncture needles, which causes complex operations. In this article, by integrating ultrasound and needle insertion mechanisms, an ultrasound-guided miniature puncture robot is proposed. This robot can work without an external navigation or industrial or cooperative manipulator after hand-eye calibration and acknowledge the coordinate relationship between the ultrasound image and the robot tip. A three degrees-of-freedom (DoFs) of in-plane mechanism using linear actuators is designed so that the puncture needle can always be scanned by ultrasound during the operation, ensuring real-time monitoring. The method of planning puncture path, modeling the robot kinematics, and ultrasound hand-eye calibration are proposed. To track a needle in an ultrasound image, the image recognition and filter algorithm for the needle tip are presented. The accuracy of the robot puncture operation is verified by point targeting and path tracking experiments in the water tank and phantom, and the puncture error of the robot is 1.5 ± 0.5 mm in the water tank, 1.98 mm in the abdominal phantom, and 1.41 mm in the breast phantom. Finally, the work of this article effectively improves the availability and effectiveness of the ultrasound-guided puncture robot.

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.

A deep learning based detection algorithm for anomalous behavior and anomalous item on buses

This paper proposes a new strategy for analysing and detecting abnormal passenger behavior and abnormal objects on buses. First, a library of abnormal passenger behaviors and objects on buses is established. Then, a new mask detection and abnormal object detection and analysis (MD-AODA) algorithm is proposed. The algorithm is based on the deep learning YOLOv5 (You Only Look Once) algorithm with improvements. For onboard face mask detection, a strategy based on the combination of onboard face detection and target tracking is used. To detect abnormal objects in the vehicle, a geometric scale conversion-based approach for recognizing large-size ab-normal objects is adopted. To apply the algorithm effectively to real bus data, an embedded video analysis system is designed. The system incorporates the proposed method, which results in improved accuracy and timeliness in detecting anomalies compared to existing approaches. The algorithm’s effectiveness and applicability is verified through comprehensive experiments using actual video bus data. The experimental results affirm the validity and practicality of the pro-posed algorithm.