Search

Picking robots have been widely used for citrus harvesting in recent years. However, the rest citrus during continuous picking can be irregularly disturbed by the wind, robot force, and the load weight of bearing branches under the natural environment. The citrus in the disturbed state cannot be rapidly and accurately detected, and then localized online, leading to the low efficiency of automatic robotic picking. In this study, online target detection and rapid localization were proposed using improved YOLOv5s+DeepSORT. The position of citrus at rest was predicted using the motion-tracking trajectory of disturbed citrus within a short period of time. The coordinates of the citrus were then obtained rapidly. Firstly, the CBAM (Convolutional Block Attention Module) attention mechanism was added to the YOLOv5s network, in order to detect the small and occluded targets. The SIoU loss function was used to enhance the direction matching between the prediction and the calibration frame, in order to improve the convergence speed of regression. Secondly, the target re-identification network was improved in the DeepSORT more suitable for the feature extraction of citrus targets. The feature extraction of the network was enhanced to improve the tracking performance on the disturbed citrus; The Count counter was used to accumulate the number of tracking frames in each citrus for an optimal target. Since the disturbance of the rest citrus was progressively propagated over time, the localization prediction and picking were only for targets with optimal tracking trajectories at a time. The real-time updating was realized in real time. Finally, the values of the depth camera were combined within the critical distance range, excluding the influence of background citrus on the detection speed. The number of tracking targets each time was limited to effectively improve the tracking speed of disturbed citrus. The experimental results show that the P (precision) and mAP (average detection accuracy) of improved YOLOv5s were improved by 3.9 and 1.1 percentage points, respectively, with a detection rate of 69.3 frames per second. The MOTA (Multi-Object Tracking Accuracy) and MOTP (Multi-Object Tracking Precision) of the improved DeepSORT were improved by 9.2 and 5.4 percentage points, respectively, whereas, the average number of ID (identity) switching times of targets was reduced by 32 times. Grasping experiments were conducted in the laboratory, in which the citrus was randomly swung along different orientations with an amplitude of about 10 cm. When the predicted localization time was 1, 2, 3, 5, 7, and 10 s, the average precision values of disturbed citrus localization were 21.3%, 53.0%, 81.9%, 83.7%, 86.1%, and 94.9%, respectively. The citrus picking test was conducted with the citrus localization time of 3 s. The average grabbing time for each citrus was 12.8 s, which was 5.6 s shorter than that without the optimization. The efficiency was improved by 30.4%. This finding can provide technical support and references for citrus picking in disturbed states. [ABSTRACT FROM AUTHOR]

Accurate tracking of tropical cyclones (TCs) can provide regions of interest for intelligent forecasting of TC tracks and intensity. There have been few studies on algorithms for automatic TC tracking. This study proposes an effective TC tracking method based on deep learning combined with infrared satellite images. The study first constructed a TC tracking dataset based on the infrared images of the China Fengyun-2D geostationary satellite covering six different TC intensity levels between 2009 and 2012. This included 47 complete cases (video sequences) of TCs from generation to extinction. Based on deep learning, the visual tracking algorithm SiamRPN was used as the model framework. Combining Bi-GRU and TC cloud spatiotemporal evolution characteristics to improve the performance of the SiamRPN network, the SiamTCNet target-tracking model was designed to track TCs automatically. Considering that the shape and scale of TC changes with time, a TC is regarded as a typical non-rigid object with obvious timing characteristics, so the first frame of a TC video sequence is combined with the satellite images of the first three frames of the current frame as inputs to the proposed SiamTCNet model, which then extracts the evolution of the TC's spatial structure and its bidirectional temporal change information. The experimental results show that the TC tracking of the proposed model is a significant improvement over the original SiamRPN model. [ABSTRACT FROM AUTHOR]

Copyright of Ordnance Industry Automation is the property of Editorial Board for Ordnance Industry Automation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The automatic identification system (AIS) can improve situational awareness at sea, but its protocol is simple and does not guarantee message integrity, authentication, and proper use. For example, the lack of safety measures creates problems when AIS messages are used for tracking a target or predicting a target trajectory. We present a methodology for the validation of AIS messages, a prerequisite for their safe use in maritime situational awareness applications. The validation method relies on target trackers that fuse AIS data and exteroceptive sensor data, and it detects errors in position, speed and course, and rate of turn. We use radar data to exemplify exteroceptive sensor data. With the use of simulated data, we show that the proposed methods effectively detect errors in the position and velocity data received through AIS messages and are also able to detect errors in turn-rate data. The effectiveness of the methods is demonstrated on a real-world dataset with injected false AIS data. [ABSTRACT FROM AUTHOR]

Target tracking is a crucial application in wireless sensor networks. Current algorithms for target tracking primarily involve node scheduling based on trajectory prediction. However, when the target is lost due to prediction errors, a target recovery mechanism initiates a search operation, potentially activating numerous nodes and leading to increased energy consumption. Furthermore, the recovery process may result in data loss. To address these challenges, we propose a fault-tolerant clustering approach using the Cat Optimization Algorithm to minimize the probability of target loss. To assess the effectiveness of our approach, simulations were conducted in OPNET using the NODIC, DCRRP, BFOABMS, and AFSRP protocols. The results illustrate that our method excels over existing approaches across various metrics. Specifically, compared to the well-known NODIC method, our approach reduces end-to-end delay by 84.93%, media access delay by 15.08%, increases throughput rate by 3.84%, lowers energy consumption by 4.49%, improves signal-to-noise ratio by 9.99%, and enhances delivery rate of data to the sink by 1.02%. Additionally, compared to the widely recognized DCRRP method, our method improves media access delay by 2.90%, throughput rate by 2.02%, reduces energy consumption by 0.30%, enhances signal-to-noise ratio by 7.36%, and improves the delivery rate of data to the sink by 0.41%. Moreover, our proposed method decreases the end-to-end delay by 10.28% compared to DCRRP. Also, the superior performance of the proposed method in terms of end-to-end delay is 1.52%, media access delay by 8.73%, throughput rate by 1.97%, energy consumption by 0.33%, signal-to-noise ratio by 9.25%, and delivery rate of successfully sending data to the sink is 0.76% higher than the well-known AFSRP method.Additionally, compared to the widely recognized BFOABMS method, our method improves media access delay by 9.56% and enhances the delivery rate of data to the sink by 0.70%. However, in our proposed method, the energy consumption criterion has increased by 13.63%, the end-to-end delay criterion by 50.78%, the signal-to-noise ratio decreased by 15.66%, and the throughput ratio decreased by 26.88% compared to BFOABMS. [ABSTRACT FROM AUTHOR]

Solar active regions serve as the primary energy sources of various solar activities, directly impacting the terrestrial environment. Therefore precise detection and tracking of active regions are crucial for space weather monitoring and forecasting. In this study, a total of 4577 HMI and MDI longitudinal magnetograms are selected for building the dataset, including the training set, validating set, and ten testing sets. They represent different observation instruments, different numbers of activity regions, and different time intervals. A new deep learning method, ReDetGraphTracker, is proposed for detecting and tracking the active regions in full-disk magnetograms. The cooperative modules, especially the redetection module, NSA Kalman filter, and the splitter module, better solve the problems of missing detection, discontinuous trajectory, drifting tracking bounding box, and ID change. The evaluation metrics IDF1, MOTA, MOTP, IDs, and FPS for the testing sets with 24-h interval on average are 74.0%, 74.7%, 0.130, 13.6, and 13.6, respectively. With the decreasing intervals, the metrics become better and better. The experimental results show that ReDetGraphTracker has a good performance in detecting and tracking active regions, especially capturing an active region as early as possible and terminating tracking in near-real time. It can well deal with the active regions whatever evolve drastically or with weak magnetic field strengths, in a near-real-time mode. [ABSTRACT FROM AUTHOR]

In order to solve the problems of loss of moving targets due to the flight status of the unmanned aerial vehicle (UAV) itself, the interference of the environment the randomness of the target and other reasons in the process of collecting moving target image information by the UAV platform, a deep deterministic policy gradient (DDPG) algorithm UAV following method based on moving target recognition was proposed. Facing the vehicle target on the highway, the relationship among the height, posture and high-speed vehicle motion of the UAV was analyzed. the velocity adaptive model of the target detection frame rate of the mobile platform was estab lished, and the flight attitude and speed of the UAV were corrected in real time according to the motion state of the target, so that the UAV could maintain the relative position and angle with the target. Then, based on the value network of DDPG algorithm, the value of UAV taking spe- cific actions in different states was estimated; the strategy network generates the strategy of UAV taking actions in a given state, and gives UAV flight altitude and speed control parameters for target tracking, so that the UAV could automatically adjust the flight state according to the movement change of the target, and realize the adaptive tracking of the moving target. Simulation experiments show that the DDPG algorithm can provide stable flight attitude data and a reliable control basis for the UAV following task, and the UAV can track the ground moving target in a circular area with a speed range of 0~33 m/s and a radius of 120 m in real time, and can achieve continuous and stable tracking within the endurance range. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this paper, we address the trajectory-/target-tracking and obstacle-avoidance problem for nonholonomic mobile robots subjected to diamond-shaped velocity constraints and predefined output performance specifications. The proposed scheme leverages the adaptive performance control to dynamically adjust the user-defined output performance specifications, ensuring compliance with input and safety constraints. A key feature of this approach is the integration of multiple constraints into a single adaptive performance function, governed by a simple adaptive law. Additionally, we introduce a robust velocity estimator with a priori-determined performance attributes to reconstruct the unmeasured trajectory/target velocity. Finally, we validate the effectiveness and robustness of the proposed control scheme, through extensive simulations and a real-world experiment. [ABSTRACT FROM AUTHOR]

In order to solve the related problems of detection and tracking of shallow marine organisms, this paper designs a YOLO v5 multi‐target detection and tracking algorithm with attention mechanism. When working underwater, the authors usually encounter many difficulties. Different luminosity and complex coral background usually affect the detection of marine organisms. At the same time, the unrestricted movement of marine organisms, the ability to hide behind rocks and algae, and their mutual occlusion while swimming pose additional challenges to this task. Considering the characteristics of shallow marine organisms activity environment, the attention mechanism is added to the feature extraction network of YOLO v5 to reduce redundant information and improve the detection accuracy of shallow marine organism targets in complex environment. The improved algorithm improves the average detection accuracy of marine organisms target detection by 3.2%. Aiming at the problem of shallow marine organisms target tracking, a shallow marine organisms multi‐target tracking algorithm based on improved Deep Simple Online And Realtime Tracking (SORT) is designed. The improved YOLO v5 algorithm is used to replace Faster R‐CNN (Faster Region‐Convolutional Neural Networks) as the detector of DeepSORT tracking algorithm, and the cascade matching strategy is adopted to solve the problem that the target cannot be tracked continuously when it is occluded for a long time. The experimental results show that the shallow marine organisms multi‐target tracking algorithm based on improved DeepSORT reduces the number of id transformation of marine biological target tracking in shallow sea environment, and improves the accuracy of shallow marine organisms multi‐target tracking. [ABSTRACT FROM AUTHOR]

Underwater sensor networks hold immense potential for advancing the field of underwater target tracking, yet they encounter significant resource constraints stemming from energy storage and communication methods. In order to balance tracking accuracy and energy consumption, the authors present a distributed bearing‐only target tracking algorithm that can be used in underwater sensor networks with resource constraints. Anchored in the diffusion cubature information filter framework, this algorithm achieves fusion for non‐linear bearing measurements and state estimation. During the incremental update stage, individual nodes leverage the Posterior Cramer‐Rao Lower Bound as a metric for tracking performance. Subsequently, a strategy for selecting neighbouring nodes is introduced, ensuring tracking accuracy while efficiently kerbing energy consumption. In the diffusion update stage, a multi‐threshold event triggering mechanism is employed to partially diffuse the intermediate estimation. Additionally, an adaptive convex combination weight is proposed for cases involving partial diffusion. Through theoretical analysis, the asymptotic unbiasedness and convergence of the algorithm have been proven. Through Monte Carlo simulation experiments, the authors verify that the algorithm is superior to existing algorithms. Furthermore, the algorithm significantly reduces energy consumption in information interaction, minimising tracking accuracy loss. [ABSTRACT FROM AUTHOR]

The application of the hybrid extended Kalman filter (HEKF), hybrid unscented Kalman filter (HUKF), hybrid particle filter (HPF), and hybrid extended Kalman particle filter (HEKPF) is discussed for hybrid non‐linear filter problems, when prediction equations are continuous‐time and the update equations are discrete‐time, and also the discrete extended Kalman filter (DEKF), discrete unscented Kalman filter (DUKF), discrete particle filter (DPF), and discrete extended Kalman particle filter (DEKPF) for discrete‐time non‐linear filter problems, when prediction equations and update equations are discrete‐time. In order to assess the performance of the filters, the authors consider the non‐linear dynamics for a re‐entry vehicle. The filters are used in two hybrid and discrete states to estimate the position, velocity, and drag parameter associated with the re‐entry vehicle. Theoretical topics concerning estimating the drag parameter of a vehicle in re‐entry phase have been dealt with. Drag parameter estimation is carried out using a combination of hybrid filters and discrete filters as an effective estimator and fixed value, forgetting factor, and Robbins‐Monro stochastic approximation methods as the noise covariance matrix adjuster of the parameter. [ABSTRACT FROM AUTHOR]

Accurate positioning of intelligent connected vehicle (ICV) is a key element for the development of cooperative intelligent transportation system. In vehicular networks, lots of state‐related measurements, especially the mutual measurements between ICVs, are shared. It is an advisable strategy to fuse these measurements for a more robust positioning. In this context, an innovative framework, referred to as multisource‐multitarget cooperative positioning (MMCP) is presented. In MMCP, ICVs are local information source, that upload both the states of ICVs estimated by on‐board sensors and the relative vectors between surrounding objects and vehicles to a fusion centre. In the fusion centre, ICVs are selected as the global targets, and the relative vectors are converted into global measurements. Then, the MMCP is modelled into a multi‐target tracking problem with specific targets. This paper proposes a low complexity Gaussian mixture probability hypothesis density (GM‐PHD‐LC) filter to match and fuse the global measurements to further improve the estimation of ICVs. The evaluation results show that our GM‐PHD‐LC can provide 10 Hz positioning services in urban area, and significantly improve the positioning accuracy compared to the standalone global navigation satellite system. [ABSTRACT FROM AUTHOR]

In order to solve the problem of low tracking accuracy of the traditional group target tracking algorithms in point-group coexistence scenarios, a trajectory Poisson multi--Bernoulli mixture (TPMBM) filtering algorithm is proposed, which can track both point target and group target simultaneously. The algorithm expands the state space of the target, introduces probability information about the target class based on the standard point target and the group target models, and achieves the judgment of the target class and the estimation of the target motion state through the prediction and update process of the TPMBM filter. Simulation results show that, compared with the existing algorithms, the proposed algorithm has significantly lower miss detection error and better tracking performance when point target and group target coexist. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Multi-target tracking using infrared images is receiving more and more attention. There are many state-of-the-art methods, and the deep learning network and low-rank and sparse matrix separation are two kinds of methods with high accuracy. However, the former suffers from heavy training samples, and the latter requires high-dimensional processing, meaning its computing cost is huge. In this work, a united detection and tracking method with matrix separation and PMBM filtering is proposed. In the detection process, a low-rank and sparse matrix separation algorithm with a differentiable form based on a single image is constructed. In the filtering process, the multi-target state is modeled as a PMBM distribution, which is conjugate in the Bayesian framework. The two processes interact mutually in that the detection provides measurements, and the filtering offers prior information for the next detection to improve accuracy. The computational complexity is given by a theoretical analysis, which shows a significant reduction. The numerical analysis, carried out on a practical dataset, verifies an enhancement in the BSF and SCRG metrics and ROC curves. [ABSTRACT FROM AUTHOR]

Abstract Underwater sensor networks hold immense potential for advancing the field of underwater target tracking, yet they encounter significant resource constraints stemming from energy storage and communication methods. In order to balance tracking accuracy and energy consumption, the authors present a distributed bearing‐only target tracking algorithm that can be used in underwater sensor networks with resource constraints. Anchored in the diffusion cubature information filter framework, this algorithm achieves fusion for non‐linear bearing measurements and state estimation. During the incremental update stage, individual nodes leverage the Posterior Cramer‐Rao Lower Bound as a metric for tracking performance. Subsequently, a strategy for selecting neighbouring nodes is introduced, ensuring tracking accuracy while efficiently kerbing energy consumption. In the diffusion update stage, a multi‐threshold event triggering mechanism is employed to partially diffuse the intermediate estimation. Additionally, an adaptive convex combination weight is proposed for cases involving partial diffusion. Through theoretical analysis, the asymptotic unbiasedness and convergence of the algorithm have been proven. Through Monte Carlo simulation experiments, the authors verify that the algorithm is superior to existing algorithms. Furthermore, the algorithm significantly reduces energy consumption in information interaction, minimising tracking accuracy loss.

Abstract The application of the hybrid extended Kalman filter (HEKF), hybrid unscented Kalman filter (HUKF), hybrid particle filter (HPF), and hybrid extended Kalman particle filter (HEKPF) is discussed for hybrid non‐linear filter problems, when prediction equations are continuous‐time and the update equations are discrete‐time, and also the discrete extended Kalman filter (DEKF), discrete unscented Kalman filter (DUKF), discrete particle filter (DPF), and discrete extended Kalman particle filter (DEKPF) for discrete‐time non‐linear filter problems, when prediction equations and update equations are discrete‐time. In order to assess the performance of the filters, the authors consider the non‐linear dynamics for a re‐entry vehicle. The filters are used in two hybrid and discrete states to estimate the position, velocity, and drag parameter associated with the re‐entry vehicle. Theoretical topics concerning estimating the drag parameter of a vehicle in re‐entry phase have been dealt with. Drag parameter estimation is carried out using a combination of hybrid filters and discrete filters as an effective estimator and fixed value, forgetting factor, and Robbins‐Monro stochastic approximation methods as the noise covariance matrix adjuster of the parameter.

Abstract In order to solve the related problems of detection and tracking of shallow marine organisms, this paper designs a YOLO v5 multi‐target detection and tracking algorithm with attention mechanism. When working underwater, the authors usually encounter many difficulties. Different luminosity and complex coral background usually affect the detection of marine organisms. At the same time, the unrestricted movement of marine organisms, the ability to hide behind rocks and algae, and their mutual occlusion while swimming pose additional challenges to this task. Considering the characteristics of shallow marine organisms activity environment, the attention mechanism is added to the feature extraction network of YOLO v5 to reduce redundant information and improve the detection accuracy of shallow marine organism targets in complex environment. The improved algorithm improves the average detection accuracy of marine organisms target detection by 3.2%. Aiming at the problem of shallow marine organisms target tracking, a shallow marine organisms multi‐target tracking algorithm based on improved Deep Simple Online And Realtime Tracking (SORT) is designed. The improved YOLO v5 algorithm is used to replace Faster R‐CNN (Faster Region‐Convolutional Neural Networks) as the detector of DeepSORT tracking algorithm, and the cascade matching strategy is adopted to solve the problem that the target cannot be tracked continuously when it is occluded for a long time. The experimental results show that the shallow marine organisms multi‐target tracking algorithm based on improved DeepSORT reduces the number of id transformation of marine biological target tracking in shallow sea environment, and improves the accuracy of shallow marine organisms multi‐target tracking.

Abstract Accurate positioning of intelligent connected vehicle (ICV) is a key element for the development of cooperative intelligent transportation system. In vehicular networks, lots of state‐related measurements, especially the mutual measurements between ICVs, are shared. It is an advisable strategy to fuse these measurements for a more robust positioning. In this context, an innovative framework, referred to as multisource‐multitarget cooperative positioning (MMCP) is presented. In MMCP, ICVs are local information source, that upload both the states of ICVs estimated by on‐board sensors and the relative vectors between surrounding objects and vehicles to a fusion centre. In the fusion centre, ICVs are selected as the global targets, and the relative vectors are converted into global measurements. Then, the MMCP is modelled into a multi‐target tracking problem with specific targets. This paper proposes a low complexity Gaussian mixture probability hypothesis density (GM‐PHD‐LC) filter to match and fuse the global measurements to further improve the estimation of ICVs. The evaluation results show that our GM‐PHD‐LC can provide 10 Hz positioning services in urban area, and significantly improve the positioning accuracy compared to the standalone global navigation satellite system.

Various mainstream target tracking algorithms based on Siamese networks are gradually becoming a trend in the field of deep learning tracking due to their concurrent advantages of accuracy and speed. Most Siamese network‐based trackers describe the tracking of a target object as a similar matching problem, and these trackers have achieved more advanced performance in several public tests. Most trackers often suffer from tracking drift or performance degradation owing to the non‐updating of the template in the first frame and the target appearance encounters disturbing environments such as occlusion and drastic deformation. Therefore, to address this problem, this paper introduces a template updating mechanism and proposes a refine structure network based on the template updating of Siamese networks as well as the greater similarity of target features in two adjacent frames, which improves the tracking accuracy while limiting the amount of computation using an anchor‐free method in order not to lose the tracking speed, and only needs to be trained by selecting the most suitable pre‐training network, thus greatly reducing the amount of network computation. Meanwhile, in the application of the refine structure, with the aim of making the weight design of the target localisation module more reasonable, we propose a new Refine Head section and analyze and design the update threshold to optimize the overall network. This method is practiced in SiamFC++ algorithm, which firstly designs the template refine module, inputs the image that needs to be improved, and then outputs it to the Refine Head to complete the template update and applies it to the tracking of the subsequent frames, thereby constituting the SiamTRN (Template‐Refine Network). According to the experiments, the improved structure of the method can effectively implement the refine module function and enhance the performance of the tracker on public datasets, such as OTB100, VOT2016, UAV123 and GOT‐10 k. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

This paper investigates region tracking and perimeter surveillance of second-order multiagent systems, where all agents move within a star-shaped set. First, by coordination transformations, the region tracking problem is converted from the star-shaped sets to a circular region. The authors employ communication and collaboration to complete region tracking and perimeter surveillance tasks, and then revert back to the star-shaped set by using inverse transformations. Second, the authors propose a distributed control strategy based on attractive and interaction potential functions, under which all agents can quickly track a given circular region and move around the perimeter. Finally, the authors validate the effectiveness and performance advantages of the proposed method through simulation experiments. [ABSTRACT FROM AUTHOR]

This study proposes an image-based visual servoing (IBVS) method based on a velocity observer for an unmanned aerial vehicle (UAV) for tracking a dynamic target in Global Positioning System (GPS)-denied environments. The proposed method derives the simplified and decoupled image dynamics of underactuated UAVs using a constructed virtual camera and then considers the uncertainties caused by the unpredictable rotations and velocities of the dynamic target. A novel image depth model that extends the IBVS method to track a rotating target with arbitrary orientations is proposed. The depth model ensures image feature accuracy and image trajectory smoothness in rotating target tracking. The relative velocities of the UAV and the dynamic target are estimated using the proposed velocity observer. Thanks to the velocity observer, translational velocity measurements are not required, and the control chatter caused by noise-containing measurements is mitigated. An integral-based filter is proposed to compensate for unpredictable environmental disturbances in order to improve the anti-disturbance ability. The stability of the velocity observer and IBVS controller is analyzed using the Lyapunov method. Comparative simulations and multistage experiments are conducted to illustrate the tracking stability, anti-disturbance ability, and tracking robustness of the proposed method with a dynamic rotating target.

Abstract High precision is a very important index in target tracking. In order to improve the prediction accuracy of target tracking, an optimized Kalman filter approach based on improved Gray Wolf algorithm (IGWO-OKF) is proposed in this paper. Since the convergence speed of traditional Gray Wolf algorithm is slow, meanwhile, the number of gray wolves and the choice of the maximum number of iterations has a great influence on the algorithm, a nonlinear control parameter combination adjustment strategy is proposed. An improved Grey Wolf Optimization algorithm (IGWO) is formed by determining the best combination of adjustment parameters through the fastest iteration speed of the algorithm. The improved Grey Wolf Optimization algorithm (IGWO) is formed, and the process noise covariance matrix and observation noise covariance matrix in Kalman filter are optimized by IGWO. The proposed approach is applied into. The experiment results show that the proposed IGWO-OKF approach has low error, high accuracy and good prediction effect.

A monocular vehicle speed detection method based on improved YOLOX and DeepSORT is proposed for the simple scene of fixed shooting angle without high precision but requiring control cost. For continuous video frames collected from a monocular fixed perspective, the vehicle is first identified by using the YOLOX object detection network improved by ELAN module and the CAENet attention mechanism constructed by CA attention and ECANet. Then, the DeepSORT target tracking algorithm is used to match the recognition results of the object detection network output in the before and after frames to find the same target in different frames. Finally, a coordinate system transformation algorithm is used to convert the position distance of the target moving in different frame images into the actual ground plane distance and divide it by the detection interval time to obtain the vehicle speed. The experimental results show that our improved object detection model can increase mAP by 2% to 4% compared with YOLOX in different versions. Compared with the original model, the target tracking using the improved YOLOX is improved by 4.3% on MOTA. The speed limiting precision of speed detection is 75% in the corresponding speed range in experimental testing site 1 and the mean error of the effective velocity value measured by our speed measurement method is 2.10 km/h in experimental testing site 2, which is better than the mean error of 5.46 km/h obtained by the radar pistol velocimeter. This detection method enables economical and efficient vehicle speed detection in simple scenes. [ABSTRACT FROM AUTHOR]

Real-time target detection plays an important role in campus intelligent surveillance systems. This paper introduces Soft-NMS, GSConv, Triplet Attention, and other advanced technologies to propose a lightweight pedestrian and vehicle detection model named SGST-YOLOv8. In this paper, the improved YOLOv8 model is trained on the self-made dataset, and the tracking algorithm is combined to achieve an accurate and efficient real-time pedestrian and vehicle tracking detection system. The improved model achieved an accuracy of 88.6%, which is 1.2% higher than the baseline model YOLOv8. Additionally, the mAP0.5:0.95 increased by 3.2%. The model parameters and GFLOPS reduced by 5.6% and 7.9%, respectively. In addition, this study also employed the improved YOLOv8 model combined with the bot sort tracking algorithm on the website for actual detection. The results showed that the improved model achieves higher FPS than the baseline YOLOv8 model when detecting the same scenes, with an average increase of 3–5 frames per second. The above results verify the effectiveness of the improved model for real-time target detection in complex environments. [ABSTRACT FROM AUTHOR]

In this study, to solve the low accuracy of multi-space-based sensor joint tracking in the presence of unknown noise characteristics, an adaptive multi-sensor joint tracking algorithm (AMSJTA) is proposed. First, the coordinate transformation from the target object to the optical sensors is considered, and the observation vector-based measurement model is established. Then, the measurement noise characteristics are assumed to be white Gaussian noise, and the measurement covariance matrix is set as a constant. On this premise, the traditional iterative extended Kalman filter is applied to solve this problem. However, in most actual engineering applications, the measurement noise characteristics are unknown. Thus, a forgetting factor is introduced to adaptively estimate the unknown measurement noise characteristics, and the AMSJTA is designed to improve the tracking accuracy. Furthermore, the lower bound of the proposed algorithm is theoretically proved. Finally, numerical simulations are executed to verify the effectiveness and superiority of the proposed AMSJTA. [ABSTRACT FROM AUTHOR]

In this paper, to track maneuvering unmanned surface vehicles (USVs) in scenarios with clutter, we propose a novel method based on the probabilistic data association (PDA) algorithm and Rao-Blackwellized particle filter (RBPF) algorithm, and we further improve the tracking performance by Max-Q criterion-based waveform selection. This work develops a maneuvering target model in the context of clutter, integrating linear and nonlinear states as well as observations with false alarms. In order to jointly tackle the mixed-state tracking problem, the PDA algorithm is integrated into the RBPF framework. This allows it to be used with the complex nonlinear and linear hybrid system and helps to minimize the state dimensions of conventional particle filtering (PF). Additionally, by utilizing Q-learning principles, we provide a Max-Q-based criterion to select the waveform parameters, which guarantees low measurement errors and efficiently handles measurement uncertainties. Our simulation results show that the PDA-RBPF algorithm, which has a more appropriate tracking mechanism, produces results that are more accurate than those of the EKF or PF algorithms alone. Furthermore, the RMSE derived by the Max-Q-based criterion is smaller and more robust than that of other selection methods, as well as yielding a fixed waveform. Our proposed mechanism, which combines the concepts of PDA-RBPF and Max-Q waveform selection, performs well in target tracking tasks and exhibits relatively good performance over some existing ones. [ABSTRACT FROM AUTHOR]