Multi-objective Tracking Research Articles

Multi-Objective Path Tracking Control for Car-Like Vehicles With Differentially Bounded n-Smooth Output

Multi-Objective Path Tracking Control for Car-Like Vehicles With Differentially Bounded <i>n</i>-Smooth Output

High-precision tracking and positioning for monitoring Holstein cattle.

Enhanced animal welfare has emerged as a pivotal element in contemporary precision animal husbandry, with bovine monitoring constituting a significant facet of precision agriculture. The evolution of intelligent agriculture in recent years has significantly facilitated the integration of drone flight monitoring tools and innovative systems, leveraging deep learning to interpret bovine behavior. Smart drones, outfitted with monitoring systems, have evolved into viable solutions for wildlife protection and monitoring as well as animal husbandry. Nevertheless, challenges arise under actual and multifaceted ranch conditions, where scale alterations, unpredictable movements, and occlusions invariably influence the accurate tracking of unmanned aerial vehicles (UAVs). To address these challenges, this manuscript proposes a tracking algorithm based on deep learning, adhering to the Joint Detection Tracking (JDT) paradigm established by the CenterTrack algorithm. This algorithm is designed to satisfy the requirements of multi-objective tracking in intricate practical scenarios. In comparison with several preeminent tracking algorithms, the proposed Multi-Object Tracking (MOT) algorithm demonstrates superior performance in Multiple Object Tracking Accuracy (MOTA), Multiple Object Tracking Precision (MOTP), and IDF1. Additionally, it exhibits enhanced efficiency in managing Identity Switches (ID), False Positives (FP), and False Negatives (FN). This algorithm proficiently mitigates the inherent challenges of MOT in complex, livestock-dense scenarios.

Maximum Power Point Tracking control of a variable speed wind turbine via a T-S fuzzy model-based approach

This paper proposes a multi-objective H2/H ∞ maximum power tracking control of a variable speed wind turbine to minimize the H2 tracking error and ensure the H ∞ model reference-tracking performance, simultaneously. The optimal condition is obtained via a boost converter use, which adapts the load impedance to the wind turbine generator. Thus, based on the fuzzy T-S model, a multi-objective Maximum Power Point Tracking (MPPT) controller is developed, ensuring maximum power transfer, despite wind speed variation and system uncertainty. To specify the optimal trajectory to follow, a TS reference model is proposed taking as input the optimal rectified DC current. The conditions of stability and stabilization are expressed in terms of linear matrix inequality (LMI) for uncertain and disturbed T-S models leading to determining the controller gains. Finally, an example of MPP tracking applied to a Wind Energy Conversion System (WECS) illustrates the effectiveness of the proposed fuzzy control law.

Efficient LiDAR-Trajectory Affinity Model for Autonomous Vehicle Orchestration

Computation and memory resource management strategies are the backbone of continuous object tracking in intelligent vehicle orchestration. Multi-object tracking generates enormous measurements of targets and extended object positions using light detection and ranging (Lidar) sensors. Designing an adequate object-tracking system is a global challenge because of dynamic object detection and data association uncertainties during scene understanding. In this regard, we develop an intelligent multi-objective tracking (IMOT) system with a novel measurement model, called the box data association inflate (BDAI) model, to assess each target’s object state and trajectory without noise by using the Bayesian approach. The box object filter method filters ambiguous detection responses during data association. The theoretical proof of the box object filter is derived based on binomial expansion. Prognosticating a lower-dimension object than the original point object reduces the computational complexity of vehicle orchestration. Two datasets (NuScenes dataset and our lab dataset) are considered during the simulations, and our approach measures the kinematic states adequately with reduced computation complexity compared to state-of-the-art methods. The simulation outcomes show that our proposed method is effective and works well to detect and track objects. The NuScenes dataset contains 28130 samples for training, 6019 examples for validation and 6008 samples for testing. IMOT achieves 58.09% tracking accuracy and 71% mAP with 5 ms pre-processing time. The Jetson Xavier NX consumes 49.63% GPU and 9.37% average power and exhibits 25.32 ms latency compared to other approaches. Our system trains a single pair frame in 169.71 ms with affinity estimation time of 12.19 ms, track association time of 0.19 ms and mATE of 0.245 compared to state-of-the-art approaches

Multi-objective pedestrian tracking method based on YOLOv8 and improved DeepSORT.

A multi-objective pedestrian tracking method based on you only look once-v8 (YOLOv8) and the improved simple online and real time tracking with a deep association metric (DeepSORT) was proposed with the purpose of coping with the issues of local occlusion and ID dynamic transformation that frequently arise when tracking target pedestrians in real complex traffic scenarios. To begin with, in order to enhance the feature extraction network's capacity to learn target feature information in busy traffic situations, the detector implemented the YOLOv8 method with a high level of small-scale feature expression. In addition, the omni-scale network (OSNet) feature extraction network was then put on top of DeepSORT in order to accomplish real-time synchronized target tracking. This increases the effectiveness of picture edge recognition by dynamically fusing the collected feature information at various scales. Furthermore, a new adaptive forgetting smoothing Kalman filtering algorithm (FSA) was created to adapt to the nonlinear condition of the pedestrian trajectory in the traffic scene in order to address the issue of poor prediction attributed to the linear state equation of Kalman filtering once more. Afterward, the original intersection over union (IOU) association matching algorithm of DeepSORT was replaced by the complete-intersection over union (CIOU) association matching algorithm to fundamentally reduce the target pedestrians' omission and misdetection situation and to improve the accuracy of data matching. Eventually, the generalized trajectory feature extractor model (GFModel) was developed to tightly merge the local and global information through the average pooling operation in order to get precise tracking results and further decrease the impact of numerous disturbances on target tracking. The fusion algorithm of YOLOv8 and improved DeepSORT method based on OSNet, FSA and GFModel was named YOFGD. According to the experimental findings, YOFGD's ultimate accuracy can reach 77.9% and its speed can reach 55.8 frames per second (FPS), which is more than enough to fulfill the demands of real-world scenarios.

Research on the Recognition and Tracking of Group-Housed Pigs' Posture Based on Edge Computing.

The existing algorithms for identifying and tracking pigs in barns generally have a large number of parameters, relatively complex networks and a high demand for computational resources, which are not suitable for deployment in embedded-edge nodes on farms. A lightweight multi-objective identification and tracking algorithm based on improved YOLOv5s and DeepSort was developed for group-housed pigs in this study. The identification algorithm was optimized by: (i) using a dilated convolution in the YOLOv5s backbone network to reduce the number of model parameters and computational power requirements; (ii) adding a coordinate attention mechanism to improve the model precision; and (iii) pruning the BN layers to reduce the computational requirements. The optimized identification model was combined with DeepSort to form the final Tracking by Detecting algorithm and ported to a Jetson AGX Xavier edge computing node. The algorithm reduced the model size by 65.3% compared to the original YOLOv5s. The algorithm achieved a recognition precision of 96.6%; a tracking time of 46 ms; and a tracking frame rate of 21.7 FPS, and the precision of the tracking statistics was greater than 90%. The model size and performance met the requirements for stable real-time operation in embedded-edge computing nodes for monitoring group-housed pigs.

Retracted: The Key Technologies of Marine Multiobjective Ship Monitoring and Tracking Based on Computer Vision

Retracted: The Key Technologies of Marine Multiobjective Ship Monitoring and Tracking Based on Computer Vision

Rotating box multi-objective visual tracking algorithm for vibration displacement measurement of large-span flexible bridges

Visual displacement measurement methods for flexible structural bodies like large-span bridges has gained wide popularity in recent years, but practical applications still have some limitations. For instance, when acquiring images of large-span flexible bridges at a distance, the slight angular tilt of the detection target due to irregular vibrations can cause extremely serious misfit errors in the displacement curves returned by the vision measurement algorithm. To improve the reliability of vibration displacement measurement of flexible structural bodies, this paper takes the bridge subjected to external excitation in the acquired image sequence as the object of vibration displacement measurement and uses a designed high-precision displacement measurement algorithm for a single-stage rotating target tracking anchor-free box to track the vibration displacement of the target in the flexible structural body. We first extract multi-scale feature information of bridge model image sequences using the improved YOLOv5-s backbone network and combine the Transformer self-attention mechanism with PANet to perform a top-down and bottom-up bi-directional fusion of target feature maps at three different scales to achieve semantic feature fusion of shallow and deep information. Second, the improved Efficient Decoupled Head performs the detection of rotating target centroid offset and bounding box size. Finally, the detected results are passed into the multi-objective tracking algorithm ByteTrack, which strengthens the spatio-temporal correlation between frames and obtains a better-fitting vibration displacement curve. The validation and comparison of traditional visual measurement methods and deep learning measurement methods on cable-stayed bridge models, small arch bridges, and large span bridges show that the vibration displacement trajectories regressed by the algorithm in this paper have the best fit with the actual vibration displacement trajectories, which also verifies that the algorithm in this paper has good potential for engineering applications and implementation space in the field of condition monitoring of flexible structural bodies.

Fruit Detection and Counting in Apple Orchards Based on Improved Yolov7 and Multi-Object Tracking Methods.

With the increasing popularity of online fruit sales, accurately predicting fruit yields has become crucial for optimizing logistics and storage strategies. However, existing manual vision-based systems and sensor methods have proven inadequate for solving the complex problem of fruit yield counting, as they struggle with issues such as crop overlap and variable lighting conditions. Recently CNN-based object detection models have emerged as a promising solution in the field of computer vision, but their effectiveness is limited in agricultural scenarios due to challenges such as occlusion and dissimilarity among the same fruits. To address this issue, we propose a novel variant model that combines the self-attentive mechanism of Vision Transform, a non-CNN network architecture, with Yolov7, a state-of-the-art object detection model. Our model utilizes two attention mechanisms, CBAM and CA, and is trained and tested on a dataset of apple images. In order to enable fruit counting across video frames in complex environments, we incorporate two multi-objective tracking methods based on Kalman filtering and motion trajectory prediction, namely SORT, and Cascade-SORT. Our results show that the Yolov7-CA model achieved a 91.3% mAP and 0.85 F1 score, representing a 4% improvement in mAP and 0.02 improvement in F1 score compared to using Yolov7 alone. Furthermore, three multi-object tracking methods demonstrated a significant improvement in MAE for inter-frame counting across all three test videos, with an 0.642 improvement over using yolov7 alone achieved using our multi-object tracking method. These findings suggest that our proposed model has the potential to improve fruit yield assessment methods and could have implications for decision-making in the fruit industry.

Multi-objective tracking for smart substation onsite surveillance based on YOLO Approach and AKCF

The onsite surveillance plays an important role in the smart substation since the smart substation is unattended. All the sites and operation staff should be supervised throughout the process since a series of risks exist on the working sites. KCF (Kernel Correlation Filter) is an effective method to track a moving object for safety surveillance. However, the occlusion and shape changes worsen the performance of KCF, especially on the occasion of multi-objective detection. This paper proposes a comprehensive method for improving the precision and robustness of detection. Firstly, all the moving objects are detected by the YOLO method. In the tracking part, an AKCF (Augmented Kernel Correlation Filter) is proposed for the heavily occluded object, and the Kalman Filter (KF) serves as a supplementary output. Moreover, in the target association section, based on priority matching and rematching based on motion estimation, a two-stage target association method is proposed. Test outcomes indicate that the proposed algorithm is accurate and robust for tracking workers’ trajectories and conducting surveillance.

A Minimal Drift MPPT Technique for Solar Grid-Tied Multilevel Converter by Multiobjective Swarm

A new multi-objective minimal-drift maximum power point tracking (MOMD-MPPT) technique is introduced to harness maximum power from single photovoltaic (PV) array fed multilevel converter (MLC). A drift in voltage arises with conventional MPPT techniques, which is minimized in this work with a new multi-objective solution. A new swarm optimization algorithm (NSOA) is used for MPPT, which combines the concept of swarm intelligence and pressure gradient force. It provides a minimal drift phenomenon for the solar MLC. Acceleration factor of the swarm particles in NSOA relies on pressure difference and distance. It leads to smoother convergence towards the operating point without trapping in the local minima. The presented algorithm is compared with well-known MPPT algorithms. Simulated results analyze the performance of MOMD-MPPT considering upper and lower voltage drift for PV fed MLC. Later, this algorithm is experimentally validated for a single PV array fed grid-tied multilevel converter. Recorded results show that the algorithm has minimal drift and improves the system performance in dynamic solar conditions.

Research on the Method of Counting Wheat Ears via Video Based on Improved YOLOv7 and DeepSort.

The number of wheat ears in a field is an important parameter for accurately estimating wheat yield. In a large field, however, it is hard to conduct an automated and accurate counting of wheat ears because of their density and mutual overlay. Unlike the majority of the studies conducted on deep learning-based methods that usually count wheat ears via a collection of static images, this paper proposes a counting method based directly on a UAV video multi-objective tracking method and better counting efficiency results. Firstly, we optimized the YOLOv7 model because the basis of the multi-target tracking algorithm is target detection. Simultaneously, the omni-dimensional dynamic convolution (ODConv) design was applied to the network structure to significantly improve the feature-extraction capability of the model, strengthen the interaction between dimensions, and improve the performance of the detection model. Furthermore, the global context network (GCNet) and coordinate attention (CA) mechanisms were adopted in the backbone network to implement the effective utilization of wheat features. Secondly, this study improved the DeepSort multi-objective tracking algorithm by replacing the DeepSort feature extractor with a modified ResNet network structure to achieve a better extraction of wheat-ear-feature information, and the constructed dataset was then trained for the re-identification of wheat ears. Finally, the improved DeepSort algorithm was used to calculate the number of different IDs that appear in the video, and an improved method based on YOLOv7 and DeepSort algorithms was then created to calculate the number of wheat ears in large fields. The results show that the mean average precision (mAP) of the improved YOLOv7 detection model is 2.5% higher than that of the original YOLOv7 model, reaching 96.2%. The multiple-object tracking accuracy (MOTA) of the improved YOLOv7-DeepSort model reached 75.4%. By verifying the number of wheat ears captured by the UAV method, it can be determined that the average value of an L1 loss is 4.2 and the accuracy rate is between 95 and 98%; thus, detection and tracking methods can be effectively performed, and the efficient counting of wheat ears can be achieved according to the ID value in the video.

Multi-Object Multi-Camera Tracking Based on Deep Learning for Intelligent Transportation: A Review.

Multi-Objective Multi-Camera Tracking (MOMCT) is aimed at locating and identifying multiple objects from video captured by multiple cameras. With the advancement of technology in recent years, it has received a lot of attention from researchers in applications such as intelligent transportation, public safety and self-driving driving technology. As a result, a large number of excellent research results have emerged in the field of MOMCT. To facilitate the rapid development of intelligent transportation, researchers need to keep abreast of the latest research and current challenges in related field. Therefore, this paper provide a comprehensive review of multi-object multi-camera tracking based on deep learning for intelligent transportation. Specifically, we first introduce the main object detectors for MOMCT in detail. Secondly, we give an in-depth analysis of deep learning based MOMCT and evaluate advanced methods through visualisation. Thirdly, we summarize the popular benchmark data sets and metrics to provide quantitative and comprehensive comparisons. Finally, we point out the challenges faced by MOMCT in intelligent transportation and present practical suggestions for the future direction.

Traffic load simulation on bridges based on improved non-contact machine vision technique and multi-source information fusion

This study presented a novel traffic load simulation method. Specifically, an improved You Only Look Once (YOLO) detector based on the k-means++ clustering algorithm is implemented to identify vehicle types, and the multi-objective tracking algorithm is used to obtain the spatial location and velocity information of vehicles. Based on the results of detection and tracking, multi-source information fusion techniques are applied to build a vehicle database. Meanwhile, a Monte Carlo-Intelligent Driving Model can be developed for traffic load simulation based on the vehicle database. The applicability and effectiveness of the method are verified by the suspension bridge field test. The results show that the identification accuracy of vehicle type and vehicle number is about 88.28% and 74.09%, respectively. Meanwhile, the vehicle speed error is less than 6.5%. The method can be used to provide a reasonable traffic load model for large-span bridges without the aid of a deck-embedded weigh-in-motion system.

Sorting recognition of taproots and stem bases of Panax notoginseng using multi-objective visual tracking algorithm

For traditional Chinese medicine Panax notoginseng, it is necessary to manually sort or mechanically separate taproots and stem bases before pharmaceutical production. However, the taproot and the stem base are very similar in morphological structure and surface texture, which makes it difficult to be effectively distinguished on the sorting conveyor belt with similar color. Aiming at this problem, this paper proposed a sorting recognition algorithm of taproots and stem bases of Panax notoginseng based on multi-object visual detection and real-time tracking: The sorting of Panax notoginseng under the background of conveyor belt requires that at least one of the taproot or the stem base can be detected. Therefore, based on the detection algorithm, we have connected a multi-object visual tracking algorithm in series. Through the tracking algorithm, we can aggregate the characteristics of the same target from different angles in different time domains, and expand the detection at time points to the detection in continuous time domain, to strengthen the accuracy of sorting recognition. The experimental results on the actual photographed Panax notoginseng dataset in the test site show that the sorting recognition algorithm of taproots and stem bases based on multi-object tracking can achieve the optimal average MOTA of 78.06% at an average speed of 34.3FPS. The method can detect and identify the stem base in the scene of sorting conveyor belt, which is obviously better than other state-of-the-art algorithms, and can provide accurate detection data for industrial intelligent sorting actuator.

The Key Technologies of Marine Multiobjective Ship Monitoring and Tracking Based on Computer Vision

In recent years, one of the key research contents of computer vision is to realize the online monitoring and information tracking of unknown targets by sea ships. For multitarget ships at sea, the most important thing is the information tracking direction. It is very appropriate to apply this computer vision technology to ship monitoring at sea. This paper uses the ship target detection algorithm (STDA) to study the tracking and detection of sea multitarget ships based on computer vision to be applied in practice and improve the protection and safety of sea navigation. Based on the background of ocean intelligent monitoring, the image processing algorithm of key target detection and tracking in the ship detection and tracking system is studied, and the ocean monitoring video image is obtained by installing the detection and tracking effect of the shipborne camera verification system. The ship object detection algorithm (STDA) of the sea antenna is compared with the traditional target detection algorithm. Experimental results show that the proposed algorithm can effectively eliminate the noise interference caused by the waves and the sky, with strong accuracy and real-time performance. The research results of this paper can effectively compensate for the shortcomings of the traditional TLD multitarget ship tracking algorithm and make its speed and real-time performance greatly meet the requirements of ship monitoring. At the same time, it improves the marine monitoring capability to provide reliable technical support for the development of intelligent ships.

Multiobjective Trajectory Tracking of a Flexible Tool During Robotic Percutaneous Nephrolithotomy

Percutaneous Nephrolithotomy (PCNL) is the leading intervention for removing large or irregularly shaped kidney stones. It involves gaining access to the kidney through a small incision in the patient's back, through which a nephroscope is steered towards the stones. Despite decades of clinical prevalence, PCNL remains a complex procedure to learn and perform, sometimes requiring several attempts to gain kidney access, leading to a variety of complications. This letter proposes to use robotic assistance to steer a flexible nephroscope during PCNL to concurrently improve accuracy and reduce the risk of tissue damage. The nephroscope is modelled as a cantilever beam fixed to the robot's end-effector. Under the assumption that an optimal tooltip path exists, Non-dominated Sorting Genetic Algorithm-II is implemented to determine the end-effector position and orientation so that the tooltip follows the path while minimizing four objective functions, i.e., tissue compression, variations in the tool's strain energy, changes in end-effector position, and tooltip error. Data collected through experiments performed on ex-vivo porcine tissue show that the path tracking error was on average 2.03 mm. The results confirm the accuracy of the model in 2 dimensions and suggest that the multiobjective optimizer returned adequate solutions that minimized 4 different cost functions, altogether allowing the robot to effectively follow the predefined path.

A Multi-objective Tracking Task Assignment Algorithm Based on Game Theory

Aiming at the relationship between competition and cooperation among sensors in multi-target tracking task allocation, this paper proposes a game theory-based method to allocate sensor resources for multi-target tracking tasks. The dissertation first establishes a target tracking model and designs a game theory payment function based on the model. Then a multi-sensor multi-target tracking task allocation game model is designed. Finally, a multi-target tracking task allocation algorithm based on game theory is given. Compared with other allocation algorithms, the average tracking error of the proposed allocation algorithm is reduced from 68.5630m to 19.7601m through experiments.

Iterative Learning Tracking for Multisensor Systems: A Weighted Optimization Approach.

Multisensor systems are widely applied to realize the comprehensive monitoring and control as they feature multiple individual sensors/outputs. In such systems, different sensors can receive different types of operation signals, such as pressure, temperature, and volume. The desired references for different sensors may conflict in that an input signal that can precisely track all references simultaneously does not exist yet. This gap has motivated us to consider the incompatible multiobjective tracking problem for multisensor systems with random process disturbances and measurement noises. Our primary approach is to solve the problem as a weighted optimization problem using iterative learning control (ILC). First, the best achievable trajectory based on multiple references, as well as the weighted optimal tracking index, is carefully defined and then the ILC algorithms with both fixed and decreasing steps are proposed to generate the input sequence. The output driven by the proposed algorithms has been strictly proven to converge to the best achievable trajectory in both the mean square and almost-sure senses. Extensions to a networked implementation, in which the networks between the sensors and the learning controller suffer random data dropouts, are also detailed. Illustrative simulations are provided to verify the theoretical results.

Optimization of multi-task nodes in wireless sensor networks based on discrete particle swarm algorithm

Aiming at the competition conflict problem of task allocation of sensor node in wireless sensor network multi-target tracking, a discrete particle swarm optimization tracking task allocation optimization algorithm based on nearest neighbor is proposed. By constructing the mathematical model and objective function of the multi-objective multi-sensor node alliance cooperative tracking task allocation problem, the nearest neighbor method is used to initialize the particle group node task allocation, the objective function is used as the fitness function to guide the particle flight, and the optimal node allocation can be quickly realized. Experiments show that in the case of sparse node coverage, the particle swarm optimization node task allocation method has greatly reduced energy consumption compared with the nearest neighbor method, and can effectively solve the problem of multi-target tracking node task allocation conflict and multiple monitoring alliances on sensor resources the problem of increased system energy consumption during competition conflicts. Discrete particle swarm optimization has superiority for wireless sensor network multi-target tracking in actual environment.