Point Tracking Research Articles

Max Sum Based Data Associations for Tracking Point and Extended Targets

Max Sum Based Data Associations for Tracking Point and Extended Targets

PETC-EM-PMBM Filter for Tracking Point and Extended Targets With Type Conversion

PETC-EM-PMBM Filter for Tracking Point and Extended Targets With Type Conversion

River Ice Regime Recognition Based on Deep Learning: Ice Concentration, Area, and Velocity

The real-time derivation of the concentration, area, and velocity of river surface ice based on camera imagery is essential for predicting the potential risks related to ice blockages in water routes. The key lies in the continuous tracking and velocity measuring of river ice, and reliable ice motion detection is a prerequisite for the dynamic perception of tracking targets. Previous studies did not utilize motion tracking for measuring ice velocity, and particle image velocimetry and feature point matching were used. This study aimed to use deep learning methods to address the challenging problems of deriving the ice concentration, area, and velocity based on camera imagery, and the focus was on measuring the ice velocity and drawing trajectories using the particle video tracking algorithm. We built a dataset named IPC_RI_IDS and collected information during the ice cover break-up process in the Nenjiang River (China). Our suggested approach was divided into four steps: (1) image preprocessing, where the camera image was calibrated to real-world coordinates; (2) determining the ice and water pixels in the camera image using the lightweight semantic segmentation network and then calculating the ice concentration and area; (3) enhancing and optimizing motion detection using the semantic segmentation results; and (4) adapting the particle video tracking algorithm to measure ice velocity using the proposed tracking points generation strategy. Finally, we analyzed the surface ice data in the study area and attempted to predict the stage of the ice break-up process to provide support for the real-time short-term forecasts of ice floods.

Structural Characteristics of the Yushuwan Fault in the Northeastern Ordos Basin: Implications for Basin Tectonics and Hydrocarbon Exploration

The Yushuwan fault is located in the transition zone among the Yimeng uplift, Jinxi fold belt and Shanbei slope in the northeastern Ordos basin and marks the boundary between Palaeozoic and Mesozoic strata. According to the field geological survey and geophysical data, this study shows that the Yushuwan fault is a deep-cut northwest-southeast-oriented strike-slip basement fault. A total of 17 apatite and zircon fission track points show that the basin experienced several stages of uplift at 190 Ma, 150–170 Ma, 110–130 Ma, 60–80 Ma, and 20–40 Ma. The characteristics of the Yushuwan fault indicate that the northeastern part of the basin is not a simple slope but rather a step with a large drop. Therefore, in the area to the southwest of the Yushuwan fault, there should be high natural gas resource potential and good exploration prospects. The contour values of the magnetic anomaly on the southwestern side of the fault are high, and the contours are dense; in contrast, the contour values of the northwest magnetic anomaly are low, and the gradient is gentle. Therefore, the fault represents the eastern boundary of the Yimeng uplift, and restricts the eastward extent of the high magnetic anomaly zone in the Yimeng uplift area.

Cooperative aerial search by an innovative optimized map-sharing algorithm

In this paper, the problem of cooperative search and tracking by multiple flying vehicles is studied. An algorithm is proposed based on optimal planning by minimizing a suitably defined cost function. In order to define the cost function, three maps are proposed: uncertainty map, detection probability map, and emitter map. In the uncertainty map, the geometrical status of the vehicle with respect to the region is considered and its suitability is measured. The detection probability map is defined such that the group of vehicles can detect new emitters that appear in their sensors’ coverage. Finally, the emitter map is a tool to keep tracking the detected emitters with acceptable error while searching the region. The assumption that the vehicles are equipped with only one commonly used radar range indicator sensor makes the proposed algorithms more applicable in the real world for a cost-effective system. The efficiency of the proposed method from the search, detection, and tracking points of view is verified through simulations.

TCM Model for improving track sequence classification in real scenarios with Multi-Feature Fusion and Transformer Block

The shipping industry has experienced rapid growth in recent years, prompting a need for advanced target recognition technology based on marine radar. This paper introduces the Track Classification Model (TCM), a novel approach for classifying track sequences in real scenarios. The TCM utilizes a feature extraction network based on multi-feature fusion, taking radar echo images and motion information of the target as input, to improve classification accuracy. Additionally, the paper also presents a dataset production method that addresses the issue of missing labels, a critical problem in track sequence classification. Through ablation experiments, the paper demonstrates the effectiveness of the design strategy, with the multi-feature fusion network successfully extracting features and achieving superior performance over single feature extraction networks. The results show that increasing the number of input track points and raising the upper limit of the input sequence leads to improved classification accuracy. Finally, in real scenarios, the proposed model outperforms other algorithms, showcasing its high engineering application value.

Obstacle avoidance USV in multi-static obstacle environments based on a deep reinforcement learning approach

Unmanned surface vehicles (USVs) are intelligent platforms for unmanned surface navigation based on artificial intelligence, motion control, environmental awareness, and other professional technologies. Obstacle avoidance is an important part of its autonomous navigation. Although the USV works in the water environment (e.g. monitoring and tracking, search and rescue scenarios), the dynamic and complex operating environment makes the traditional methods not suitable for solving the obstacle avoidance problem of the USV. In this paper, to address the issue of poor convergence of the Twin Delayed Deep Deterministic policy gradient (TD3) algorithm of Deep Reinforcement Learning (DRL) in an unstructured environment and wave current interference, random walk policy is proposed to deposit the pre-exploration policy of the algorithm into the experience pool to accelerate the convergence of the algorithm and thus achieve USV obstacle avoidance, which can achieve collision-free navigation from any start point to a given end point in a dynamic and complex environment without offline trajectory and track point generation. We design a pre-exploration policy for the environment and a virtual simulation environment for training and testing the algorithm and give the reward function and training method. The simulation results show that our proposed algorithm is more manageable to converge than the original algorithm and can perform better in complex environments in terms of obstacle avoidance behavior, reflecting the algorithm’s feasibility and effectiveness.

The integration of traditional lacquerware and modern art design in the context of artificial intelligence

Abstract This paper aims to promote the integration of traditional lacquerware and modern art design. AR technology is used for feature calculation of the appearance contour of traditional lacquerware. In this paper, the BRIEF algorithm is selected as the main algorithm for image feature calculation. The Steer BRIEF algorithm is used for key points, and the image feature points are extracted. The classical optical flow method of CMT is applied to track the appearance contour of traditional lacquerware, and the SSD and NCC are combined with filtering the measurement of tracking points. The results show that 90% of the traditional lacquerware can reflect the cultural connotation of the time, 80% of the traditional lacquerware can reflect the characteristics of the time, 80% of the traditional lacquerware has excellent craftsmanship, and the added value reflected by modern art design is much lower than that of the traditional lacquerware.

Spatial and temporal variation patterns of summer grazing trajectories of Sunit sheep

GPS is an important tool for real-time monitoring of individual livestock. Analysis of the spatial and temporal changes in the grazing trajectory of Sunit sheep provided a scientific basis for the rational use of Inner Mongolia desert grassland resources and optimal breeding of livestock. In this study, GPS collars were used to track Sunit sheep in the Inner Mongolia desert grassland. These data were combined with ground measurement data and spatial remote sensing data to investigate the spatial and temporal variation patterns of sheep grazing tracks. The results showed that the distance travelled by sheep in June was significantly different from that in July and August (p < 0.05). The effective daily foraging time was mainly concentrated in the time ranges of 7:00–10:00 and 15:00–18:00 in June and August, and in the time ranges of 7:00–9:00 and 16:00–19:00 in July, for more active grazing behavior in the morning and evening hours. The degree of nuclear density of foraging track points was significantly different from the edible forage biomass (p < 0.05), with the average daily walking distance negatively correlated with the total grass biomass (R2 = 0.49). Overall, the results of this study confirm that GPS-positioning technology can be applied to study the spatial and temporal variation patterns of sheep and suggest new strategies for more effective grassland management in this region.

A novel global FPPT strategy for PV system under partial shading condition

AbstractFlexible power point tracking (FPPT) is a common and significate photovoltaic control problem under partial shading conditions. Based on CPP and MPP distribution analysis, both constant power point tracking and maximum power point tracking could be mathematically described by a single objective optimization. As one of the recent meta‐heuristic algorithms, which avoid the limitations of conventional scanning methods, the carnivorous plant algorithm (CPA) solves non‐convex optimization problems with fast speed, high accuracy, and simple calculation. However, it exhibits several drawbacks such as inappropriate parameters, over‐searching, and feasible solution ignored issues. Therefore, a global FPPT strategy based on modified CPA (mCPA) is proposed, which includes a search objective integration, efficient non‐convex search space skipping strategy, and adaptive tuning parameters according to sensitivity analysis. By statistical experiments compared with eight popular meta‐heuristic algorithms, the mCPA can correctly converge to the global MPP under various scenarios with the highest accuracy of 99.0%. Meanwhile, the observations of dynamic experiments demonstrate the effectiveness of the proposed strategy in terms of fast time response (0.5–3 s) for global FPPT under various uniform and non‐uniform insolation conditions.

Real-Time Incentive Design Under Unknown Demand Response Curves via a Proportional–Integral Control Frameworks

Implementing voluntary Demand Response (DR) in real-time or close to real-time is technically feasible because of the deployment of smart grid infrastructures such as smart meters, remote control units, and mobile communication devices. However, most cases require estimating/predicting load demand curves and typically operate from an electricity market clearing perspective. In this work, two frameworks of voluntary incentive-based DR to enhance the resilience and reliability of the system are designed, including a single Proportional-Integral controller based real-time DR framework and a multiple PI controllers cooperation based DR framework, which can be operated in real-time without the requirement of estimating or predicting the load demand curves. Under the proposed frameworks, the overall system can converge to the optimal tracking point to improve resilience/reliability via the cooperation of the different DR devices. Additionally, the corresponding incentive payments can be precisely determined. In particular, both frameworks are proven to be stable. In addition, deep reinforcement learning is adopted to enhance the performance of the proposed frameworks. Because of the generality of the proposed frameworks and the simplicity of the PI controllers, our proposed DR frameworks are promising for practical implementation. Finally, numerical studies verify the effectiveness of the proposed frameworks.

Path-following control strategy for gantry virtual track train based on distributed virtual driving model

In this paper, a chained architecture of virtual track train (VTT), gantry virtual track train (G-VTT), was proposed. The distributed virtual driving model (DVD model) for G-VTT was proposed to realise the automatic tracking of paths with arbitrary ommon curves. The core of the DVD model is the cascade modular wheel steering angle (WSA) control algorithm based on the optimal lateral acceleration (OLA) of tracking points. A local tracking objective function based on 2-norm was established to find the OLA in the preview window, thereby the optimal local trajectory was realised. The cascade structure of the algorithm gives the DVD model the advantages of modularity and high scalability, facilitating the cascade control of an n-unit G-VTT. The proposed control strategy was verified by co-simulation of G-VTT dynamics model and the DVD model. Results show that the DVD model can effectively improve the path-following ability and small-curve-passing capacity of the G-VTT with remarkable reduction of the lateral deviation (up to about 99.16%) and turning passageway width (about 59.71%); Besides, the yaw and anti-jackknifing stability of the train are also significantly improved, and the DVD model is well adaptable to speed, curve radius, and payload.

Performance Evaluation of a Combined Transition System in Slab-Ballasted Railway Track Using a Vehicle-Track-Substructure Interaction Model

Abrupt stiffness variations along the railway track may increase the geometrical and mechanical defects of railway lines. The conjunction points of a railway track with concrete and ballast pavements, which are called slab-ballasted track transitions, are one of the main areas where vertical track stiffness changes sharply. Therefore, the potential benefits of a combined transition system along the slab-ballasted transition, made of an approach slab and additional rails, are studied in this paper. For this purpose, a vehicle-track-substructure interaction model, which included three main segments of the railway track (slab track, transition zone, and ballasted track) was programmed based on the finite element method. A test line with the mentioned combined transition system was built to measure the railway track responses through field study. Then, the three-dimensional (3D) numerical model was validated using the results obtained from the experimental tests. Afterwards, a number of parametric studies were performed to analyze the dynamic responses of the combined transition zone. The results indicated that this type of transition system promotes a smoother stiffness transition between the slab track segment and the ballasted track segment by making the transition in three gradual steps. The track displacements in the analyzed case-study gradually increased by about 22%, 28%, and 34% along the combined transition zone in the junction points of the slab and ballasted tracks.

Automatic horizon tracking algorithm with curvature constraint

Seismic horizon tracing is a key step in seismic data interpretation. At present, it mainly relies on manual interpretation to mark the layers within the region. The deficiency of manual interpretation lies in its low precision and efficiency, and it relies heavily on the experience of the interpreter. Aiming at the above problems, the author proposes an automatic horizon tracking algorithm with curvature constraint. The algorithm firstly determines the initial seed points of horizon tracking based on logging data, and then generates all seed points by tracing the direction of crossline. According to the seed point, track the horizon by the direction of the inline. The curvature of each horizon point is calculated in the direction of the crossline according to the tracked results. For the layer point that do not meet the ruling curvature threshold, they are traced again in the direction of the crossline, and finally the corrected tracking results are obtained. Through the test of actual data, this method has achieved good results.

Autonomous Asteroid Characterization Through Nanosatellite Swarming

This paper first defines a class of estimation problem called simultaneous navigation and characterization (SNAC), which is a superset of simultaneous localization and mapping (SLAM). A SNAC framework is then developed for the Autonomous Nanosatellite Swarming (ANS) mission concept to autonomously navigate about and characterize an asteroid including the asteroid gravity field, rotational motion, and 3D shape. The ANS SNAC framework consists of three modules: 1) multi-agent optical landmark tracking and 3D point reconstruction using stereovision, 2) state estimation through a computationally efficient and robust unscented Kalman filter, and 3) reconstruction of an asteroid spherical harmonic shape model by leveraging a priori knowledge of the shape properties of celestial bodies. Despite significant interest in asteroids, there are several limitations to current asteroid rendezvous mission concepts. First, completed missions heavily rely on human oversight and Earth-based resources. Second, proposed solutions to increase autonomy make oversimplifying assumptions about state knowledge and information processing. Third, asteroid mission concepts often opt for high size, weight, power, and cost (SWaP-C) avionics for environmental measurements. Finally, such missions often utilize a single spacecraft, neglecting the benefits of distributed space systems. In contrast, ANS is composed of multiple autonomous nanosatellites equipped with low SWaP-C avionics. The ANS SNAC framework is validated through a numerical simulation of three spacecraft orbiting asteroid 433 Eros. The simulation results demonstrate that the proposed architecture provides autonomous and accurate SNAC in a safe manner without an a priori shape model and using only low SWaP-C avionics.

IDENTIFICATION OF THE MOLUCCAN MEGAPODE (Eulipoa wallacei) NATURAL HABITAT IN HARUKU ISLAND, INDONESIA AND ITS VEGETATION COMPOSITION

The characteristics of island vegetation greatly influence the activities of endemic birds in island areas, such as the Moluccan endemic megapodes (Eulipoa wallacei) on Haruku Island. Therefore, it is essential to identify the specific location of the habitat utilized by individual birds for their daily activities on Haruku Island and to analyze the composition of the vegetation and the variety of plant species. Identification of bird habitat locations using radio-tracking on four newly hatched chicks and four adult birds. A total of 330 individual tracking points were recorded during the study period. The vegetation sample used a total of 420 plots for seedlings, saplings, poles, and trees which were then analyzed for importance value index (IVI), diversity, evenness, and similarity. We found that the Tanjung Maleo forest was their nesting habitat, while the Marunimei and Lalean forests were their daily habitats. A total of 91 plant species and 60 plant families were discovered with the vegetation diversity value of the three habitats was moderate (H’mean = 3.07) and tended to be dominated by air plant (Kalanchoe pinnata), sword fern (Nephrolepsis exalta), cogongrass (Imperata cylindrica), coco-grass (Cyperus rotundus), Indian camphorweed (Pluchea indica), and lanzone (Lansium domesticum) (Emean = 0.88), and have a relatively low level of species similarity between habitats (SImean = 38.30%). We found that the daily habitat of the Moluccan megapode on Haruku Island was around their nesting sites and has a complex structure because it was composed four vegetation strata. Therefore, for conservation purposes, habitat management must prioritize preserving forest habitats around the bird nesting sites.

Driving and Energy Profiles of Urban Bus Routes Predicted for Operation with Battery Electric Buses

Battery electric buses are used for operation on urban bus routes. The main disadvantage of battery electric buses is their limited range that depends on energy consumption. This paper presents a new approach to the estimation of energy consumption on urban bus routes based on driving and energy profiles. The energy consumption results from the travel parameters along the bus route. The travel parameters are described by driving profiles. The determination of driving profiles is based on GPS location data recorded by a receiver on a bus. Location data are recorded at consecutive track points at a constant frequency. For each track point, the distance to the preceding track point is determined using the location data, and then the speed and acceleration are calculated. The analyzed bus route is divided into sections. For each section, travel parameters consisting of travel time, speed parameters, and acceleration parameters are determined. Using travel parameters, the energy consumption is estimated for individual sections and the entire bus route. The estimated energy consumption is described by energy profiles. Experimental results have been obtained for the selected urban bus route under various traffic conditions. For the assumed model of energy consumption, the energy consumed on the entire bus route is 1.8 KWh/km at off-peak hours and 2.1 KWh/km at peak hours. The driving and energy profiles describe the urban bus routes well and allow evaluation of the suitability of the bus route for operation with battery electric buses.

Intelligent marine area supervision based on AIS and radar fusion

A weighted track fusion algorithm is proposed to address the complexity of conventional sea monitoring data and the lack of effective and convenient monitoring methods. The new algorithm uses local information entropy and fuses data from the automatic identification system (AIS) and X-band radar. The new model employs ship monitoring data to detect five types of abnormal ship behavior: speed, course, position, ship spacing, and time abnormalities. The method weights various factors using a weight matrix built up from a distance difference matrix between different track points and calculations of the distance information entropy and residual degree using information entropy theory. We tested the proposed weighted track fusion algorithm the fusion accuracy using actual data for 2813 ships, AIS, and radar track points based on local information entropy. The resulting correlation accuracy was 95.54% for 2716 ship track points and a correlation accuracy of 90.72% for 97 ship tracks. The results indicate that the proposed algorithm is suitable for fusing multiple tracks and is more robust than traditional fusion methods.

Accumulated Cyclone Energy-Based Tropical Cyclone Return Periods in Florida

This article introduces an accumulated cyclone energy (ACE) approach for estimating the return period of tropical cyclone (TC) wind risk in Florida. As opposed to calculating return periods directly from maximum sustained wind speed, the ACE-based approach also describes the duration of the strong winds, giving an additional dimension to the assessment of TC wind risks. Because Florida is a peninsula, TCs can move across the state within six hours of landfall, causing an underestimation of the inland wind footprint if only the six-hour reanalysis track points are employed as an input data source. This study uses four different scenarios and an inland exponential decay function to interpolate the wind speed between the six-hour reanalysis track points to feed the ACE-based return period calculation based on a 121-year record from 1900 to 2020. South Florida has the shortest return period (five to ten years) of TCs with an ACE equivalent to one hour of hurricane intensity (≥ 64 kt; 1 kt ∼ 0.51 m s−1) caused by intense historical hurricane strikes, and Polk County in inland central Florida has an equal return period due to frequent and long-duration TC occurrences, acting as an intersection for landfalling TCs in the Florida peninsula.

A Fusion Designed Improved Elastic Potential Field Method in AUV Underwater Target Interception

In this article, the single autonomous underwater vehicle (AUV) interception problem is analyzed and studied, and a new improved elastic potential field (EPF)-particle swarm-sliding window fusion strategy is proposed to achieve fast interception of underwater moving targets. First, the Sliding Window Fitting Prediction Method is used to fit and predict the trajectory of the target object. To improve the interception efficiency, the Elastic Predictive Interception Method is used to predict the position of the target object at the next moment, and the tracking point is replaced by the prediction point to intercept moving targets. Second, an expansion potential field method is proposed to replace the gradient potential field in the artificial potential field (APF), and the relatively appropriate influence range of the obstacle is found through the particle swarm optimization (PSO) algorithm. Then, the AUV converges gradually from the starting point to the target point through the stepping interception scheme. This method can make up for some shortcomings of the APF method and find a better interception path while making a rapid path planning decision. Simulation results show the interception effect of improved EPF under elastic prediction conditions, and the effectiveness of the proposed method is verified by a comparative analysis.