Efficient Target Tracking Research Articles

Information-Theoretic Bayesian Inference for Multi-Agent Localization and Tracking of an Radio Frequency Target With Unknown Waveform

Abstract Information-theoretic motion planning and machine learning through Bayesian inference are exploited to localize and track a dynamic radio frequency (RF) emitter with unknown waveform (uncooperative target). A target-state estimator handles non-Gaussian distributions, while mutual information is utilized to coordinate the motion control of a network of mobile sensors (agents) to minimize measurement uncertainty. The mutual information is computed for pairs of sensors through a four-permutation-with-replacement process. The information surfaces are combined to create a composite map, which is then used by agents to plan their motion for more efficient and effective target estimation and tracking. Simulations and physical experiments involving micro-aerial vehicles with time difference of arrival (TDOA) measurements are performed to evaluate the performance of the algorithm. Results show that when two or three agents are used, the algorithm outperforms state-of-the-art methods. Results also show that for four or more agents, the performance is as competitive as an idealized static sensor network.

Dynamic Merging for Optimal Onboard Resource Utilization: Innovating Mission Queue Constructing Method in Multi-Satellite Spatial Information Networks

The purpose of constructing onboard observation mission queues is to improve the execution efficiency of onboard tasks and reduce energy consumption, representing a significant challenge in achieving efficient global military reconnaissance and target tracking. Existing research often focuses on the aspect of task scheduling, aiming at optimizing the efficiency of single-task execution, while neglecting the complex dependencies that might exist between multiple tasks and payloads. Moreover, traditional task scheduling schemes are no longer suitable for large-scale tasks. To effectively reduce the number of tasks within the network, we introduce a network aggregation graph model based on multiple satellites and tasks, and propose a task aggregation priority dynamic calculation algorithm based on graph computations. Subsequently, we present a dynamic merging-based method for multi-satellite, multi-task aggregation, a novel approach for constructing onboard mission queues that can dynamically optimize the task queue according to real-time task demands and resource status. Simulation experiments demonstrate that, compared to baseline algorithms, our proposed task aggregation method significantly reduces the task size by approximately 25% and effectively increases the utilization rate of onboard resources.

A physics-informed deep learning liquid crystal camera with data-driven diffractive guidance

Whether in the realms of computer vision, robotics, or environmental monitoring, the ability to monitor and follow specific targets amidst intricate surroundings is essential for numerous applications. However, achieving rapid and efficient target tracking remains a challenge. Here we propose an optical implementation for rapid tracking with negligible digital post-processing, leveraging an all-optical information processing. This work combines a diffractive-based optical nerual network with a layered liquid crystal electrical addressing architecture, synergizing the parallel processing capabilities inherent in light propagation with liquid crystal dynamic adaptation mechanism. Through a one-time effort training, the trained network enable accurate prediction of the desired arrangement of liquid crystal molecules as confirmed through numerical blind testing. Then we establish an experimental camera architecture that synergistically combines an electrically-tuned functioned liquid crystal layer with materialized optical neural network. With integrating the architecture into optical imaging path of a detector plane, this optical computing camera offers a data-driven diffractive guidance, enabling the identification of target within complex backgrounds, highlighting its high-level vision task implementation and problem-solving capabilities.

Detection and Tracking of Small Targets in Remote Sensing Images

In the context of remote sensing imagery, the accurate detection and tracking of small targets pose significant challenges. This study delves into the intricate task of identifying and monitoring these minute targets within such images. To address this, we embark on a comprehensive investigation of existing methodologies, with the intention to not only understand their intricacies but also to replicate their results. In addition, our project takes a step further by introducing a visually intuitive interface. This interface serves as a valuable tool, enhancing the usability of our work by providing a platform for efficient small target detection and tracking. Through this combined effort of research, replication, and innovation, our study aims to contribute to the advancement of target detection and tracking in remote sensing images.

Energy Efficient Target Tracking in WSN : An Adaptive Approach

Energy Efficient Target Tracking in WSN : An Adaptive Approach

Combined Fuzzy-PID Controller of an Inertial Stabilized Platform

An Inertially Stabilized Platform (ISP) is used when certain sensors are meant to be stable around a required orientation regardless of any movements of the carrier platform. ISPs are essential for vision-guided flying vehicles to stabilize the equipped seeker attached to the guided vehicle body for efficient target tracking and guidance. This work aims to design a suitable and robust controller for an ISP that can mitigate the disturbances and noise expected when attached to a guided vehicle seeker system. The ISP system is modeled, designed, and implemented. To overcome system uncertainties, external disturbances, and coupling, an efficient controller is to be designed to meet stability and performance requirements. In this research, a decoupled dynamic modelling of a two-axis ISP while accounting for system uncertainties is introduced. In addition to that, a combined fuzzy-PID controller is designed. To evaluate the proposed system's performance, a series of experiments based on two axes and transformations between two frames are carried out. The proposed controllers are compared to traditional PID controllers. The simulation and laboratory tests show the high performance achieved by the proposed combined fuzzy-PID controller for the designed ISP, where better robustness, transient response, and steady-state error are obtained when compared to the conventional controllers.

Energy efficient target tracking in wireless sensor network using PF-SVM (particle filter-support vector machine) technique

When using a Wireless Sensor Network (WSN) for target tracking applications, optimum selection of right functioning nodes can reduce the number of active nodes and also ensuring tracking reliability requirement. Due to the limitations of the WSN's sensing range, it is crucial to create a mechanism that allows nodes to coordinate in order to follow the target reliably and with a high probability. By doing this, the network's overall energy consumption can be decreased, resulting in a longer network lifetime. Target tracking (TT) is a well observed and significant application of WSNs. In simple words, it maintains a proper trade-off between tracking quality and energy consumption. In the proposed work, Particle Filter (PF) with a machine learning technique called Support Vector Machine (SVM) based energy efficient target tracking used in WSN's. PF is considered to be the most accepted filtering algorithm in various tracking and localization problems. Simulation results show greater performance in determining the target location and maintain lower energy consumption.

Energy-Efficient Object Detection and Tracking Framework for Wireless Sensor Network

Object detection and tracking is one of the key applications of wireless sensor networks (WSNs). The key issues associated with this application include network lifetime, object detection and localization accuracy. To ensure the high quality of the service, there should be a trade-off between energy efficiency and detection accuracy, which is challenging in a resource-constrained WSN. Most researchers have enhanced the application lifetime while achieving target detection accuracy at the cost of high node density. They neither considered the system cost nor the object localization accuracy. Some researchers focused on object detection accuracy while achieving energy efficiency by limiting the detection to a predefined target trajectory. In particular, some researchers only focused on node clustering and node scheduling for energy efficiency. In this study, we proposed a mobile object detection and tracking framework named the Energy Efficient Object Detection and Tracking Framework (EEODTF) for heterogeneous WSNs, which minimizes energy consumption during tracking while not affecting the object detection and localization accuracy. It focuses on achieving energy efficiency via node optimization, mobile node trajectory optimization, node clustering, data reporting optimization and detection optimization. We compared the performance of the EEODTF with the Energy Efficient Tracking and Localization of Object (EETLO) model and the Particle-Swarm-Optimization-based Energy Efficient Target Tracking Model (PSOEETTM). It was found that the EEODTF is more energy efficient than the EETLO and PSOEETTM models.

Machine Learning-Assisted Computationally Efficient Target Detection and Tracking in Massive Fully Digital Phased Arrays

Machine Learning-Assisted Computationally Efficient Target Detection and Tracking in Massive Fully Digital Phased Arrays

Nonlinear autoregressive neural network with exogenous input for an energy efficient non-cooperative target tracking in wireless sensor network

Nonlinear autoregressive neural network with exogenous input for an energy efficient non-cooperative target tracking in wireless sensor network

An efficient real-time target tracking algorithm using adaptive feature fusion

Visual-based target tracking is easily influenced by multiple factors, such as background clutter, targets’ fast-moving, illumination variation, object shape change, occlusion, etc. These factors influence the tracking accuracy of a target tracking task. To address this issue, an efficient real-time target tracking method based on a low-dimension adaptive feature fusion is proposed to allow us the simultaneous implementation of the high-accuracy and real-time target tracking. First, the adaptive fusion of a histogram of oriented gradient (HOG) feature and color feature is utilized to improve the tracking accuracy. Second, a convolution dimension reduction method applies to the fusion between the HOG feature and color feature to reduce the over-fitting caused by their high-dimension fusions. Third, an average correlation energy estimation method is used to extract the relative confidence adaptive coefficients to ensure tracking accuracy. We experimentally confirm the proposed method on an OTB100 data set. Compared with nine popular target tracking algorithms, the proposed algorithm gains the highest tracking accuracy and success tracking rate. Compared with the traditional Sum of Template and Pixel-wise LEarners (STAPLE) algorithm, the proposed algorithm can obtain a higher success rate and accuracy, improving by 2.3% and 1.9%, respectively. The experimental results also demonstrate that the proposed algorithm can reach the real-time target tracking with 50+fps. The proposed method paves a more promising way for real-time target tracking tasks under a complex environment, such as appearance deformation, illumination change, motion blur, background, similarity, scale change, and occlusion.

Dynamic Nodes Collaboration for Target Tracking in Wireless Sensor Networks

In target tracking WSNs, the tree-based and cluster-based network should be rebuilt when the location of target changes, which involves energy and time overheads. Although the chain structure solves this problem, it involves lots of unnecessary nodes and unacceptable transmitting delay. Therefore, we propose a dynamic chain-based collaboration (DCBC) approach for efficient target tracking and data gathering in this paper. DCBC completes the target tracking task by forming a dynamic tracking chain around the target. With the target moving, the dynamic tracking chain is adjusted by pruning some nodes as long as they are out of the range of the target and adding the nodes which entered the range of the target, so that the chain can adapt to the changing location of the target. The structure of the dynamic tracking chain does not need to be re-established when the target position changes. Furthermore, the sensing data are fused at every step when they are transmitted along the dynamic tracking chain. Using this way, the sensing data can be collected by tracking nodes and fused locally. In addition, we propose a dynamic and energy-efficient sleep scheduling for data transmission in the target tracking chain. The nodes in the tracking chain send their own data in turn. Thus it improves the energy utilization and data transmission efficiency of the network. The experimental results verify that DCBC can reduce and balance the average energy consumption of the network compared with the state-of-the-art approaches, and prolong the lifetime of networks.

Reinforcement Learning Based Querying in Camera Networks for Efficient Target Tracking

Surveillance camera networks are a useful monitoring infrastructure that can be used for various visual analytics applications, where high-level inferences and predictions could be made based on target tracking across the network. Most multi-camera tracking works focus on re-identification problems and trajectory association problems. However, as camera networks grow in size, the volume of data generated is humongous, and scalable processing of this data is imperative for deploying practical solutions. In this paper, we address the largely overlooked problem of scheduling cameras for processing by selecting one where the target is most likely to appear next. The inter-camera handover can then be performed on the selected cameras via re-identification or another target association technique. We model this scheduling problem using reinforcement learning and learn the camera selection policy using Q-learning. We do not assume the knowledge of the camera network topology but we observe that the resulting policy implicitly learns it. We evaluate our approach using NLPR MCT dataset, which is a real multi-camera multi-target tracking benchmark and show that the proposed policy substantially reduces the number of frames required to be processed at the cost of a small reduction in recall.

LeDA: leadership delegation based activation scheme for target tracking in wireless sensor networks

Energy-efficiency is an issue that needs to be considered while designing a scheme for target tracking. The purpose of this paper is to propose a scheme for target tracking that mitigates the power consumption. The proposed scheme consists of a dynamic leadership delegation based activation algorithm for efficient target tracking. A dynamic activation range for awaking sensors in the neighborhood of the target is used depending on its speed. The effectiveness of the proposed scheme is analysed through extensive simulations. The performance of the proposed approach is observed to be better than the existing approaches in terms of the accuracy of tracking and the amount of power consumption.

A non-conventional lightweight Auto Regressive Neural Network for accurate and energy efficient target tracking in Wireless Sensor Network

The design of an energy-efficient tracking framework is a well-investigated issue and a prominent sensor network application. The current research state shows a clear scope for developing algorithms that can work, accompanying both energy efficiency and accuracy. The prediction-based algorithms can save network energy by carefully selecting suitable nodes for continuous target tracking. However, the conventional prediction algorithms are confined to fixed motion models and generally fail in accelerated target movements. The neural networks can learn any non-linearity between input and output as they are model-free estimators. To design a lightweight neural network-based prediction algorithm for resource-constrained tiny sensor nodes is a challenging task. This research aims to develop a simpler, energy-efficient, and accurate network-based tracking scheme for linear and non-linear target movements. The proposed technique uses an autoregressive model to learn the temporal correlation between successive samples of a target trajectory. The simulation results are compared with the traditional Kalman filter (KF), Interacting Multiple models (IMM), Current Statistical model (CSM), Long Short Term Memory (LSTM), Decision Tree (DT), and Random Forest (RF) based tracking approach. It shows that the proposed algorithm can save up to 70% of network energy with improved prediction accuracy.

Nonlinear autoregressive neural network with exogenous input for an energy efficient non-cooperative target tracking in wireless sensor network

Nonlinear autoregressive neural network with exogenous input for an energy efficient non-cooperative target tracking in wireless sensor network

Energy Efficient Target Tracking Method for Multi-Sensory scheduling in Wireless Sensor Networks

Data collection utilizing wireless sensors networks (WSNs) has been utilized for surveillance, monitoring environment, animal etc. Target tracking of maneuvering objects is an essential need of modern life. Nonetheless, because of diverse nature of sensor and complex environment, sensors measurement errors need to be minimized considering diverse motion states in process of tracking (sensing) operation. Enhancing network lifetime (i.e., reducing energy dissipation of sensor nodes) and improving tracking quality are major concern of target tracking using WSN. Form improving network energy efficiency, multi-sensory target tracking method has been modelled using Kalman Filter (KF) by existing target tracking method. The KF based model are affected due to presence of noise or missing data. For overcoming research issues this paper present an H-infinity filter (HF) to evaluate fusion for maneuvering target tracking in WSN. Further, to minimize the estimation errors and reduces/controlling the effects of outliers fuzzy H-infinity (FHF) filter for target tracking WSN is presented. Experiment outcome shows proposed HF and FHF fusion model attain better performance than existing KF based method for clustered based WSN in terms of positional and velocity root mean square error and energy dissipation.

Bayesian Localized Energy Optimized Sensor Distribution for Efficient Target Tracking

In wireless sensor network application, the localization of nodes are carried out for extended life time of the node. Many applications in wireless sensor network perform localization of nodes over an extended period of time with energy variance. However, optimal selection algorithm poses new challenges to the overall transmission power levels for target detection, and thus localized energy optimized sensor management strategies are necessary for improving the accuracy of target tracking. In this work, it is proposed to develop a Bayesian Localized Energy Optimized Sensor Distribution (BLEOSD) scheme for efficient target tracking in Wireless Sensor Network. The sensor node localized with Bayesian average scheme thatestimates the sensor node’s energy are optimized as per data transfer capacity verification. The Bayesian average energy level of the sensor network is compared with the energy of each sensor node. The sensor nodes are localized and energy distribution based on the Bayesian energy estimate for efficient target tracking. The sensor node distribution strategy improves the accuracyto identify the targets effectively. Experiments are conducted using simulation of WSN by varying number of nodes, energy levels of the node and target object density using the Network Simulator Tool (NS2) The proposed BLEOSD technique is compared with various recent methods by evaluating accuracy of target tracking, energy consumption rate, localized node density and time for target tracking. The experimental results shows that the performance of BLESOD is more encouraging compared to contemporary methods.

An Efficient Target Tracking in Directional Sensor Networks Using Adapted Unscented Kalman Filter

In this paper we have considered an efficient adapted Unscented Kalman Filter based target tracking in directional wireless sensor networks while observations are noise-corrupted. In directional sensor networks, sensors are able to observe the target only in specified (and certainly changeable) directions. Also, sensor nodes are capable of measuring the bearings (relative angle to the target). To make target tracking efficient, first, we use scheduling algorithm which determines the sensor nodes activity. Also coverage is a challenge that we will discuss in this paper as well. Sensor nodes activation algorithm directly affects the target areas coverage. Second, we use time series to predict the motion of the target. Using ARIMA, in each step of target position estimation, an area will be predicted where the target would be there with high probability. Third, we use a version of UKF, which is adjusted to the requirements of the target tracking application, to determine the position of the target with desired precision. Fourth, a routing algorithm called as C-RPL is used to perform the communications between sensor nodes in each step. Simulation results approve that the proposed efficient target tracking algorithm achieves its goals.

Particle swarm optimization-based energy efficient target tracking in wireless sensor network

Wireless Sensor Network plays a vital role in tracking the mobility of targets like animals for habitat monitoring, vehicle monitoring etc. Many researches have been carried out for the precise identity of the target. In this research work, a distributed energy optimization method for target tracking is carried out using Particle Swarm Optimization. The proposed work is comprised of estimation phase and prediction phase. Here, clustering is performed using maximum entropy method. Grid exclusion is used for the coverage of nodes in the network. Performance evaluation is carried out for the proposed target tracking method with the existing systems using network simulator software.