The goal of maritime situational awareness (MSA) is to provide a seamless wide-area operational picture of ship traffic in coastal areas and the oceans in real time. Radar is a central sensing modality for MSA. In par...
详细信息
The goal of maritime situational awareness (MSA) is to provide a seamless wide-area operational picture of ship traffic in coastal areas and the oceans in real time. Radar is a central sensing modality for MSA. In particular, oceanographic high-frequency surface-wave (HFSW) radars are attractive for surveying large sea areas at over-the-horizon distances, due to their low environmental footprint and low power requirements. However, their design is not optimal for the challenging conditions prevalent in MSA applications, thus calling for the development of dedicated information fusion and multisensor-multitargettrackingalgorithms. In this study, the authors show how the multisensor-multitargettracking problem can be formulated in a Bayesian framework and efficiently solved by running the loopy sum-product algorithm on a suitably devised factor graph. Compared to previously proposed methods, this approach is advantageous in terms of estimation accuracy, computational complexity, implementation flexibility, and scalability. Moreover, its performance can be further enhanced by estimating unknown model parameters in an online fashion and by fusing automatic identification system (AIS) data and context-based information. The effectiveness of the proposed Bayesian multisensor-multitargettracking and information fusionalgorithms is demonstrated through experimental results based on simulated data as well as real HFSW radar data and real AIS data.
In order to balance the accuracy and real-time performance of the moving targettracking system, an optimized design and implementation method based on high-level synthesis (HLS) of multi-feature fusion with kernel co...
详细信息
In order to balance the accuracy and real-time performance of the moving targettracking system, an optimized design and implementation method based on high-level synthesis (HLS) of multi-feature fusion with kernel co...
详细信息
In order to balance the accuracy and real-time performance of the moving targettracking system, an optimized design and implementation method based on high-level synthesis (HLS) of multi-feature fusion with kernel correlation filtering algorithms on FPGA is designed. This design improves the KCF algorithm with LBP and HOG features, and proposes a new dimensionality reduction method for LBP, which enhances the real-time performance while maintaining effective extraction of target features. The algorithm is implemented with FPGA, and a well acceleration effect is obtained on the basis of high precision. In test, the frame rate reaches 35 frames per second. Finally, it is verified through simulation that this feature extraction method can be used to process various image data such as infrared detection and SAR radar imaging, and has a wide range of applications.
The point target assumption, which suggests that a target can generate at most one measurement at a time, is used in typical targettrackingalgorithms. However, in many practical applications, multiple scattering poi...
详细信息
The point target assumption, which suggests that a target can generate at most one measurement at a time, is used in typical targettrackingalgorithms. However, in many practical applications, multiple scattering points of a target can be resolved using a high-resolution sensor, which gives rise to the multiple detection problem. The typical algorithms with the point target assumption are not eligible for multiple detection tracking environments. The multiple detection joint integrated probabilistic data association algorithm is designed to solve the multiple detection multitargettracking problem. However, the computational complexity of this algorithm grows exponentially with the number of tracks and measurement cells. Here, multiple detection linear multitarget integrated probabilistic data association is proposed to enhance computational efficiency by introducing the modulated clutter measurement density, which takes into account the contributions of clutter as well as other targets of each measurement cell. The computational complexity of the proposed algorithm is linear in the number of tracks and the number of measurement cells. Simulation results verify the applicability and efficiency of the proposed algorithm in multiple detection multitargettracking scenarios.
In this study, an enhanced approach for automotive radar systems is proposed to solve the detection, tracking, and track management problem in the presence of clutter with high accuracy and low computational cost. The...
详细信息
In this study, an enhanced approach for automotive radar systems is proposed to solve the detection, tracking, and track management problem in the presence of clutter with high accuracy and low computational cost. The unscented Kalman filter (UKF) with a constant turn rate and acceleration (CTRA) dynamic model is employed for targettracking, and the tracking accuracy is enhanced by incorporating the linear regression (LR) algorithm into the UKF-CTRA algorithm. We investigate, for the first time, the Joint Probabilistic data Association (JPDA) algorithm for data association, and the composite M/N tests for track management. The capability of the proposed approach (CTRA-UKF-LR-JPDA-composite-M/N-tests) is demonstrated by comparing it with various algorithms for different single and multi-targettracking scenarios and for various sets of parameter regimes. The results show the superior performance of the proposed method over other existing techniques in automotive radar systems. This reveals the effectiveness of the proposed algorithm as a promising technique in automotive applications.
The proceedings contain 12 papers. The topics discussed include: Bayesian tracking and multi-core beamforming for estimation of correlated brain sources;particle filtering for network-based positioning terrestrial rad...
ISBN:
(纸本)9781849198639
The proceedings contain 12 papers. The topics discussed include: Bayesian tracking and multi-core beamforming for estimation of correlated brain sources;particle filtering for network-based positioning terrestrial radio networks;tracking simulated UAV swarms using particle filters;rectangular extended object tracking with box particle filter using dynamic constraints;probabilistic step and turn detection in indoor localization;fusing kinect sensor and inertial sensors with multi-rate kalman filter;piecewise constant sequential importance sampling for fast particle filtering;hybrid gauss-hermite filter;regional variance in target number: analysis and application for multi-Bernoulli point processes;combined evidential data association;and PHD filtering in presence of highly structured sea clutter process and tracks with extent.
The proceedings contain 23 papers. The topics discussed include: fusion without independence;investigation into the utility of using CFAR cluster size information in target track association;multi-sensor debris tracki...
ISBN:
(纸本)9780863419102
The proceedings contain 23 papers. The topics discussed include: fusion without independence;investigation into the utility of using CFAR cluster size information in target track association;multi-sensor debris tracking;Gaussian mixture implementations of probability hypothesis density filters for non-linear dynamical models;population based particle filtering;MAP estimation in particle filter tracking;a new algorithm for GMTI tracking problems, subject to a Doppler blind zone constraint;a technique to segment by tracking extended targets manoeuvring through complex scenes;video tracking using dual-tree wavelet polar matching and particle filtering;cluster tracking under kinematical constraints using random matrices;evolving networks for group object motion estimation;fusion of novel biometrics for human tracking and identification;and NATO intelligence surveillance reconnaissance tracking standard NATO STANAG 4676.
In this paper, we present a new method for data association in multi-targettracking situation in the framework of evidence theory. The representation and the fusion of the information in our method are based on the u...
详细信息
ISBN:
(纸本)9781849198639
In this paper, we present a new method for data association in multi-targettracking situation in the framework of evidence theory. The representation and the fusion of the information in our method are based on the use of belief function in the sense of Dempster-Shafer theory of evidence. The proposal generates two belief matrices using two different specialized basic belief mass assignments. While the decision making process is based on the extension of the frame of hypotheses. The method has been tested for a nearly constant velocity target in two ambiguous cases using Monte Carlo simulations.
This paper provides an initial examination of the use of particle filters in tracking swarms of small targets such as Unmanned Aerial Vehicles using a radar. From the standpoint of conventional tracking solutions, suc...
详细信息
ISBN:
(纸本)9781849198639
This paper provides an initial examination of the use of particle filters in tracking swarms of small targets such as Unmanned Aerial Vehicles using a radar. From the standpoint of conventional tracking solutions, such swarms present a severe challenge - due not only to the quasi-erratic motion of the UAVs relative to the swarm trajectory as a whole, but also from the effects of the small target size upon radar resolution and detection probability. It is shown here that a particle filter is capable of providing a stable track on the swarm centroid, although not the individual constituent UAVs.
In the context of multi-targettracking application, the concept of variance in the number of targets estimated in specified regions of the surveillance scene has been recently introduced for multi-object filters. Thi...
详细信息
ISBN:
(纸本)9781849198639
In the context of multi-targettracking application, the concept of variance in the number of targets estimated in specified regions of the surveillance scene has been recently introduced for multi-object filters. This article has two main objectives. First, the regional variance is derived for a multi-object representation commonly used in the tracking literature, known as the multi-Bernoulli point process, in which the multi-target state is described with a set of hypothesised tracks with associated existence probabilities. This model is exploited in multi-targetapplications where it can be assumed that targets evolve independently of each other and generate sensor observations that are uncorrelated with other targets. An illustration of the concept of regional statistics (mean and variance) in target number, and how to interpret them in the broader context of multi-object filtering, it then provided. Possible applications include performance assessment and sensor control for multi-targettracking.
暂无评论