Gaussian Mixture initialization in passive tracking applications

Daun, Martina; Kaune, Regina

doi:10.1109/icif.2010.5711980

Cited by 10 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Assigning a cost to each of the association events ε s with its generalized likelihood ratio, i.e. (20) and denoting as the association event space which contains all the feasible association events ε s , the m-best 2-D assignment problem is casted in the following…”

Section: B Sequential Msjpdamentioning

confidence: 99%

“…More challengingly in PMSR with only range and Doppler measurements, the position of a target cannot be determined by using only one transmit-receive pair. To cope with these difficulties, research has been conducted on track initiation, track confirm, track maintenance, and track terminate [17]- [20]. In this paper we assume track initiation and confirm to have been performed beforehand.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sequential Multi-Sensor JPDA for Target Tracking in Passive Multi-Static Radar With Range and Doppler Measurements

Lyu

Wang

2019

IEEE Access

View full text Add to dashboard Cite

Target tracking in passive multi-static radar (PMSR) with bistatic range and Doppler frequency measurements from multiple transmit-receive pairs is gaining increasing interest. For the data association problem in this scenario, the parallel architecture of a multi-sensor joint probabilistic data association (P-MSJPDA) filter has been significantly investigated. As an alternative architecture, the sequential MSJPDA (S-MSJPDA) is rarely discussed in PMSR. In this paper, we evaluate the behaviors of S-MSJPDA in PMSR target tracking with bistatic range and Doppler frequency measurements. A comprehensive comparison between the S-MSJPDA and the P-MSJPDA in PMSR is provided. It can be found from the analysis that S-MSJPDA outperforms its parallel counterpart in terms of computational efficiency, given an acceptable degradation in position accuracy. The S-MSJPDA is further applied to an experimental passive multi-static radar for aircrafts tracking. The real data results obtained are rather close to the true trajectories of the targets. This demonstrates that the S-MSJPDA has great potentials in PMSR target tracking. INDEX TERMS Passive multi-static radar, target tracking, multi-sensor joint probabilistic data association.

show abstract

Section: B Sequential Msjpdamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Sequential Multi-Sensor JPDA for Target Tracking in Passive Multi-Static Radar With Range and Doppler Measurements

Lyu

Wang

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, the opposite approach, approximating the measurement as a Gaussian mixture in Cartesian coordinates, was considered in [82] for track initiation using range-only measurements and in [212] for bearings-only tracking. These two approaches for approximating the converted measurement as a Gaussian mixture differ from the approach used in numerous other Gaussian mixture trackers such as [8], which allowed the noise in the nonlinear measurement domain to be represented as a Gaussian mixture but did not convert the measurement to the Cartesian domain.…”

Section: A Estimation Using Nonlinear Measurementsmentioning

confidence: 99%

“…Letting t be the Cartesian position of the target in the radar's local coordinate system, the measurement is (82) where w is zero-mean, additive Gaussian noise with covariance matrix R. The nonlinear function h ruv transforms the Cartesian coordinates into r-u-v coordinates. The presence of the noise means that a noise-ignorant transformation of an observation in noisy bistatic r-u-v Cartesian coordinates using (14)- (16) would result in a biased estimate.…”

Section: A An Overview Of the Conversionmentioning

confidence: 99%

Basic tracking using nonlinear 3D monostatic and bistatic measurements

Crouse¹

2014

IEEE Aerosp. Electron. Syst. Mag.

View full text Add to dashboard Cite

Monostatic and bistatic position and Doppler measurements used in radar and sonar systems are nonlinear transformations of a Cartesian state. These nonlinearities pose a challenge for many target tracking algorithms, causing the so-called contact lens problem, which describes the nonlinear appearance of the measurement probability density function in Cartesian coordinates. This tutorial considers methods for measurement filtering (tracking without considering data association) using a single-Gaussian approximation when monostatic and bistatic position and Doppler measurements are available. The connection between the cubature Kalman filter and numerous other filtering algorithms is shown, and the accuracy and consistency of different algorithms are compared through simulation. An effort is made to express the geometric relationships associated with multistatic tracking in a simple vectorial manner. This tutorial focuses on basic tracking, and the companion tutorials "Tracking Using 3D Monostatic and Bistatic Measurements in Refractive Environments" and "Basic Tracking Using Nonlinear Continuous-Time Dynamic Models" extend the results to more sophisticated physical models.

show abstract

“…In [15] the MHT operates efficiently locally at each receiver, initially forming two-dimensional (bistatic range and range-rate) hypotheses that are later resolved into three dimensions. Track initiation using Gaussian mixtures is in [14]. In this paper, our interest is in tracking in native geographic coordinates directly.…”

Section: Introductionmentioning

confidence: 99%

Multistatic target tracking for passive radar in a DAB/DVB network: initiation

Choi

Crouse

Willett

et al. 2015

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

A passive radar system that coopts digital broadcast (DAB/ DVB) signals is appealing but challenging: a single-antenna receiver system can only measure a bistatic range/range-rate; and, due to the energy-efficient multitransmitter commercial implementation, there is a confounding uncertainty as to which transmitter (illuminator) was responsible for a given "hit." In a companion paper we proposed some ways to track directly in native geographic coordinates. Here we suggest and compare two approaches for track initiation.

show abstract

Gaussian Mixture initialization in passive tracking applications

Cited by 10 publications

References 5 publications

Sequential Multi-Sensor JPDA for Target Tracking in Passive Multi-Static Radar With Range and Doppler Measurements

Sequential Multi-Sensor JPDA for Target Tracking in Passive Multi-Static Radar With Range and Doppler Measurements

Basic tracking using nonlinear 3D monostatic and bistatic measurements

Multistatic target tracking for passive radar in a DAB/DVB network: initiation

Contact Info

Product

Resources

About