Posterior Cramer-Rao bounds for multi-target tracking

Hue, Carine; Cadre, J.-P. Le; Pérez, Patrick

doi:10.1109/taes.2006.1603404

Cited by 50 publications

(15 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data association uncertainty in presence of imperfect detections was solved via a computational feasible multi- analogous to the problem of multi-sensor/multi-target tracking in clutter [62,63].…”

Section: Discussionmentioning

confidence: 99%

Simultaneous Target and Multipath Positioning

Krolik

2014

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

In this work, we present the Simultaneous Target and Multipath Positioning (STAMP) technique to jointly estimate the unknown target position and uncertain multipath channel parameters. We illustrate the applications of STAMP for target tracking/geolocation problems using single-station hybrid TOA/AOA system, monostatic MIMO radar and multistatic range-based/AOA based localization systems.The STAMP algorithm is derived using a recursive Bayesian framework by including the target state and multipath channel parameters as a single random vector, and the unknown correspondence between observations and signal propagation channels is solved using the multi-scan multi-hypothesis data association. In the presence of the unknown time-varying number of multipath propagation modes, the STAMP algorithm is modified based on the single-cluster PHD filtering by modeling the multipath parameter state as a random finite set. In this case, the target state is defined as the parent process, which is updated by using a particle filter or multi-hypothesis Kalman filter. The multipath channel parameter is defined as the daughter process and updated based on an explicit Gaussian mixture PHD filter. Moreover, the idenfiability analysis of the joint estimation problem is provided in terms of Cramér-Rao lower bound (CRLB).The Fisher information contributed by each propagation mode is investigated, and the v effect of Fisher information loss caused by the measurement origin uncertainty is also studied. The proposed STAMP algorithms are evaluated based on a set of illustrative numeric simulations and real data experiments with an indoor multi-channel radar testbed. Substantial improvement in target localization accuracy is observed.vi

show abstract

Section: Discussionmentioning

confidence: 99%

Simultaneous Target and Multipath Positioning

Krolik

2014

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

show abstract

“…In summary, we have cast the multi-target tracking problem in the form of the nonlinear filtering problem with state and measurement equations given by (4) and (8) respectively. This approach has already been adopted in [8], [9], [7] to perform recursive Bayesian track-before-detect estimation.…”

Section: Problem Formulationmentioning

confidence: 99%

“…Ideally, P d = 1 and P f = 0, but in reality this is never the case (P d < 1 and P f > 0); hence the tracker needs to deal with the uncertainty in the measurement origin. The most recent references on CRLBs for tracking in the presence of measurement origin uncertainty are [3] for single target case and [4] for multiple target case. In both cases the theoretical derivations are fairly involved and their solution requires numerical integration of multi-dimensional integrals.…”

Section: Introductionmentioning

confidence: 99%

Cram?r-Rao Bound for Multiple Target Tracking Using Intensity Measurements

Ristić¹,

Morelande

2007

2007 Information, Decision and Control

View full text Add to dashboard Cite

show abstract

“…Based on [2], there has been a surge of interest in extending the PCRLB to more practical scenarios, e.g., to include measurement origin uncertainty [17,18], to consider issues related to the quantization of sensor data, to compute approximated online PCRLB [19], and to derive online conditional PCRLB [20]. Subsequently, the PCRLB theory has been extended to several applications, e.g., for adaptive resource management [14], dynamic sensor selection [15], bearing-only tracking [21], and multiple-target tracking [22]. As stated earlier, previous derivations of the PCRLB are limited to the centralized and hierarchical estimation architectures [15], and only recently has a suboptimal PCRLB expression [16] been derived for the decentralized architectures.…”

Section: Introductionmentioning

confidence: 99%

Full- and reduced-order distributed Bayesian estimation analytical performance bounds

Mohammadi¹,

Asif²

2014

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

Motivated by the resource management problem in nonlinear multisensor tracking networks, the paper derives online, distributed estimation algorithms for computing the posterior Cramér-Rao lower bound (PCRLB) for full-order and reduced-order distributed Bayesian estimators without requiring a fusion center and with nodal communications limited to local neighborhoods. For both cases, Riccati-type recursions are derived that sequentially determine the global Fisher information matrix (FIM) from localizedFIMs of the distributed estimators. We use particle filter realizations for these bounds and quantify their performance for data fusion problems through Monte Carlo simulations. Manuscript

show abstract

Posterior Cramer-Rao bounds for multi-target tracking

Cited by 50 publications

References 18 publications

Simultaneous Target and Multipath Positioning

Simultaneous Target and Multipath Positioning

Cram?r-Rao Bound for Multiple Target Tracking Using Intensity Measurements

Full- and reduced-order distributed Bayesian estimation analytical performance bounds

Contact Info

Product

Resources

About