Offline and Real-Time Methods for ML-PDA Track Validation

Blanding, Wayne; Willett, Peter; Bar‐Shalom, Yaakov

doi:10.1109/tsp.2007.893212

Cited by 42 publications

(25 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous work from [2] showed that this peak PDF is a Gumbel distribution. This distribution has the form [7] f…”

Section: Extreme-value Clutter Pdfsmentioning

confidence: 69%

“…These results are compared to thresholds developed via the (much slower) method described in [2] -i.e. repeatedly simulating and optimizing a (clutter-only) ML-PMHT LLR surface.…”

Section: Threshold Determinationmentioning

confidence: 99%

“…Previous work in [2] presented a method for determining a track acceptance threshold for ML-PDA; the same method can be applied to ML-PMHT. Basically, for a certain set of problem parameters such as search volume, clutter density, probability of detection, signal-to-noise ratio, etc., the ML-PMHT LLR can be simulated and then maximized; if this is done repeatedly with Monte Carlo trials the empirical PDF (probability density function) of the maximum point in the LLR due to clutter can be obtained.…”

Section: Introductionmentioning

confidence: 99%

“…Often, this threshold determination method takes long enough that in past works [6], [12], a combination of this method and trial and error was used to find an appropriate tracking threshold for ML-PMHT implementations. The work in [2] did also develop a "real-time" method for track-validation for ML-PDA, but its accuracy was not as good as the "off-line" approach described above. We seek the accuracy of the off-line method in realtime speed.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

ML-PMHT threshold determination for false track probability using extreme-value analysis

Schoenecker

Bar‐Shalom

Willett

2013

2013 5th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)

Self Cite

View full text Add to dashboard Cite

The Maximum Likelihood Probabilistic MultiHypothesis Tracker (ML-PMHT) can be used as a powerful multisensor, low-observable, multitarget tracker. It is a nonBayesian algorithm that uses a generalized likelihood ratio (LR) test to differentiate between clutter and target tracks. Prior to this work, the detection threshold used for target track acceptance was determined either through trial and error or with lengthy Monte-Carlo simulations. We present a new method for determining this threshold by assuming that the clutter is uniformly distributed in the search space, and then treating the log-likelihood ratio (LLR) as a random variable transformation. In this manner, we can obtain an expression for the PDF of the likelihood function caused by clutter. We then use extreme value theory to obtain an expression for the PDF of the peak point of the LLR surface due to clutter. From this peak PDF, we can then calculate a threshold based on some desired (small) false track acceptance probability.

show abstract

“…Previous work from [2] showed that this peak PDF is a Gumbel distribution. This distribution has the form [7] f…”

Section: Extreme-value Clutter Pdfsmentioning

confidence: 69%

“…These results are compared to thresholds developed via the (much slower) method described in [2] -i.e. repeatedly simulating and optimizing a (clutter-only) ML-PMHT LLR surface.…”

Section: Threshold Determinationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%