BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Gaussian Particle Implementations of Probability Hypothesis Densit
 y Filters - Daniel Clark
DTSTART:20070222T130000Z
DTEND:20070222T140000Z
UID:TALK6693@talks.cam.ac.uk
CONTACT:Taylan Cemgil
DESCRIPTION:The Probability Hypothesis Density (PHD) filter is a multiple-
 target filter for recursively estimating the number of targets and their s
 tate vectors from sets of observations.\nThe filter is able to operate in 
 environments with false alarms and missed detections. Two distinct algorit
 hmic implementations of this technique have been developed. The\nfirst of 
 which\, known as the Particle PHD filter\, requires clustering techniques 
 to provide target state estimates which can lead to inaccurate estimates a
 nd is computationally expensive.\nThe second algorithm\, called the Gaussi
 an Mixture PHD (GM-PHD) filter does not require clustering algorithms but 
 is restricted to linear-Gaussian target dynamics\, since it\nuses the Kalm
 an filter to estimate the means and covariances of the Gaussians. Extensio
 ns for the GM-PHD filter allow for mildly non-linear dynamics using extend
 ed and Unscented Kalman filters. \nA new particle implementation of the PH
 D filter which does not require clustering to determine target states is p
 resented. \nThe PHD is approximated by a mixture of Gaussians\, as in the 
 GM-PHD filter but the transition density and likelihood function can be no
 n-linear. \nThe resulting filter no longer has a closed form solution so M
 onte Carlo integration is applied for approximating the prediction and upd
 ate distributions. \nThis is calculated using a bank of Gaussian particle 
 filters\, similar to the procedure used with the Gaussian sum particle fil
 ter. \nThe new algorithm is derived and presented with simulated results.\
 n 
LOCATION:LR6\, Engineering\, Department of
END:VEVENT
END:VCALENDAR