Analytic Implementations of the Cardinalized Probability Hypothesis Density Filter

By B. Vo, Antonio Cantoni. IEEE Transactions on Signal Processing, 2007

851 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Oceanography

View Paper: https://www.semanticscholar.org/paper/f416bb885d9ecb0ef54f6a5cb84e4b914bd42644

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Oceanography

Citations in the corpus

The Labeled Multi-Bernoulli Filter (2014, background): “Gaussian mixture and particle implementations of these filters have been developed in [10], [12]–[16].”
The Cardinality Balanced Multi-Target Multi-Bernoulli Filter and Its Implementations (2009, methodology): “Sequential Monte Carlo (SMC) implementations [6]–[8] with provable convergence [6], [9], [10] and closed form solutions [11], [12] have opened the door to numerous novel extensions and applications which can be found in the surveys [3], [13].”
Joint Detection and Estimation of Multiple Objects From Image Observations (2010, background): “D. Suter is with the School of Computer Science, University of Adelaide, North Terrace SA 5005, Australia (e-mail: dsuter@cs.adelaide.edu.au).”
Consensus CPHD Filter for Distributed Multitarget Tracking (2013, methodology): “Taking into account all the above considerations, this paper presents a novel consensus Cardinalized Probability Hypothesis Density (CPHD) filter, based on a Gaussian Mixture (GM) implementation, for Distributed MultiTarget Tracking (DMTT) over a sensor network.”
Labeled Random Finite Sets and the Bayes Multi-Target Tracking Filter (2013, methodology): “In this subsection we use the PHD/CPHD update and prediction [8], [29], [50]–[52] to look-ahead and identify the prediction/update components that generate significant updated/predicted components.”
PHD filters of higher order in target number (2006, background): “Vo, Vo, and Cantoni have implemented and successfully tested it and compared its performance with that of the PHD filter and the joint probabilistic data association (JPDA) filter (see Section V).”
A Random-Finite-Set Approach to Bayesian SLAM (2011, neutral): “Both ∏ m∈Mk vk |k−1(m|X0:k ) and ∏ m∈Mk vk (m|X0:k ) are empty, thereby implying that their product is 1, m̂k |k−1 =∫ vk |k−1(m|X0:k )dm, and m̂k = ∫ vk (m|X0:k )dm, giving gk (Zk |Z0:k−1 ,X0:k ) = ∏ z∈Zk ck (z|Xk ) × exp ( m̂k − m̂k |k−1 − ∫ ck (z|Xk )dz ) .”
On performance evaluation of multi-object filters (2008, methodology): “6(a) shows the results for c = 30m which suggests that on average the CPHD and PHD filters are making an error of roughly 11m and 12m respectively per target.”
Adaptive Target Birth Intensity for PHD and CPHD Filters (2012, methodology): “Then the predicted cardinality distribution can be written as a convolution [10]:”
A Tutorial on Bernoulli Filters: Theory, Implementation and Applications (2013, background): “…classes of its simplifications or principled approximations have emerged recently: the Bernoulli filter (also known as JoTT or joint target detection and tracking filter) [10], [15]–[18], the probability hypothesis density (PHD) filter [19]–[22], the cardinalized PHD filter [23], [24] and the…”
Labeled Random Finite Sets and Multi-Object Conjugate Priors (2013, background): “Implementations of these filters are developed in [23]–[26], [22], with convergence analysis given in [23], [27]–[30].”
Marginal multi-bernoulli filters: RFS derivation of MHT, JIPDA, and association-based member (2012, methodology): “We compare the proposed methods to CPHD [4] [5], CB- MeMBer [6], JITS and linear multi-target ITS (LMITS) [10] [11] (a variant of JITS which replaces the marginal association probabilities with a heuristic approximation).”
A Consistent Metric for Performance Evaluation of Multi-Object Filters (2008, methodology): “The multi-target filters used to test the new metric are the Gaussian mixture PHD [22] and Gaussian mixture CPHD [23] filters.”
Tracking of extended objects and group targets using random matrices — a new approach (2008, background): “In particular, the probability hypothesis density (PHD) filter [3]–[5] has been suggested as one possibility to track an unknown number of possibly closely spaced targets while simultaneously solving the association problem in an approximate yet very efficient manner, especially in its Gaussian mixt”