The Experts below are selected from a list of 10509 Experts worldwide ranked by ideXlab platform
Jean-marc Le Caillec - One of the best experts on this subject based on the ideXlab platform.
-
EUSIPCO - Marked Poisson Point process PHD filter for DOA tracking
2015 23rd European Signal Processing Conference (EUSIPCO), 2015Co-Authors: Augustin-alexandru Saucan, Thierry Chonavel, Christophe Sintes, Jean-marc Le CaillecAbstract:In this paper we propose a Track Before Detect (TBD) filter for Direction Of Arrival (DOA) tracking of multiple targets from phased-array observations. The phased-array model poses a new problem since each target emits a signal, called source signal. Existing methods consider the source signal as part of the system state. This is inefficient, especially for particle approximations of posteriors, where samples are drawn from the higher-dimensional posterior of the extended state. To address this problem, we propose a novel Marked Poisson Point Process (MPPP) model and derive the Probability Hypothesis Density (PHD) filter that adaptively estimates target DOAs. The PPP models variations of both the number and the location of Points representing targets. The mark of a Point represents the source signal, without the need of an extended state. Recursive formulas for the MPPP PHD filter are derived with simulations showcasing improved performance over state-of-the art methods.
-
Track before detect DOA tracking of extended targets with marked Poisson Point processes
2015 18th International Conference on Information Fusion (Fusion), 2015Co-Authors: Augustin-alexandru Saucan, Thierry Chonavel, Christophe Sintes, Jean-marc Le CaillecAbstract:In this paper we propose a novel Track Before Detect (TBD) filter aimed at tracking multiple extended targets from phased-array observations. For extended targets, the source signal is angularly distributed, and hence we track the centroid Direction Of Arrival (DOA) of the target generated signal - called target signal. In this work we suppose known the shape and extent of the target-signal angular spread. Solutions based on extending the system state, to include the target signal, lead to higher-dimensional posteriors. We avoid an extended state by using a novel Marked Poisson Point Process (MPPP) model for the system, and accordingly, we derive the intensity/PHD filter that adaptively estimates target number and corresponding centroid DOAs. The source signals are interpreted as the mark of a target, and they are analytically integrated in the update formula of the filter. Therefore, an efficient particle filter implementation is possible. Results on simulated data showcase the improved results of the proposed filter over state-of-the-art methods.
-
Marked Poisson Point process PHD filter for DOA tracking
2015 23rd European Signal Processing Conference (EUSIPCO), 2015Co-Authors: Augustin-alexandru Saucan, Thierry Chonavel, Christophe Sintes, Jean-marc Le CaillecAbstract:In this paper we propose a Track Before Detect (TBD) filter for Direction Of Arrival (DOA) tracking of multiple targets from phased-array observations. The phased-array model poses a new problem since each target emits a signal, called source signal. Existing methods consider the source signal as part of the system state. This is inefficient, especially for particle approximations of posteriors, where samples are drawn from the higher-dimensional posterior of the extended state. To address this problem, we propose a novel Marked Poisson Point Process (MPPP) model and derive the Probability Hypothesis Density (PHD) filter that adaptively estimates target DOAs. The PPP models variations of both the number and the location of Points representing targets. The mark of a Point represents the source signal, without the need of an extended state. Recursive formulas for the MPPP PHD filter are derived with simulations showcasing improved performance over state-of-the art methods.
Hung Gia Hoang - One of the best experts on this subject based on the ideXlab platform.
-
the cauchy schwarz divergence for Poisson Point processes
IEEE Transactions on Information Theory, 2015Co-Authors: Hung Gia Hoang, Ba-ngu Vo, Ba-tuong Vo, Ronald P S MahlerAbstract:In this paper, we extend the notion of Cauchy–Schwarz divergence to Point processes and establish that the Cauchy–Schwarz divergence between the probability densities of two Poisson Point processes is half the squared ${L^{2}}$ -distance between their intensity functions. Extension of this result to mixtures of Poisson Point processes and, in the case where the intensity functions are Gaussian mixtures, closed form expressions for the Cauchy–Schwarz divergence are presented. Our result also implies that the Bhattacharyya distance between the probability distributions of two Poisson Point processes is equal to the square of the Hellinger distance between their intensity measures. We illustrate the result via a sensor management application where the system states are modeled as Point processes.
-
The Cauchy–Schwarz Divergence for Poisson Point Processes
IEEE Transactions on Information Theory, 2015Co-Authors: Hung Gia Hoang, Ba-ngu Vo, Ba-tuong Vo, Ronald MahlerAbstract:In this paper, we extend the notion of Cauchy-Schwarz divergence to Point processes and establish that the Cauchy-Schwarz divergence between the probability densities of two Poisson Point processes is half the squared L2-distance between their intensity functions. Extension of this result to mixtures of Poisson Point processes and, in the case where the intensity functions are Gaussian mixtures, closed form expressions for the Cauchy-Schwarz divergence are presented. Our result also implies that the Bhattacharyya distance between the probability distributions of two Poisson Point processes is equal to the square of the Hellinger distance between their intensity measures. We illustrate the result via a sensor management application where the system states are modeled as Point processes.
-
The Cauchy-Schwarz divergence for Poisson Point processes
2014 IEEE Workshop on Statistical Signal Processing (SSP), 2014Co-Authors: Hung Gia Hoang, Ba-ngu Vo, Ba-tuong Vo, Ronald MahlerAbstract:Information theoretic divergences are fundamental tools used to measure the difference between the information conveyed by two random processes. In this paper, we show that the Cauchy-Schwarz divergence between two Poisson Point processes is the half the squared L2-distance between their respective intensity functions. Moreover, this can be evaluated in closed form when the intensities are Gaussian mixtures.
Ronald Mahler - One of the best experts on this subject based on the ideXlab platform.
-
The Cauchy–Schwarz Divergence for Poisson Point Processes
IEEE Transactions on Information Theory, 2015Co-Authors: Hung Gia Hoang, Ba-ngu Vo, Ba-tuong Vo, Ronald MahlerAbstract:In this paper, we extend the notion of Cauchy-Schwarz divergence to Point processes and establish that the Cauchy-Schwarz divergence between the probability densities of two Poisson Point processes is half the squared L2-distance between their intensity functions. Extension of this result to mixtures of Poisson Point processes and, in the case where the intensity functions are Gaussian mixtures, closed form expressions for the Cauchy-Schwarz divergence are presented. Our result also implies that the Bhattacharyya distance between the probability distributions of two Poisson Point processes is equal to the square of the Hellinger distance between their intensity measures. We illustrate the result via a sensor management application where the system states are modeled as Point processes.
-
The Cauchy-Schwarz divergence for Poisson Point processes
2014 IEEE Workshop on Statistical Signal Processing (SSP), 2014Co-Authors: Hung Gia Hoang, Ba-ngu Vo, Ba-tuong Vo, Ronald MahlerAbstract:Information theoretic divergences are fundamental tools used to measure the difference between the information conveyed by two random processes. In this paper, we show that the Cauchy-Schwarz divergence between two Poisson Point processes is the half the squared L2-distance between their respective intensity functions. Moreover, this can be evaluated in closed form when the intensities are Gaussian mixtures.
Augustin-alexandru Saucan - One of the best experts on this subject based on the ideXlab platform.
-
EUSIPCO - Marked Poisson Point process PHD filter for DOA tracking
2015 23rd European Signal Processing Conference (EUSIPCO), 2015Co-Authors: Augustin-alexandru Saucan, Thierry Chonavel, Christophe Sintes, Jean-marc Le CaillecAbstract:In this paper we propose a Track Before Detect (TBD) filter for Direction Of Arrival (DOA) tracking of multiple targets from phased-array observations. The phased-array model poses a new problem since each target emits a signal, called source signal. Existing methods consider the source signal as part of the system state. This is inefficient, especially for particle approximations of posteriors, where samples are drawn from the higher-dimensional posterior of the extended state. To address this problem, we propose a novel Marked Poisson Point Process (MPPP) model and derive the Probability Hypothesis Density (PHD) filter that adaptively estimates target DOAs. The PPP models variations of both the number and the location of Points representing targets. The mark of a Point represents the source signal, without the need of an extended state. Recursive formulas for the MPPP PHD filter are derived with simulations showcasing improved performance over state-of-the art methods.
-
Track before detect DOA tracking of extended targets with marked Poisson Point processes
2015 18th International Conference on Information Fusion (Fusion), 2015Co-Authors: Augustin-alexandru Saucan, Thierry Chonavel, Christophe Sintes, Jean-marc Le CaillecAbstract:In this paper we propose a novel Track Before Detect (TBD) filter aimed at tracking multiple extended targets from phased-array observations. For extended targets, the source signal is angularly distributed, and hence we track the centroid Direction Of Arrival (DOA) of the target generated signal - called target signal. In this work we suppose known the shape and extent of the target-signal angular spread. Solutions based on extending the system state, to include the target signal, lead to higher-dimensional posteriors. We avoid an extended state by using a novel Marked Poisson Point Process (MPPP) model for the system, and accordingly, we derive the intensity/PHD filter that adaptively estimates target number and corresponding centroid DOAs. The source signals are interpreted as the mark of a target, and they are analytically integrated in the update formula of the filter. Therefore, an efficient particle filter implementation is possible. Results on simulated data showcase the improved results of the proposed filter over state-of-the-art methods.
-
Marked Poisson Point process PHD filter for DOA tracking
2015 23rd European Signal Processing Conference (EUSIPCO), 2015Co-Authors: Augustin-alexandru Saucan, Thierry Chonavel, Christophe Sintes, Jean-marc Le CaillecAbstract:In this paper we propose a Track Before Detect (TBD) filter for Direction Of Arrival (DOA) tracking of multiple targets from phased-array observations. The phased-array model poses a new problem since each target emits a signal, called source signal. Existing methods consider the source signal as part of the system state. This is inefficient, especially for particle approximations of posteriors, where samples are drawn from the higher-dimensional posterior of the extended state. To address this problem, we propose a novel Marked Poisson Point Process (MPPP) model and derive the Probability Hypothesis Density (PHD) filter that adaptively estimates target DOAs. The PPP models variations of both the number and the location of Points representing targets. The mark of a Point represents the source signal, without the need of an extended state. Recursive formulas for the MPPP PHD filter are derived with simulations showcasing improved performance over state-of-the art methods.
Ba-tuong Vo - One of the best experts on this subject based on the ideXlab platform.
-
the cauchy schwarz divergence for Poisson Point processes
IEEE Transactions on Information Theory, 2015Co-Authors: Hung Gia Hoang, Ba-ngu Vo, Ba-tuong Vo, Ronald P S MahlerAbstract:In this paper, we extend the notion of Cauchy–Schwarz divergence to Point processes and establish that the Cauchy–Schwarz divergence between the probability densities of two Poisson Point processes is half the squared ${L^{2}}$ -distance between their intensity functions. Extension of this result to mixtures of Poisson Point processes and, in the case where the intensity functions are Gaussian mixtures, closed form expressions for the Cauchy–Schwarz divergence are presented. Our result also implies that the Bhattacharyya distance between the probability distributions of two Poisson Point processes is equal to the square of the Hellinger distance between their intensity measures. We illustrate the result via a sensor management application where the system states are modeled as Point processes.
-
The Cauchy–Schwarz Divergence for Poisson Point Processes
IEEE Transactions on Information Theory, 2015Co-Authors: Hung Gia Hoang, Ba-ngu Vo, Ba-tuong Vo, Ronald MahlerAbstract:In this paper, we extend the notion of Cauchy-Schwarz divergence to Point processes and establish that the Cauchy-Schwarz divergence between the probability densities of two Poisson Point processes is half the squared L2-distance between their intensity functions. Extension of this result to mixtures of Poisson Point processes and, in the case where the intensity functions are Gaussian mixtures, closed form expressions for the Cauchy-Schwarz divergence are presented. Our result also implies that the Bhattacharyya distance between the probability distributions of two Poisson Point processes is equal to the square of the Hellinger distance between their intensity measures. We illustrate the result via a sensor management application where the system states are modeled as Point processes.
-
The Cauchy-Schwarz divergence for Poisson Point processes
2014 IEEE Workshop on Statistical Signal Processing (SSP), 2014Co-Authors: Hung Gia Hoang, Ba-ngu Vo, Ba-tuong Vo, Ronald MahlerAbstract:Information theoretic divergences are fundamental tools used to measure the difference between the information conveyed by two random processes. In this paper, we show that the Cauchy-Schwarz divergence between two Poisson Point processes is the half the squared L2-distance between their respective intensity functions. Moreover, this can be evaluated in closed form when the intensities are Gaussian mixtures.
