Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks93 from public data
- Fusion of Finite-Set Distributions: Pointwise Consistency and Global Cardinality62
It is proved that pointwise consistency of EMDs does not imply consistency in global cardinality and vice versa, and the variational problems underlying fusion are rewritten to provide iterative solutions thereby establishing a framework that guarantees cardinality consistent fusion.
- 58
- A Second-Order PHD Filter With Mean and Variance in Target Number49
A Second-Order PHD (SO-PHD) filter is proposed, propagating the second-order moment of the number of targets alongside its mean, which is more versatile in the modeling choices than the PHD filter, and its computational cost is significantly lower compared to the CPHD filter.
- Regional Variance for Multi-Object Filtering48
The proposed concept of regional variance quantifies the level of confidence on target number estimates in arbitrary regions and facilitates information-based decisions.
- Robust target motion analysis using the possibility particle filter42
The authors present a recently proposed stochastic filter implemented in the sequential Monte Carlo framework, and named the possibility particle filter, which demonstrates its superior performance against the standard (Bayesian) particle filter in the presence of a model mismatch.
- Smoothing and Filtering with a Class of Outer Measures41
It is shown how this representation of uncertainty can be propagated using outer-measure-type versions of Markov kernels and generalised Bayesian-like update equations to lead to a system of generalised smoothing and filtering equations.
- A Unified Approach for Multi-Object Triangulation, Tracking and Camera Calibration38
This paper addresses problems within a unified Bayesian framework for joint multi-object tracking and camera calibration, based on the finite set statistics methodology, and investigates an alternative parametrization for triangulation, called disparity space.
- The CPHD Filter With Target Spawning37
A principled derivation of the CPHD filter prediction step including spontaneous birth and spawning is proposed, illustrated with three applicable spawning models on a simulated scenario involving two parent targets spawning a total of five objects.
- 33
- Target tracking in the framework of possibility theory: The possibilistic Bernoulli filter32
The main advantage of the possibilistic Bernoulli filter, derived in this paper, is that it can operate even in the absence of precise measurement and/or dynamic model parameters.
- Novel Multi-Object Filtering Approach for Space Situational Awareness30
The observation process is indeed hindered by short observation arcs, and surveillance activities with ground-based assets in the context of space situational awareness are particularly challenging.
- Representation and estimation of stochastic populations27
It is demonstrated that this can be achieved within a measure-theoretic Bayesian paradigm and the proposed representation of stochastic populations is used for the introduction of various filtering algorithms from the most general to the most specific.
- A Tractable Forward– Backward CPHD Smoother26
To circumvent the intractability of the usual Cardinalized Probability Hypothesis Density smoother, an approximate scheme where the population of targets born until and after the starting time of the smoothing are estimated separately and where smoothing is only applied to the estimate of the former population.
- A new multi-target tracking algorithm for a large number of orbiting objects25
The HISP filter is shown on a challenging surveillance scenario built from real data for 115 satellites of PlanetLabs’ Dove constellation, and simulated observations collected from two sensors with limited coverage and measurement noise, in the presence of false positives and missed detection.
- Marker-Less Stage Drift Correction in Super-Resolution Microscopy Using the Single-Cluster PHD Filter24
A Bayesian approach is used to simultaneously track the locations of objects with different motion behaviors and the stage drift using image data obtained from fluorescence microscopy experiments.
- Tracking with MIMO sonar systems: applications to harbour surveillance23
A MIMO sonar system based scheme to tackle the difficult problem of harbour surveillance and proposes two radically different methods for the underwater target tracking problem in complex environment: a digital tracker and an analogue tracker.
- Physics and human-based information fusion for improved resident space object tracking21
This paper proposes the first exploitation of uncertain variables in a RSO tracking problem, allowing for a representation of the uncertain components reflecting the information available to the space analyst, however scarce, and nothing more.
- 20
- 20
- 18
- 16
- 16
- 16
- 15
- Spatio-temporal tracking from natural language statements using outer probability theory14
An estimation and tracking method based on the concept of outer probability measures is introduced and an estimation algorithm for handling this temporal uncertainty, along with delayed and out-of-sequence information arrival, is developed.
- 14
- 14
- Possibilistic space object tracking under epistemic uncertainty12
A refined Possibilistic Admissible Region approach is proposed, in which the initial orbital state is modeled using a novel parameter estimation method and the OPM filter is employed to integrate types of data sources in the presence of assumed ignorance.
- 12
- 11
- 11
- Uncertainty modelling and computational aspects of data association10
A novel solution to the smoothing problem for multi-object dynamical systems is proposed and evaluated and is shown to outperform existing algorithms in a range of scenarios.
- 9
- Particle Association Measures and Multiple Target Tracking9
This chapter focuses on the different ways of establishing the equations of the phd filter, using a consistent set of notations, and introduces the idea of observation path, upon which association measures are defined.
- 8
- 8
- 8
- PHD filtering with localised target number variance8
This paper proposes a first implementation of aPHD filter that also includes an estimation of localised variance in the target number following each update step and illustrates the advantage of the PHD filter + variance on simulated data from a multiple-target scenario.
- 7
- Unbiased multi-index Monte Carlo7
A new version of multi-index Monte Carlo (MIMC) is introduced that has the added advantage of reducing the computational effort, relative to i.i.d. sampling from the most precise discretization, for a given level of error.
- A filter for distinguishable and independent populations7
A multi-object filter for the resolution of joint detection/tracking problems involving multiple targets, derived from the novel Bayesian estimation framework for stochastic populations is introduced.
- 7
- Regional variance in target number: Analysis and application for multi-Bernoulli point processes7
The regional variance is derived for a multi-object representation commonly used in the tracking literature, known as the multi-Bernoulli point process, in which the multi -target state is described with a set of hypothesised tracks with associated existence probabilities.
- 7
- Identification of MultiObject Dynamical Systems: Consistency and Fisher Information6
It is shown that specific aspects of the multi-target tracking (MTT) problem such as detection failures and unknown data association lead to a loss of information which is quantified in special cases of interest.
- Hypothesised filter for independent stochastic populations6
A new filter for independent stochastic populations is studied and detailed, based on recent works introducing the concept of distinguishability in point processes, using a version of Bayes' theorem for multi-object systems.
- 6
- 6
- 6
- 5
- Improving Active Learning with a Bayesian Representation of Epistemic Uncertainty5
A particular combination of probability and possibility theories is proposed, with the aim of using the latter to specifically represent epistemic uncertainty, and it is shown how this combination leads to new active learning strategies that have desirable properties.
- 5
- Detection and estimation of partially-observed dynamical systems: an outer-measure approach5
This article proposes to use outer measures of a certain form to allow for additional flexibility in the modelling of these effects within the Bayesian paradigm and shows that such an approach can compete with standard methods even when the latter are given the true parameter values.
- 5
- Investigating Relational State Abstraction in Collaborative MARL4
This work introduces MARC (Multi-Agent Relational Critic), a simple yet effective critic architecture incorporating spatial relational inductive biases by transforming the state into a spatial graph and processing it through a relational graph neural network, and conducts a comprehensive empirical analysis.
- Robust Multi-Sensor Multi-Target Tracking Using Possibility Labeled Multi-Bernoulli Filter4
An innovative possibility Labeled Multi-Bernoulli (LMB) Filter based on the labeled Uncertain Finite Set (UFS) theory is developed which inherits the high robustness of the possibility generalized labeled multi-Bernoulli filter with simplified computational complexity.
- Multilevel Monte Carlo for Smoothing via Transport Methods4
This article considers recursive approximations of the smoothing distribution associated to partially observed stochastic differential equations (SDEs), which are observed discretely in time, and considers a new approach to replace the particle filter, using transport methods in [27].
- 4
- 4
- 4
- Possibilistic Predictive Uncertainty for Deep Learning3
Dirichlet-approximated possibilistic posterior predictions (DAPPr) is introduced, a principled framework grounded in possibility theory that achieves competitive or superior uncertainty quantification performance over state-of-the-art second-order predictors while maintaining both principled derivation and computational efficiency.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- Decentralised possibilistic inference with applications to target tracking2
The proposed decentralised inference framework based on possibility theory derives a principled fusion rule that is proven to be asymptotically exact, meaning it recovers the posterior of the optimal centralised possibilistic approach.
- 2
- Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference2
This work develops a principled formulation for performing possibilistic VI by establishing a maxitive analogue of the classical Donsker-Varadhan formulation, enabling it to derive a learning rule for possibilistic VI with exponential-family candidates and practical update rules for neural-network training, giving rise to a family of optimizers termed CBOpt.
- On Large Lag Smoothing for Hidden Markov Models2
This article introduces a novel application of the multilevel Monte Carlo (MLMC) method with a coupling based on the Knothe-Rosenblatt rearrangement, and proves that this method can approximate the afore-mentioned quantity with a mean square error (MSE) of $\mathcal{O}(\epsilon^2)$.
- 2
- 2
- 2
- 2
- 1
- 1
- Hierarchical interacting stochastic population processes1
A unified probabilistic framework for modelling systems of hierarchical interacting systems of multiple objects with interactions and hierarchies is developed, using a new result in variational calculus, Faa di Bruno's formula for Gateaux differentials.
- –
- –
- Action-Free Offline-to-Online RL via Discretised State Policies–
This work introduces a simple yet novel state discretisation transformation and proposes Offline State-Only DecQN (Algo), a value-based algorithm designed to pre-train state policies from action-free data that integrates the transformation to scale efficiently to high-dimensional problems while avoiding instability and overfitting associated with continuous state prediction.
- –
- –
- –
- –
- Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning–
This work introduces MaxMax Q-Learning, which employs an iterative process of sampling and evaluating potential next states, selecting those with maximal Q-values for learning, and demonstrates that MMQ frequently outperforms existing baselines, exhibiting enhanced convergence and sample efficiency.
- Redesigning the ensemble Kalman filter with a dedicated model of epistemic uncertainty–
The possibilistic approach motivates a robust mechanism for characterizing uncertainty which shows good performance with small sample sizes, and can outperform standard ensemble Kalman filters at given sample size, even when dealing with genuinely aleatoric uncertainty.
- –
- –
- –
- –
- Calibration of asynchronous smart phone cameras from moving objects–
The issues of acquisition, detection of moving objects, dynamic camera registration and tracking of arbitrary number of targets, and the single-cluster PHD filter are addressed.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar; position from the scholar’s ORCID record, last synced 2026-10-10. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.