pith. sign in

arxiv: 2311.06139 · v3 · pith:XXHJK4KHnew · submitted 2023-11-10 · 📊 stat.AP

Joint Object Tracking and Intent Recognition

Jiaming Liang , Bashar I. Ahmad , Simon Godsill This is my paper

Pith reviewed 2026-05-25 08:15 UTC · model grok-4.3

classification 📊 stat.AP
keywords object trackingintent recognitionBayesian inferencesequential Monte Carloparticle filteringvirtual leadermaneuvering targetsRao-Blackwellisation
0
0 comments X

The pith

A Bayesian framework augments target state with hidden intent and estimates both via particle filtering on virtual leader models.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper sets out a method to infer the joint posterior over an object's kinematic state and its unknown goal or intent, such as waypoints or a final destination. Latent intent models inside a virtual leader formulation link the hidden goal to the target's observed motion at each instant. Sequential Monte Carlo sampling, with Rao-Blackwellisation, performs the simultaneous estimation and handles cases where intent changes over time or the target maneuvers sharply. The approach is tested on both simulated trajectories and real radar returns. If successful, it yields filters that anticipate where a target is heading rather than only where it is now.

Core claim

The paper claims that the posterior of an augmented state—kinematic variables plus latent intent—can be recursively estimated by embedding several intent models inside a virtual leader structure, applying suitable motion models for maneuvering targets, and running a Rao-Blackwellised sequential Monte Carlo sampler that treats the unknown intent as a dynamically evolving quantity that may take any value in the state space.

What carries the argument

Virtual leader formulation containing multiple latent intent models that encode the effect of the target's hidden goal on its instantaneous dynamics.

If this is right

  • Intent can be inferred even when it changes during the observation window and can lie anywhere in the state space.
  • The same sampler works with a range of motion models that cover highly maneuvering objects.
  • Rao-Blackwellisation reduces variance in the kinematic-state estimates relative to a standard particle filter.
  • The method produces usable results on both simulated data and recorded radar measurements.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Surveillance systems could use the inferred intent to trigger earlier alerts or resource allocation before a target reaches a sensitive area.
  • The framework could be extended to multiple targets whose intents interact, provided the virtual-leader models are coupled.
  • Real-time implementations would need to monitor particle degeneracy when intent switches rapidly.

Load-bearing premise

Latent intent models placed inside a virtual leader are adequate to represent how an unobserved goal shapes the target's current motion.

What would settle it

Run the filter on radar tracks whose final destination is known in advance and check whether the posterior mass on intent converges to the true destination region before the target arrives.

Figures

Figures reproduced from arXiv: 2311.06139 by Bashar I. Ahmad, Jiaming Liang, Simon Godsill.

Figure 1
Figure 1. Figure 1: Radar observations of a drone surveying an area with predefined waypoints; truth trajectory from onboard GPS is shown. contains the 3-D Cartesian coordinates1 of targets of interest within the radar field of coverage, specifically: a) a DJI Inspire II quadcopter drone (diameter ≈ 0.5m and weight ≈ 3.5 kg) undertaking a site surveying task within an authorised flying zone A whilst following waypoints-driven… view at source ↗
Figure 2
Figure 2. Figure 2: Drone track estimation results (green crosses are radar observations). The dotted solid lines are posterior mean filtering estimates for VL-D-KF, VL-PC-RBVRPF and standard Kalman filter (i.e. no intent modelling); posterior confidence ellipses are shown. the ability of the introduced VL-D-KF and VL-PC-RBVRPF to predict the waypoints well in advance. The former exhibits higher variability in predictions (i.… view at source ↗
Figure 3
Figure 3. Figure 3: Waypoint estimates showing filtering posterior of the desti￾nation location along the X and Y axes. Vertical red dashed lines indicate time instants when the drone reached a waypoint. Red solid horizontal lines are true waypoint positions in the corresponding axis [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Destination switching time τ with smoothing; vertical red dashed lines indicate time instant drone reached a waypoint [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Threat detection with the drone exiting and re-entering a permitted zone A. Left: target trajectory, waypoints and probability Pr(Des = A|m0:n) as provided by VL-PC-RBVRPF; t0 is the flight start time. Right: probability of destination being within the zone given by the two the proposed algorithms VL-D-KF and VL-PC￾RBVRPF; vertical dashed lines are time instant the drone reach each of the waypoints [PITH_… view at source ↗
Figure 6
Figure 6. Figure 6: Threat detection example with results of estimating the probability that the protected region is the intended destination of two targets of interest. The trajectories color reflects the probabilities produced by the VL-PC-RBVRPF method. Subplots show the calcu￾lated probabilities over-time for VL-PC-RBVRPF and VL-D-KF. Finally, the presented Bayesian approach provides the means to continuously estimate the… view at source ↗
read the original abstract

This paper presents a Bayesian framework for inferring the posterior of the augmented state of a target, incorporating its underlying goal or intent, such as any intermediate waypoints and/or the final destination. Thus, it is for joint object tracking and intent recognition. Several latent intent models are proposed here within a virtual leader formulation. They capture the influence of the target's hidden goal on its instantaneous behaviour. In this context, various motion models, including for highly maneuvering objects, are also considered. The a priori unknown target intent (e.g. destination) can dynamically change over time and take any value within the state space (e.g. a location or spatial region). A sequential Monte Carlo (particle filtering) approach is introduced for the simultaneous estimation of the target's (kinematic) state and its intent. Rao-Blackwellisation is employed to enhance the statistical performance of the inference routine. Simulated data and real radar measurements are used to demonstrate the efficacy of the proposed techniques.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 3 minor

Summary. The paper presents a Bayesian framework for joint object tracking and intent recognition. It augments the target state with a latent intent variable (waypoints or destination) modeled via several virtual-leader intent models that influence instantaneous motion. Various motion models (including for highly maneuvering targets) are considered. Inference uses sequential Monte Carlo (particle filtering) with Rao-Blackwellisation to estimate the joint posterior over kinematics and intent; the intent can change dynamically and take values anywhere in the state space. Efficacy is shown on simulated data and real radar measurements.

Significance. If the technical claims hold, the work supplies a direct, implementable extension of standard SMC methods to goal-aware tracking. The virtual-leader construction and Rao-Blackwellisation are standard tools applied to an augmented state; the main contribution is therefore the concrete formulation and the empirical demonstration on radar data rather than a new theoretical primitive. Reproducible code or machine-checked derivations are not mentioned.

minor comments (3)
  1. The abstract states that 'several latent intent models are proposed' but does not indicate how many models, their parametric forms, or the prior over model index; a dedicated subsection or table listing the models and their transition kernels would improve reproducibility.
  2. The description of Rao-Blackwellisation is brief; the paper should explicitly state which variables are marginalized analytically and which remain in the particle representation (e.g., § on inference algorithm).
  3. The real-radar experiment section should report the specific sensor characteristics, clutter model, and any preprocessing steps applied to the measurements.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the constructive review and the recommendation of minor revision. The report provides a clear summary of the work but does not enumerate any specific major comments requiring point-by-point rebuttal. We therefore have no individual referee comments to address in the responses section below.

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The described framework is a direct application of existing sequential Monte Carlo and Rao-Blackwellised particle filtering techniques to an augmented state that includes a latent intent variable under virtual-leader motion models. No load-bearing step reduces by construction to a fitted parameter, self-definition, or self-citation chain; the derivation applies standard Bayesian inference tools to the joint tracking/intent problem without renaming known results or smuggling ansatzes via internal citations.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

Only abstract available so ledger is minimal; no free parameters or invented entities with independent evidence are identifiable.

axioms (1)
  • domain assumption Latent intent models within a virtual leader formulation capture the influence of hidden goal on instantaneous behaviour.
    Stated as the basis for the proposed models in the abstract.
invented entities (1)
  • Latent intent models in virtual leader formulation no independent evidence
    purpose: To model how hidden goal affects target motion for joint estimation.
    Introduced as part of the framework in the abstract.

pith-pipeline@v0.9.0 · 5688 in / 1195 out tokens · 31078 ms · 2026-05-25T08:15:12.852552+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

58 extracted references · 58 canonical work pages

  1. [1]

    Spatiotemporal trajectory models for metalevel target tracking,

    M. Fanaswala and V . Krishnamurthy, “Spatiotemporal trajectory models for metalevel target tracking,” IEEE Aerospace and Electronic Systems Magazine, vol. 30, no. 1, pp. 16–31, 2015

    work page 2015

  2. [2]

    Bayesian intent prediction in object tracking using bridging distributions,

    B. I. Ahmad, J. K. Murphy, P. M. Langdon, and S. J. Godsill, “Bayesian intent prediction in object tracking using bridging distributions,” IEEE Transactions on Cybernetics , vol. 48, no. 1, pp. 215–227, 2018

    work page 2018

  3. [3]

    Malicious AIS spoofing and abnormal stealth deviations: A comprehensive statistical framework for maritime anomaly detection,

    E. d’Afflisio, P. Braca, and P. Willett, “Malicious AIS spoofing and abnormal stealth deviations: A comprehensive statistical framework for maritime anomaly detection,” IEEE Transactions on Aerospace and Electronic Systems, 2021

    work page 2021

  4. [4]

    Detection of malicious intent in non-cooperative drone surveillance,

    J. Liang, B. I. Ahmad, M. Jahangir, and S. Godsill, “Detection of malicious intent in non-cooperative drone surveillance,” in 2021 Sensor Signal Processing for Defence Conference (SSPD) , 2021

    work page 2021

  5. [5]

    Embedded stochastic syntactic processes: A class of stochastic grammars equivalent by embedding to a Markov process,

    F. Carravetta and L. B. White, “Embedded stochastic syntactic processes: A class of stochastic grammars equivalent by embedding to a Markov process,” IEEE Transactions on Aerospace and Electronic Systems , vol. 57, no. 4, pp. 1996–2005, 2021

    work page 1996

  6. [6]

    Sequential dynamic leadership inference using Bayesian Monte Carlo methods,

    Q. Li, B. I. Ahmad, and S. J. Godsill, “Sequential dynamic leadership inference using Bayesian Monte Carlo methods,” IEEE Transactions on Aerospace and Electronic Systems , 2021

    work page 2021

  7. [7]

    Joint stochastic prediction of vessel kinematics and destination based on a maritime traffic graph,

    T. Tengesdal, L. M. Millefiori, P. Braca, and E. Brekke, “Joint stochastic prediction of vessel kinematics and destination based on a maritime traffic graph,” in2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) . IEEE, 2022, pp. 1–8

    work page 2022

  8. [8]

    R. W. Beard and T. W. McLain, Small unmanned aircraft: Theory and practice. Princeton university press, 2012

    work page 2012

  9. [9]

    Stochastic linear hybrid systems: Modeling, estimation, and application in air traffic control,

    C. E. Seah and I. Hwang, “Stochastic linear hybrid systems: Modeling, estimation, and application in air traffic control,” IEEE Transactions on Control Systems Technology, vol. 17, no. 3, pp. 563–575, 2009

    work page 2009

  10. [10]

    Modeling vessel kinematics using a stochastic mean-reverting process for long-term prediction,

    L. M. Millefiori, P. Braca, K. Bryan, and P. Willett, “Modeling vessel kinematics using a stochastic mean-reverting process for long-term prediction,” IEEE Transactions on Aerospace and Electronic Systems , vol. 52, no. 5, pp. 2313–2330, 2016

    work page 2016

  11. [11]

    Conditionally Markov modeling and optimal estimation for trajectory with waypoints and destination,

    R. Rezaie, X. R. Li, and V . P. Jilkov, “Conditionally Markov modeling and optimal estimation for trajectory with waypoints and destination,” IEEE Transactions on Aerospace and Electronic Systems, vol. 57, no. 4, pp. 2006–2020, 2021

    work page 2006

  12. [12]

    Algorithms for the incorporation of predictive information in surveillance theory,

    D. A. Castanon, B. C. Levy, and A. S. Willsky, “Algorithms for the incorporation of predictive information in surveillance theory,” Interna- tional Journal of Systems Science , vol. 16, no. 3, pp. 367–382, 1985

    work page 1985

  13. [13]

    Recursive filtering and smoothing for reciprocal Gaussian processes with Dirichlet boundary conditions,

    E. Baccarelli and R. Cusani, “Recursive filtering and smoothing for reciprocal Gaussian processes with Dirichlet boundary conditions,”IEEE Transactions on Signal Processing , vol. 46, no. 3, pp. 790–795, 1998

    work page 1998

  14. [14]

    Modelling and estimation for finite state reciprocal processes,

    F. Carravetta and L. B. White, “Modelling and estimation for finite state reciprocal processes,” IEEE Transactions on Automatic Control, vol. 57, no. 9, pp. 2190–2202, 2012

    work page 2012

  15. [15]

    State space realisations and optimal smoothing for Gaussian generalised reciprocal processes,

    L. B. White and F. Carravetta, “State space realisations and optimal smoothing for Gaussian generalised reciprocal processes,” IEEE Trans- actions on Automatic Control , 2020

    work page 2020

  16. [16]

    Detection of anomalous trajectory patterns in target tracking via stochastic context-free grammars and reciprocal process models,

    M. Fanaswala and V . Krishnamurthy, “Detection of anomalous trajectory patterns in target tracking via stochastic context-free grammars and reciprocal process models,” IEEE Journal of Selected Topics in Signal Processing, vol. 7, no. 1, pp. 76–90, 2013

    work page 2013

  17. [17]

    Gaussian conditionally Markov sequences: Dynamic models and representations of reciprocal and other classes,

    R. Rezaie and X. R. Li, “Gaussian conditionally Markov sequences: Dynamic models and representations of reciprocal and other classes,” IEEE Transactions on Signal Processing , vol. 68, pp. 155–169, 2019

    work page 2019

  18. [18]

    Syntactic enhancement to vsimm for roadmap based anomalous trajectory detection: A natural language processing approach,

    V . Krishnamurthy and S. Gao, “Syntactic enhancement to vsimm for roadmap based anomalous trajectory detection: A natural language processing approach,” IEEE Transactions on Signal Processing, vol. 66, no. 20, pp. 5212–5227, Oct 2018

    work page 2018

  19. [19]

    Target tracking problems subject to kinematic constraints,

    M. Tahk and J. L. Speyer, “Target tracking problems subject to kinematic constraints,” IEEE transactions on automatic control , vol. 35, no. 3, pp. 324–326, 1990

    work page 1990

  20. [20]

    On destination prediction based on Markov bridging distributions,

    J. Liang, B. I. Ahmad, R. Gan, P. Langdon, R. Hardy, and S. Godsill, “On destination prediction based on Markov bridging distributions,” IEEE Signal Processing Letters , vol. 26, no. 11, pp. 1663–1667, Nov 2019. 11

    work page 2019

  21. [21]

    State estima- tion with a destination constraint using pseudo-measurements,

    G. Zhou, K. Li, X. Chen, L. Wu, and T. Kirubarajan, “State estima- tion with a destination constraint using pseudo-measurements,” Signal Processing, vol. 145, pp. 155–166, 2018

    work page 2018

  22. [22]

    Constrained state estimation using noisy destination information,

    G. Zhou, K. Li, and T. Kirubarajan, “Constrained state estimation using noisy destination information,” Signal Processing, vol. 166, p. 107226, 2020

    work page 2020

  23. [23]

    Intent inference for hand pointing gesture-based interactions in vehicles,

    B. I. Ahmad, J. K. Murphy, P. M. Langdon, S. J. Godsill, R. Hardy, and L. Skrypchuk, “Intent inference for hand pointing gesture-based interactions in vehicles,” IEEE Transactions on Cybernetics , vol. 46, no. 4, pp. 878–889, 2016

    work page 2016

  24. [24]

    Simultaneous intent prediction and state estimation using an intent-driven intrinsic coordinate model,

    J. Liang, B. I. Ahmad, and S. Godsill, “Simultaneous intent prediction and state estimation using an intent-driven intrinsic coordinate model,” in 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP) , 2020, pp. 1–6

    work page 2020

  25. [25]

    Modeling and state estimation of linear destination-constrained dynamic systems,

    L. Xu, X. R. Li, Y . Liang, and Z. Duan, “Modeling and state estimation of linear destination-constrained dynamic systems,” IEEE Transactions on Signal Processing , 2022

    work page 2022

  26. [26]

    R. P. S. Mahler, Statistical Multisource-Multitarget Information Fusion . USA: Artech House, Inc., 2007

    work page 2007

  27. [27]

    Detection and tracking of coordinated groups,

    S. K. Pang, J. Li, and S. J. Godsill, “Detection and tracking of coordinated groups,” IEEE Transactions on Aerospace and Electronic Systems, vol. 47, no. 1, pp. 472–502, January 2011

    work page 2011

  28. [28]

    Group and extended object tracking,

    D. J. Salmond and N. J. Gordon, “Group and extended object tracking,” in Signal and Data Processing of Small Targets 1999 , O. E. Drummond, Ed., vol. 3809, International Society for Optics and Photonics. SPIE, 1999, pp. 284 – 296. [Online]. Available: https://doi.org/10.1117/12.364028

    work page doi:10.1117/12.364028 1999

  29. [29]

    A SMC sampler for joint tracking and destination estimation from noisy data,

    L. Vladimirov and S. Maskell, “A SMC sampler for joint tracking and destination estimation from noisy data,” in2020 IEEE 23rd International Conference on Information Fusion (FUSION) , 2020, pp. 1–8

    work page 2020

  30. [30]

    Intelligent interactive displays in vehicles with intent prediction: A Bayesian framework,

    B. I. Ahmad, J. K. Murphy, S. Godsill, P. Langdon, and R. Hardy, “Intelligent interactive displays in vehicles with intent prediction: A Bayesian framework,” IEEE Signal Processing Magazine, vol. 34, no. 2, pp. 82–94, 2017

    work page 2017

  31. [31]

    Bayesian intent prediction for fast maneuvering objects using variable rate particle filters,

    R. Gan, J. Liang, B. Ahmad, and S. Godsill, “Bayesian intent prediction for fast maneuvering objects using variable rate particle filters,” in 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP), 2019

    work page 2019

  32. [32]

    Modeling intent and destination prediction within a Bayesian framework: Predictive touch as a usecase,

    R. Gan, J. Liang, B. I. Ahmad, and S. Godsill, “Modeling intent and destination prediction within a Bayesian framework: Predictive touch as a usecase,” Data-Centric Engineering, vol. 1, p. e12, 2020

    work page 2020

  33. [33]

    L ´evy state-space models for tracking and intent prediction of highly maneuverable objects,

    R. Gan, B. I. Ahmad, and S. J. Godsill, “L ´evy state-space models for tracking and intent prediction of highly maneuverable objects,” IEEE Transactions on Aerospace and Electronic Systems, vol. 57, no. 4, 2021

    work page 2021

  34. [34]

    Forecasting high- frequency futures returns using online Langevin dynamics,

    H. L. Christensen, J. Murphy, and S. J. Godsill, “Forecasting high- frequency futures returns using online Langevin dynamics,” IEEE Jour- nal of Selected Topics in Signal Processing , vol. 6, no. 4, pp. 366–380, 2012

    work page 2012

  35. [35]

    Models and algorithms for tracking of maneuvering objects using variable rate particle filters,

    S. J. Godsill, J. Vermaak, W. Ng, and J. F. Li, “Models and algorithms for tracking of maneuvering objects using variable rate particle filters,” Proceedings of the IEEE , vol. 95, no. 5, pp. 925–952, 2007

    work page 2007

  36. [36]

    Particle smoothing algorithms for variable rate models,

    P. Bunch and S. Godsill, “Particle smoothing algorithms for variable rate models,” IEEE Transactions on Signal Processing , vol. 61, no. 7, pp. 1663–1675, 2013

    work page 2013

  37. [37]

    Intent prediction of pedestrians via motion trajectories using stacked recurrent neural networks,

    K. Saleh, M. Hossny, and S. Nahavandi, “Intent prediction of pedestrians via motion trajectories using stacked recurrent neural networks,” IEEE Transactions on Intelligent Vehicles, vol. 3, no. 4, pp. 414–424, 2018

    work page 2018

  38. [38]

    Discriminatively learning inverse opti- mal control models for predicting human intentions,

    S. Gaurav and B. D. Ziebart, “Discriminatively learning inverse opti- mal control models for predicting human intentions,” in International Conference on Autonomous Agents and Multiagent Systems , 2019

    work page 2019

  39. [39]

    Multimodal interaction-aware motion prediction for autonomous street crossing,

    N. Radwan, W. Burgard, and A. Valada, “Multimodal interaction-aware motion prediction for autonomous street crossing,” The International Journal of Robotics Research , vol. 39, no. 13, pp. 1567–1598, 2020

    work page 2020

  40. [40]

    Human motion trajectory prediction: A survey,

    A. Rudenko, L. Palmieri, M. Herman, K. M. Kitani, D. M. Gavrila, and K. O. Arras, “Human motion trajectory prediction: A survey,” The International Journal of Robotics Research, vol. 39, no. 8, pp. 895–935, 2020

    work page 2020

  41. [41]

    Intention-aware motion modeling using GP priors with conditional kernels,

    L. Xu, Z. Hou, M. Mallick, and Y . Fang, “Intention-aware motion modeling using GP priors with conditional kernels,” in 2022 25th International Conference on Information Fusion (FUSION) . IEEE, 2022, pp. 1–7

    work page 2022

  42. [42]

    Øksendal, Stochastic differential equations: an introduction with applications

    B. Øksendal, Stochastic differential equations: an introduction with applications. Springer-Verlag Berlin Heidelberg, 2003

    work page 2003

  43. [43]

    S ¨arkk¨a and A

    S. S ¨arkk¨a and A. Solin, Applied Stochastic Differential Equations , ser. Institute of Mathematical Statistics Textbooks. Cambridge University Press, 2019

    work page 2019

  44. [44]

    Piecewise-deterministic Markov processes: A general class of non-diffusion stochastic models,

    M. H. A. Davis, “Piecewise-deterministic Markov processes: A general class of non-diffusion stochastic models,”Journal of the Royal Statistical Society. Series B (Methodological) , vol. 46, no. 3, pp. 353–388, 1984

    work page 1984

  45. [45]

    Monte Carlo filtering of piecewise deterministic processes,

    N. Whiteley, A. M. Johansen, and S. Godsill, “Monte Carlo filtering of piecewise deterministic processes,” Journal of Computational and Graphical Statistics, vol. 20, no. 1, pp. 119–139, 2011

    work page 2011

  46. [46]

    Particle filters for continuous-time jump models in tracking applications,

    S. Godsill, “Particle filters for continuous-time jump models in tracking applications,” in ESAIM: Proceedings, vol. 19. EDP Sciences, 2007, pp. 39–52

    work page 2007

  47. [47]

    On sequential Monte Carlo sampling methods for Bayesian filtering,

    A. Doucet, S. Godsill, and C. Andrieu, “On sequential Monte Carlo sampling methods for Bayesian filtering,” Statistics and computing , vol. 10, no. 3, pp. 197–208, 2000

    work page 2000

  48. [48]

    Jacobsen, Point process theory and applications: marked point and piecewise deterministic processes

    M. Jacobsen, Point process theory and applications: marked point and piecewise deterministic processes . Boston: Birkh ¨auser, MA, 2006

    work page 2006

  49. [49]

    Mixture kalman filters,

    R. Chen and J. S. Liu, “Mixture kalman filters,” Journal of the Royal Statistical Society: Series B (Statistical Methodology) , vol. 62, no. 3, pp. 493–508, 2000

    work page 2000

  50. [50]

    C. P. Robert and G. Casella, Monte Carlo statistical methods; 2nd ed. , ser. Springer texts in statistics. Berlin: Springer, 2005

    work page 2005

  51. [51]

    Rao-blackwellised variable rate particle filters,

    M. R. Morelande and N. Gordon, “Rao-blackwellised variable rate particle filters,” in 2009 12th International Conference on Information Fusion, 2009, pp. 1–8

    work page 2009

  52. [52]

    Sequential Monte Carlo methods for dynamic systems,

    J. S. Liu and R. Chen, “Sequential Monte Carlo methods for dynamic systems,” Journal of the American Statistical Association , vol. 93, no. 443, pp. 1032–1044, 1998

    work page 1998

  53. [53]

    Marginalized particle filters for mixed linear/nonlinear state-space models,

    T. Sch ¨on, F. Gustafsson, and P.-J. Nordlund, “Marginalized particle filters for mixed linear/nonlinear state-space models,”IEEE Transactions on Signal Processing , vol. 53, no. 7, pp. 2279–2289, 2005

    work page 2005

  54. [54]

    Lookahead strategies for sequential Monte Carlo,

    M. Lin, R. Chen, and J. S. Liu, “Lookahead strategies for sequential Monte Carlo,” Statistical Science, vol. 28, no. 1, pp. 69 – 94, 2013

    work page 2013

  55. [55]

    Anderson and J

    B. Anderson and J. Moore, Optimal Filtering. Englewood Cliffs, NJ: Prentice-Hall, 1979

    work page 1979

  56. [56]

    A. C. Harvey, Forecasting, structural time series models and the Kalman filter. Cambridge university press, 1990

    work page 1990

  57. [57]

    Robust drone classification using two-stage decision trees and results from SESAR SAFIR trials,

    M. Jahangir, B. I. Ahmad, and C. J. Baker, “Robust drone classification using two-stage decision trees and results from SESAR SAFIR trials,” in 2020 IEEE International Radar Conference (RADAR) . IEEE, 2020, pp. 636–641

    work page 2020

  58. [58]

    Estimation of drone intention using trajectory frequency defined in radar’s measurement phase planes,

    J. Yun, D. Anderson, and F. Fioranelli, “Estimation of drone intention using trajectory frequency defined in radar’s measurement phase planes,” IET Radar, Sonar & Navigation , 2023

    work page 2023