Bayesian path estimation using the spatial attributes of a road network

Morelande, Mark R.; Duckham, Matt; Kealy, Allison; Legg, Jonathan

doi:10.1109/icassp.2015.7178740

Cited by 2 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We will call such targets source-destination aware, and as in [5]- [8] we work with finite-state processes because the arbitrary source-destination pair relationships are better captured by a cellular state space. In contrast to [6]- [8], which largely focus on applications and only model a target's destination implicitly or via an ad hoc approach, we examine explicitly whether the use of dynamic target models which George 2) Related Work: From a modelling point of view, being source-destination aware means that the initial and final target states have a specified joint probability distribution and that target dynamics are anticipative, or non-causal, reflecting the intention of the target to move towards its destination. There have been a range of approaches to incorporating available a priori information about the future within the class of Markov models, both at the estimation stage and in the target dynamics model itself.…”

Section: Introductionmentioning

confidence: 90%

“…Thus we have that any RC may be uniquely specified by the finite set of Markov bridges with probability transition matrices given by (5) and initial distributions (6). As we will see below, a more intuitive description of RCs can be found via the construction of a reciprocal process from a Markov process, which we will refer to as the base process.…”

Section: A the Markov Bridge Construction Of A Rcmentioning

confidence: 99%

“…We will call such targets source-destination aware, and as in [5]- [8] we work with finite-state processes because the arbitrary source-destination pair relationships are better captured by a cellular state space. In contrast to [6]- [8], which largely focus on applications and only model a target's destination implicitly or via an ad hoc approach, we examine explicitly whether the use of dynamic target models which George Stamatescu, Langford B White and Riley Bruce-Doust are with the School of Electrical and Electronic Engineering, The University of Adelaide, North Tce, Adelaide 5005, Australia. {George.Stamatescu, Lang.White, Riley.Bruce-Doust}@adelaide.edu.au incorporate such information can improve track extraction.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Track Extraction With Hidden Reciprocal Chains

Stamatescu

White

Bruce-Doust

2018

IEEE Trans. Automat. Contr.

View full text Add to dashboard Cite

This paper develops Bayesian track extraction algorithms for targets modelled as hidden reciprocal chains (HRC). HRC are a class of finite-state random process models that generalise the familiar hidden Markov chains (HMC). HRC are able to model the "intention" of a target to proceed from a given origin to a destination, behaviour which cannot be properly captured by a HMC. While Bayesian estimation problems for HRC have previously been studied, this paper focusses principally on the problem of track extraction, of which the primary task is confirming target existence in a set of detections obtained from thresholding sensor measurements. Simulation examples are presented which show that the additional model information contained in a HRC improves detection performance when compared to HMC models.

show abstract

Section: Introductionmentioning

confidence: 90%

Section: A the Markov Bridge Construction Of A Rcmentioning

confidence: 99%

“…We will call such targets source-destination aware, and as in [5]- [8] we work with finite-state processes because the arbitrary source-destination pair relationships are better captured by a cellular state space. In contrast to [6]- [8], which largely focus on applications and only model a target's destination implicitly or via an ad hoc approach, we examine explicitly whether the use of dynamic target models which George Stamatescu, Langford B White and Riley Bruce-Doust are with the School of Electrical and Electronic Engineering, The University of Adelaide, North Tce, Adelaide 5005, Australia. {George.Stamatescu, Lang.White, Riley.Bruce-Doust}@adelaide.edu.au incorporate such information can improve track extraction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Track Extraction With Hidden Reciprocal Chains

Stamatescu

White

Bruce-Doust

2018

IEEE Trans. Automat. Contr.

View full text Add to dashboard Cite

show abstract

“…For localizing multiple radiation sources, various formulations of this problem have been studied extensively [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 ]. Earlier works only deal with separately distributed sources [ 8 , 9 , 10 , 11 ], that is, the radiation field could be characterized by several unimodal distributions.…”

Section: Introductionmentioning

confidence: 99%

“…Thus source parameters could be estimated on the basis of the individual distributions, while the cumulative effect of multiple sources has been neglected [ 11 ]. Beyond that, mixture models and stochastic processes have also been adopted to locate the sources, incorporating the cumulative effect into these statistic models [ 12 , 13 , 14 , 15 , 16 , 17 ]. As referenced in [ 15 ], Morelande et al approximates the radiation field as Gaussian mixtures, of which the component number is selected through exhaustive cases by the CRB criterion [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

Robust Radiation Sources Localization Based on the Peak Suppressed Particle Filter for Mixed Multi-Modal Environments

Gao

Wang

Zhu

et al. 2018

Sensors

View full text Add to dashboard Cite

This paper addresses a detection problem where sparse measurements are utilized to estimate the source parameters in a mixed multi-modal radiation field. As the limitation of dimensional scalability and the unimodal characteristic, most existing algorithms fail to detect the multi-point sources gathered in narrow regions, especially with no prior knowledge about intensity and source number. The proposed Peak Suppressed Particle Filter (PSPF) method utilizes a hybrid scheme of multi-layer particle filter, mean-shift clustering technique and peak suppression correction to solve the major challenges faced by current existing algorithms. Firstly, the algorithm realizes sequential estimation of multi-point sources in a cross-mixed radiation field by using particle filtering and suppressing intensity peak value, while existing algorithms could just identify single point or spatially separated point sources. Secondly, the number of radioactive sources could be determined in a non-parametric manner as the fact that invalid particle swarms would disperse automatically. In contrast, existing algorithms either require prior information or rely on expensive statistic estimation and comparison. Additionally, to improve the prediction stability and convergent performance, distance correction module and configuration maintenance machine are developed to sustain the multimodal prediction stability. Finally, simulations and physical experiments are carried out in aspects such as different noise level, non-parametric property, processing time and large-scale estimation, to validate the effectiveness and robustness of the PSPF algorithm.

show abstract

Bayesian path estimation using the spatial attributes of a road network

Cited by 2 publications

References 15 publications

Track Extraction With Hidden Reciprocal Chains

Track Extraction With Hidden Reciprocal Chains

Robust Radiation Sources Localization Based on the Peak Suppressed Particle Filter for Mixed Multi-Modal Environments

Contact Info

Product

Resources

About