Corpus ID: 201645296

Spooky effect in optimal OSPA estimation and how GOSPA solves it

@article{GarcaFernndez2019SpookyEI,
  title={Spooky effect in optimal OSPA estimation and how GOSPA solves it},
  author={{\'A}ngel F. Garc{\'i}a-Fern{\'a}ndez and Lennart Svensson},
  journal={2019 22th International Conference on Information Fusion (FUSION)},
  year={2019},
  pages={1-8}
}
In this paper, we show the spooky effect at a distance that arises in optimal estimation of multiple targets with the optimal sub-pattern assignment (OSPA) metric. This effect refers to the fact that if we have several independent potential targets at distant locations, a change in the probability of existence of one of them can completely change the optimal estimation of the rest of the potential targets. As opposed to OSPA, the generalised OSPA (GOSPA) metric $(\alpha=2)$ penalises… Expand

Figures and Topics from this paper

A Metric on the Space of Finite Sets of Trajectories for Evaluation of Multi-Target Tracking Algorithms
TLDR
A lower bound for the metric is proposed, which is also a metric for sets of trajectories and is computable in polynomial time using linear programming and extended to random finite sets of trajectoryories. Expand
Decentralized Poisson Multi-Bernoulli Filtering for Extended Target Tracking
TLDR
A decentralized Poisson multi-Bernoulli filter is proposed to track multiple extended targets using multiple sensors and an efficient implementation is achieved by parametric state representation, utilization of single hypothesis tracks, and fusion of target information based on a fusion mapping. Expand
Decentralized Poisson Multi-Bernoulli Filtering for Vehicle Tracking
TLDR
A decentralized Poisson multi-Bernoulli filter is proposed to track multiple vehicles using multiple high-resolution sensors and an efficient implementation is achieved by parametric state representation, utilization of single hypothesis tracks, and fusion of vehicle information based on a fusion mapping. Expand
An analysis on metric-driven multi-target sensor management: GOSPA versus OSPA
  • 'Angel F. Garc'ia-Fern'andez, Marcel Hernandez, S. Maskell
  • Engineering, Computer Science
  • 2021
This paper presents an analysis on sensor management using a cost function based on a multi-target metric, in particular, the optimal subpattern-assignment (OSPA) metric, the unnormalised OSPAExpand
A time-weighted metric for sets of trajectories to assess multi-object tracking algorithms
  • 'Angel F. Garc'ia-Fern'andez, Abu Sajana Rahmathullah, Lennart Svensson
  • Computer Science, Mathematics
  • 2021
This paper proposes a metric for sets of trajectories to evaluate multi-object tracking algorithms that includes timeweighted costs for localisation errors of properly detected targets, for falseExpand

References

SHOWING 1-10 OF 33 REFERENCES
Generalized optimal sub-pattern assignment metric
TLDR
The generalized optimal sub-pattern assignment metric is presented, which allows us to penalize localization errors for detected targets and the errors due to missed and false targets, as indicated by traditional multiple target tracking (MTT) performance measures, in a sound manner. Expand
"Spooky Action at a Distance" in the Cardinalized Probability Hypothesis Density Filter
The cardinalized probability hypothesis density (CPHD) filter is a recursive Bayesian algorithm for estimating multiple target states with varying target number in clutter. In the present work, it isExpand
Shooting two birds with two bullets: How to find Minimum Mean OSPA estimates
TLDR
This manuscript derives a general algorithm which provided the optimal estimator which minimize the Mean OSPA (MOSPA), and calls such an estimator a Minimum MOSPA (MMOSPA) estimator. Expand
An approximate Minimum MOSPA estimator
TLDR
This paper derives an approximation to the MMOSPA estimator in the two-target case, which is generally very complicated, based on minimizing a Bhattacharyya-like bound, which has a particularly nice form for Gaussian mixtures. Expand
Multitarget miss distance via optimal assignment
  • J. R. Hoffman, R. Mahler
  • Computer Science
  • IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans
  • 2004
TLDR
A comprehensive L/sub p/-type theory of distance metrics for multitarget (and, more generally, multiobject) systems is introduced and it is shown that this theory extends, and provides a rigorous theoretical basis for, an intuitively appealing optimal-assignment approach proposed by Drummond for evaluating the performance of multitarget tracking algorithms. Expand
Metrics for Evaluating Feature-Based Mapping Performance
TLDR
The cardinalized optimal linear assignment (COLA) metric is introduced, as a complement to the OSPA metric, for feature map evaluation, and is shown to provide a robust solution for the evaluation of map estimation errors in an intuitive manner. Expand
A Geometrical Look at MOSPA Estimation Using Transportation Theory
TLDR
This letter proves that the equivalence of Wasserstein distance with the MOSPA measure holds for general types of the probability density function, and allows one recent finding in the computational geometry literature to show that the Minimum M OSPA (MMOSPA) estimates are the centroids of additive weighted Voronoi regions with a specific choice of the weights. Expand
Set JPDA Filter for Multitarget Tracking
TLDR
It is shown that when targets are closely spaced, traditional tracking algorithms can be adjusted to perform better under a performance measure that disregards identity, and an adjusted version of the joint probabilistic data association (JPDA) filter is proposed, which is called set JPDA (SJPDA). Expand
Polynomial-Time Algorithms for the Exact MMOSPA Estimate of a Multi-Object Probability Density Represented by Particles
TLDR
The first exact polynomial-time algorithms for calculating the MMOSPA estimate for probability densities that are represented by particles are presented, which can be found by means of enumerating the cells of a hyperplane arrangement. Expand
A Joint Multitarget Estimator for the Joint Target Detection and Tracking Filter
TLDR
This paper proposes a joint multitarget (JoM) estimator for the joint target detection and tracking (JoTT) filter and demonstrates that the JoM estimator achieves better track management performance in terms of track confirmation latency and track maintenance than the MaM estimators for different values of detection probability. Expand
...
1
2
3
4
...