2CoBel: A scalable belief function representation for 2D discernment frames

Pellicanò, Nicola; Hégarat‐Mascle, Sylvie Le; Aldea, Emanuel

doi:10.1016/j.ijar.2018.10.007

Cited by 4 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The open source 1 library 2CoBel [14] has been developed in the applicative context of crowd monitoring. Indeed, for such application, the localization has to be all the more precise that the crowd is dense.…”

Section: B the Case Of A 2d Discernment Framementioning

confidence: 99%

“…Besides this geometrical representation allowing for handling precise shapes of 2D hypotheses of interest, 2CoBel [14] provides an useful and compact representation of the interactions between FEs under the form of a Directed Acyclic Graph (DAG). In brief, any intersection between FEs can be represented by a path on the DAG.…”

Section: B the Case Of A 2d Discernment Framementioning

confidence: 99%

“…Therefore, decisions have to be taken among paths representing non empty intersections and having maximal length on the DGA. Now, since the systematic exploration of the whole graph may be numerically expensive, [14] provides some tricks for efficient exploration, in particular early avoiding non maximal length paths (by detection of subpath features).…”

Section: B the Case Of A 2d Discernment Framementioning

confidence: 99%

“…A keypoint is that the maximal length paths corresponding to non-empty intersections are the most precise hypotheses that we can consider given the BBA m. They are among the singleton hypotheses when considering the equivalent 1D discernment frame used for instance for canonical decomposition as proposed by [14]. Then, we are able to decide in favor of compound hypotheses of a 2D discernment frame, maximizing the BetP criterion (or the contour function) in an equivalent 1D discernment frame.…”

Section: B the Case Of A 2d Discernment Framementioning

confidence: 99%

“…Then, [12]- [14] propose a solution where 2 Ω elements (singleton and compound hypotheses) are no longer labelled (as for enumeration) while each element of the focal set (that is usually a small subset of 2 Ω ) is handled through its own description. Specifically, in [12], [13], the handled focal elements are described as sets of rectangles (tiles) similarly to the representation used in Interval Analysis [15], whereas [14] provides a more general representation of any 2D shapes using polygons. In both cases, belief function operators based on set relationships (intersection, union etc.)…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Camera Localization Based on Belief Clustering

Chen

Aldea

Hégarat‐Mascle

2020

2020 IEEE 23rd International Conference on Information Fusion (FUSION)

Self Cite

View full text Add to dashboard Cite

This work deals with epipole estimation related to egocentric camera localization in surveillance and security applications. Matching visual features in the images provides some evidences for various solutions, so that epipole localization can be addressed as a fusion task with a large number of sources including outlier ones. In order to deal with source imprecision and uncertainty, we rely on the belief function theory and a 2D framework suited for our application. In this framework, we address the challenges introduced by a large number of sources with a strategy based on clustering and intra-cluster fusion. The proposed method exhibits more robustness in terms of accuracy and precision when compared on real data with the standard algorithms which provide single solution. Since we provide a Basic Belief Assignment as a result, our strategy is particularly adapted for the prospective combination with additional sources of information.

show abstract

Section: B the Case Of A 2d Discernment Framementioning

confidence: 99%

Section: B the Case Of A 2d Discernment Framementioning

confidence: 99%

Section: B the Case Of A 2d Discernment Framementioning

confidence: 99%

Section: B the Case Of A 2d Discernment Framementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Camera Localization Based on Belief Clustering

Chen

Aldea

Hégarat‐Mascle

2020

2020 IEEE 23rd International Conference on Information Fusion (FUSION)

Self Cite

View full text Add to dashboard Cite

show abstract

Belief functions clustering for epipole localization

Chen

Hégarat‐Mascle

Aldea

2021

International Journal of Approximate Reasoning

View full text Add to dashboard Cite

Multistep Prediction using Point-Cloud Approximation of Continuous Belief Functions

Denœux

Kanjanatarakul

2019

2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

View full text Add to dashboard Cite

We consider the problem of quantifying prediction uncertainty in the Dempster-Shafer framework. Our approach assumes a parametric statistical model relating the variable of interest, the parameter and a pivotal random variable with known probability distribution. A predictive belief function is computed using this model and a belief function defined in the parameter space. In the case of multistep prediction, the quantity to be predicted is a vector, and the predictive belief function is defined in a multidimensional space, making its representation and manipulation difficult. To address this issue, we propose to approximate the focal sets of belief functions using point clouds, which allows us to approximate the belief and plausibility of arbitrary events with any accuracy. As an illustration, the approach is applied to the case of a first-order autoregressive process.

show abstract

2CoBel: A scalable belief function representation for 2D discernment frames

Cited by 4 publications

References 31 publications

Camera Localization Based on Belief Clustering

Camera Localization Based on Belief Clustering

Belief functions clustering for epipole localization

Multistep Prediction using Point-Cloud Approximation of Continuous Belief Functions

Contact Info

Product

Resources

About