R
Roslyn A. Lau
Researcher at Defence Science and Technology Organisation
Publications - 7
Citations - 501
Roslyn A. Lau is an academic researcher from Defence Science and Technology Organisation. The author has contributed to research in topics: Belief propagation & Approximate inference. The author has an hindex of 5, co-authored 7 publications receiving 353 citations. Previous affiliations of Roslyn A. Lau include NICTA.
Papers
More filters
Journal ArticleDOI
Message Passing Algorithms for Scalable Multitarget Tracking
Florian Meyer,Thomas Kropfreiter,Jason L. Williams,Roslyn A. Lau,Franz Hlawatsch,Paolo Braca,Moe Z. Win +6 more
TL;DR: This tutorial paper advocates a recently proposed paradigm for scalable multitarget tracking that is based on message passing or, more concretely, the loopy sum–product algorithm, which provides a highly effective, efficient, and scalable solution to the probabilistic data association problem, a major challenge in multitargettracking.
Journal ArticleDOI
Approximate evaluation of marginal association probabilities with belief propagation
Jason L. Williams,Roslyn A. Lau +1 more
TL;DR: A graphical model formulation of data association is presented and an approximate inference method, belief propagation (BP), is applied to obtain estimates of marginal association probabilities to prove that BP is guaranteed to converge, and bound the number of iterations necessary.
Proceedings ArticleDOI
Convergence of loopy belief propagation for data association
Jason L. Williams,Roslyn A. Lau +1 more
TL;DR: A graphical model approach to data association is presented and an approximate inference method, loopy belief propagation, is applied to obtain the marginal association weights to reveal loopy beliefs propagation as a highly attractive method for approximate calculation of joint association weights.
Journal ArticleDOI
Multiple Scan Data Association by Convex Variational Inference
Jason L. Williams,Roslyn A. Lau +1 more
TL;DR: In this article, a convex free energy is constructed using the recently proposed fractional free energy (FFE), and a convergent, BP-like algorithm is provided for the single scan FFE, and employed in optimizing the multiple scan free energy using primal-dual coordinate ascent.
Journal ArticleDOI
Approximate evaluation of marginal association probabilities with belief propagation
Jason L. Williams,Roslyn A. Lau +1 more
TL;DR: In this article, the authors present a graphical model formulation of data association and apply an approximate inference method, belief propagation (BP), to obtain estimates of marginal association probabilities, and prove that BP is guaranteed to converge, and bound the number of iterations necessary.