Multiple Object Tracking in Unknown Backgrounds with Labeled Random Finite Sets

Abstract

This paper proposes an on-line multiple object tracking algorithm that can operate in unknown background. In a majority of multiple object tracking applications, model parameters for background processes such as clutter and detection are unknown and vary with time, hence the ability of the algorithm to adaptively learn the these parameters is essential in practice. In this work, we detail how the Generalized Labeled Multi Bernouli (GLMB) filter a tractable and provably Bayes optimal multi-object tracker can be tailored to learn clutter and detection parameters on the fly while tracking. Provided that these background model parameters do not fluctuate rapidly compared to the data rate, the proposed algorithm can adapt to the unknown background yielding better tracking performance.

12 pages, 10 figures

References in corpus (3)

• Robust Distributed Fusion with Labeled Random Finite Sets
• Multi-Target Tracking with Time-Varying Clutter Rate and Detection Profile: Application to Time-lapse Cell Microscopy Sequences
• A Generalized Labeled Multi-Bernoulli Filter for Maneuvering Targets

Cited by in corpus (8)

• A Bayesian Filter for Multi-view 3D Multi-object Tracking with Occlusion Handling
• Tracking Cells and their Lineages via Labeled Random Finite Sets
• An Overview of Multi-Object Estimation via Labeled Random Finite Set
• Robust multi-sensor Generalized Labeled Multi-Bernoulli filter
• Stochastic Neural Networks for Automatic Cell Tracking in Microscopy Image Sequences of Bacterial Colonies
• Filtering Point Targets via Online Learning of Motion Models
• Randomized Multiple Model Multiple Hypothesis Tracking
• Multi-object Tracking in Unknown Detection Probability with the PMBM Filter