Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Transactions on Machine Learning Research Journal Year : 2024

Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation

Abstract

In this paper, we present an unsupervised probabilistic model and associated estimation algorithm for multi-object tracking (MOT) based on a dynamical variational autoencoder (DVAE), called DVAE-UMOT. The DVAE is a latent-variable deep generative model that can be seen as an extension of the variational autoencoder for the modeling of temporal sequences. It is included in DVAE-UMOT to model the objects' dynamics, after being pre-trained on an unlabeled synthetic dataset of single-object trajectories. Then the distributions and parameters of DVAE-UMOT are estimated on each multi-object sequence to track using the principles of variational inference: Definition of an approximate posterior distribution of the latent variables and maximization of the corresponding evidence lower bound of the data likehood function. DVAE-UMOT is shown experimentally to compete well with and even surpass the performance of two state-of-the-art probabilistic MOT models. Code and data are publicly available.
Fichier principal
Vignette du fichier
2202.09315.pdf (1.38 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03584014 , version 1 (22-02-2022)

Licence

Attribution

Identifiers

  • HAL Id : hal-03584014 , version 1

Cite

Xiaoyu Lin, Laurent Girin, Xavier Alameda-Pineda. Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation. Transactions on Machine Learning Research Journal, 2024, pp.1-19. ⟨hal-03584014⟩
146 View
147 Download

Share

Gmail Facebook X LinkedIn More